Upload folder using huggingface_hub (#13)

- eea0e409d3f32ac71dba2e5f413e44a00141c7a60096c650669b150ac75b0f9c (4de78c187d3c62c2ca75018e339d6b774a31d5bd)
- 723d67775f0445b776fbe2fed8500964eb243bd9f503646933789261e1e3e822 (1fb0a283539837e81ae5a0f3e993caa487e3bae5)
- b255c4858212deb19682717f8d2b20d1ff6385fc0ba340a7d9019f9251af39dc (3dcf4831d52a67094bf2decb54c797f1813eaaaf)
- 17d2abaae6c8377c78f7681759342e01a1f6e06df3430594636301b1e5a3efb6 (cd9f8049f45069650ae0dd217f37bb9264098505)
- 000c5a48599983d65766ef509898628061fdd23e13da65e386f1dda319d107cf (35664e316818103f411bcdf43a184155213496d6)
- 0568fbebba34373d15d2d1c08da432968dded950950c3c553bb549d0039f304b (65e8d6756bd5b7f0445d69150fa6ff716f27d6e6)
- 7d33ac75f7174c8d60efb50d0de119b234ca7991216f5bd78350ff71289dcf0a (b2ad28f85d176ca457a21a3673feb3077cde04f1)
- 8a446debf19b961ecaf6231e24a2565770b560d2cb07e7228ef25f6da27ac5cb (07db4584a35f12b5896d8facd054b0df37d95aef)
- b8fa1df6325137eae02204d16a3867bdb880310652956c2e620d829f0fb812d0 (451dcfac7a9a5f6d773ee5fd02aac87438eeb679)
- 5adbc90b79dc407207e3f5de193e273dae830df1b639d3c0ed21b4824003a463 (ded4acd615481089ba95f40a80bad52d93075edd)
- a0ce48104ef591b08756c77a1e87f19f8d8065ac5a3d72875dc39e336ed7baaa (74121f5545ac94fe7905f67904154ff118d3fa3e)
- 867bc004d278781af9e558c3f000be69dac4576694f796ca54519d730580a857 (4d5f0db488b47520990fd208cb42c8b02cfd9afb)
- fb38370e9bb7c90b3a519fcd76da99563e8ad73b5f7d1734835657b806035ced (b7b6dcc30a13c2f40b3b1b3a2d660d5d029fd4c7)
- 7b8c234be541480cc188d0b032310172f45dc3e4455642399b9c7edf2882d45b (8bf6f7203381273bcece48c1e1fcfe162cdb199a)
- 6f171e968da5cb93842135c14ccbf816fb9c87842519bfffe612b0dc873be3c6 (84533b682c38d79cf6529680febecbe8fbb0cc89)
- 1ec1cc6dad07094759a77784ce15f71ddf4bb0b5999d41702e7b9060f8905668 (7bdef3363e7114fcb68cca1a8c52857e8d9257ef)
- 635dd06dab325170552ce0e042c8a1a010e4139a9eb6afe139d671623f8b6719 (3eb5cd7888007a69d9024b8e235b521efa197d29)
- d03c6b970ff5fa47ed18209aaa44a1366bcaded8e5547f730eacaf74bc6813a4 (43b6ad432e4dd02a4a3fe1fb2fc24c8fe7cb52b3)
- 12916c518a66ffbbc86e62d827e44d5453ff95bf753d54900834b9a9a69e81c7 (ce7452f36c6bea09979d59222f3615fa082417ff)

README.md

@@ -6,38 +6,30 @@ language:
 - es
 - en
 license: apache-2.0
-library_name: mlx
 tags:
-- moe
-inference: false
+- mlx
+inference:
+  parameters:
+    temperature: 0.5
+widget:
+- messages:
+  - role: user
+    content: What is your favorite condiment?
 ---
-# Model Card for Mixtral-8x7B
-The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.
 
-For full details of this model please read our [release blog post](https://mistral.ai/news/mixtral-of-experts/).
+# mlx-community/Mixtral-8x7B-Instruct-v0.1
 
-## Instruction format
+The Model [mlx-community/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mlx-community/Mixtral-8x7B-Instruct-v0.1) was converted to MLX format from [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) using mlx-lm version **0.12.0**.
 
