Upload 12 files
Browse files- added_tokens.json +5 -0
- config.json +34 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00016.safetensors +3 -0
- model-00002-of-00016.safetensors +3 -0
- model-00003-of-00016.safetensors +3 -0
- model-00004-of-00016.safetensors +3 -0
- model-00005-of-00016.safetensors +3 -0
- model-00006-of-00016.safetensors +3 -0
- model-00007-of-00016.safetensors +3 -0
- model.safetensors.index.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "anthracite-org/magnum-v2-72b",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 8192,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 29568,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 80,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 64,
|
16 |
+
"num_hidden_layers": 80,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"quantization_config": {
|
19 |
+
"activation_scheme": "dynamic",
|
20 |
+
"ignored_layers": [
|
21 |
+
"lm_head"
|
22 |
+
],
|
23 |
+
"quant_method": "fp8"
|
24 |
+
},
|
25 |
+
"rms_norm_eps": 1e-06,
|
26 |
+
"rope_theta": 1000000.0,
|
27 |
+
"sliding_window": null,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.44.2",
|
31 |
+
"use_cache": false,
|
32 |
+
"use_sliding_window": false,
|
33 |
+
"vocab_size": 152064
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.44.2"
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:639ff98ef7b28bccaa8b64b55f87ef80b2f8bb3bc94426ff74a38ac293d469ba
|
3 |
+
size 4882302792
|
model-00002-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56f24f1628e3c2f0d4518652f4ab74d83c8c986ba234f0655f89cdaba874f620
|
3 |
+
size 4781837952
|
model-00003-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f84c71d4f1c60fa9afd6b0b4c934a2788b736916b467eacbefcad5cec55c7bd
|
3 |
+
size 4873009684
|
model-00004-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3158e7f9732010130652b9763d92827d77bb2fde6affe8305cd1466e2e63faef
|
3 |
+
size 4781838064
|
model-00005-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fb0ede4cd93b831b52bdd57815de07cea5e1651934c8837d421ec17e9024b30
|
3 |
+
size 4873009716
|
model-00006-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc16d306663d3bff28740bd920d2e8efcf3dfe30de576f665986d67537610cbb
|
3 |
+
size 4781838064
|
model-00007-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebde37f43ba5132286f73b4dac37250efdb94bb17c30bec170dcb66dfb417fa2
|
3 |
+
size 4873009716
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|