Upload Qwen2ForCausalLM
Browse files- config.json +42 -0
- generation_config.json +9 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./models/DeepSeek-R1-Distill-Qwen-32B-AWQ-4bits-GEMM",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 27648,
|
13 |
+
"max_position_embeddings": 131072,
|
14 |
+
"max_window_layers": 64,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 40,
|
17 |
+
"num_hidden_layers": 64,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"quantization_config": {
|
20 |
+
"backend": "autoawq",
|
21 |
+
"bits": 4,
|
22 |
+
"do_fuse": false,
|
23 |
+
"exllama_config": null,
|
24 |
+
"fuse_max_seq_len": null,
|
25 |
+
"group_size": 128,
|
26 |
+
"modules_to_fuse": null,
|
27 |
+
"modules_to_not_convert": null,
|
28 |
+
"quant_method": "awq",
|
29 |
+
"version": "gemm",
|
30 |
+
"zero_point": true
|
31 |
+
},
|
32 |
+
"rms_norm_eps": 1e-05,
|
33 |
+
"rope_scaling": null,
|
34 |
+
"rope_theta": 1000000.0,
|
35 |
+
"sliding_window": null,
|
36 |
+
"tie_word_embeddings": false,
|
37 |
+
"torch_dtype": "float16",
|
38 |
+
"transformers_version": "4.47.1",
|
39 |
+
"use_cache": false,
|
40 |
+
"use_sliding_window": false,
|
41 |
+
"vocab_size": 152064
|
42 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 151646,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 151643,
|
6 |
+
"temperature": 0.6,
|
7 |
+
"top_p": 0.95,
|
8 |
+
"transformers_version": "4.47.1"
|
9 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87bac59d875c952037c9aaa847bc88cfeabdc1cc930e973e430a3f82c6d4f839
|
3 |
+
size 4956994912
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bb37549e1626dc893ca67e00430075097981bf1c211508b47c00a986fc6f5af
|
3 |
+
size 4993553816
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72059be31845f6290a149dc1a393d1648c4615a120178db84308a46334699f30
|
3 |
+
size 4960830976
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3831dd7d3a27e15e116145dd8fd7aeb52cf27ede2690ca407133e54a4f36d244
|
3 |
+
size 4417614296
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|