-This format must be strictly respected, otherwise the model will generate sub-optimal outputs.
-
-The template used to build a prompt for the Instruct model is defined as follows:
-```
-<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
-```
-Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.
-
-## Run the model
+## Use with mlx
 
 ```bash
-# Install mlx, mlx-examples, huggingface-cli
-pip install mlx
-pip install huggingface_hub hf_transfer
-git clone https://github.com/ml-explore/mlx-examples.git
+pip install mlx-lm
+```
 
-# Download model
-export HF_HUB_ENABLE_HF_TRANSFER=1
-huggingface-cli download --local-dir Mixtral-8x7B-Instruct-v0.1 mlx-community/Mixtral-8x7B-Instruct-v0.1
+```python
+from mlx_lm import load, generate
 
-# Run example
-python mlx-examples/mixtral/mixtral.py --model_path Mixtral-8x7B-Instruct-v0.1
-```
+model, tokenizer = load("mlx-community/Mixtral-8x7B-Instruct-v0.1")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -1 +1,29 @@
-{"dim": 4096, "n_layers": 32, "head_dim": 128, "hidden_dim": 14336, "n_heads": 32, "n_kv_heads": 8, "norm_eps": 1e-05, "vocab_size": 32000, "moe": {"num_experts_per_tok": 2, "num_experts": 8}, "model_type": "mixtral"}
+{
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mixtral",
+    "num_attention_heads": 32,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "router_aux_loss_coef": 0.02,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.36.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f0461157e77c18c1e389c1893e7753372682c12da79c72338806e8afcab063
+size 5362572091

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa6e71382203dded86e57c0db5ab39ac00d21fdcc99fa9180d3fd6764f0b950
+size 5335325880

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90868868767c838a9bd25dcc59a2598f30487a0b3b76f72fa6361c594eac46d1
+size 5335325880

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba581171b8dfdd9096888da9100e42308fc609ae7f52b3df04c8ce5a46ab129
+size 5335325876

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186c8c5bbc644b6814be96bf8e6fbc8bdcbd309297b6367e011e5135206a6dc7
+size 5335325876

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c16fdf164fa449a23a350bb37ebcf18bb4c6e04c29a00904710107360d61e08
+size 5251357102

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8163d3e4e56764a6d875f3f726f7d8968534738f9b20f14edb9059fe14ddcc
+size 5335325944

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27230cf03d902bec4caf3a1d6375183100fbc71abe1573ff9467b48504d016ca
+size 5335325944

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da59382be815bb6ff839d14632d6ec0f4b0243fd0c5ae36ac64d3ce0eb2eae96
+size 5335325936

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a542edfd597eb7aa6602464f4d61745ab46c36a58bcf858adee72975d4a9b730
+size 5335325938

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7818a3e90bd4f52b3a0f32843162b76b01584c8548fc61cadf6c8a4cb32c25d8
+size 5335325936

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6704271054f1634946b2c4824e2d68aae204a30e1f5b2e1ea1f26435e01a824d
+size 5251357126

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33d2813d5df2bf3c2371f66b73e6449f601e4637d44a8e1f535d065eba54374
+size 5335325944

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377f1e0385e3f718f453a01dc463007b64af794dd46ac32570d44e23581b3a11
+size 5335325942

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a45afe38b74c95e4767f9ba7d13f5fc683e2369e392a60b67a5ff0ac4768256
+size 5335325940

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:016e5230d5e22a05fe5624f06a3357212a020396087ac7933cf21a7366f7aea5
+size 5335325938

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2db0d1658a8e85547c18437cc984e7ccd13d2252e1a12dc4b7057194abf43a
+size 5335325934

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e42ba714909d4ef4aa5a6f3626e0c3bd26c2070b9e457597d658e86730412b
+size 2845863152

model.safetensors.index.json

@@ -0,0 +1,1002 @@
+{
+    "metadata": {
+        "total_size": 93405585408
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00018-of-00018.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00002-of-00018.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00007-of-00018.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00008-of-00018.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.block_sparse_moe.gate.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.block_sparse_moe.gate.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.block_sparse_moe.gate.weight": "model-00011-of-00018.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.21.block_sparse_moe.gate.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00013-of-00018.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00014-of-00018.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.block_sparse_moe.gate.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.block_sparse_moe.gate.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.block_sparse_moe.gate.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.block_sparse_moe.gate.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.block_sparse_moe.gate.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.block_sparse_moe.gate.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.block_sparse_moe.gate.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.block_sparse_moe.gate.weight": "model-00017-of-00018.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.block_sparse_moe.gate.weight": "model-00005-of-00018.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
+        "model.norm.weight": "model-00018-of-00018.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}