Epoch 0 - Val loss 0.9000
Browse files- README.md +12 -0
- config.json +22 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
+
tags:
|
| 5 |
+
- model_hub_mixin
|
| 6 |
+
- pytorch_model_hub_mixin
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 10 |
+
- Code: [More Information Needed]
|
| 11 |
+
- Paper: [More Information Needed]
|
| 12 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"att_groups": 4,
|
| 3 |
+
"att_heads": 8,
|
| 4 |
+
"att_query_groups": 4,
|
| 5 |
+
"cross_att_type": "sqa",
|
| 6 |
+
"embed_dim": 128,
|
| 7 |
+
"ff_activation": "silu",
|
| 8 |
+
"ff_dim": 256,
|
| 9 |
+
"ff_dropout": 0.1,
|
| 10 |
+
"init_identity_norm": true,
|
| 11 |
+
"moe_top_k": 2,
|
| 12 |
+
"num_experts": 12,
|
| 13 |
+
"num_layers": 6,
|
| 14 |
+
"self_att_type": "sqa",
|
| 15 |
+
"seq_len": 256,
|
| 16 |
+
"stm_size": 256,
|
| 17 |
+
"use_flash_attention": false,
|
| 18 |
+
"use_gated": true,
|
| 19 |
+
"use_head_norm": true,
|
| 20 |
+
"use_moe": true,
|
| 21 |
+
"vocab_size": 7500
|
| 22 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b34d7b282abb3001b862560ed0c8b99c34ca2a7384983aadcbd01e371a8262
|
| 3 |
+
size 38674040
|