Upload Qwen2ForCausalLM
Browse files- config.json +43 -0
- generation_config.json +6 -0
- model-00001-of-00009.safetensors +3 -0
- model-00002-of-00009.safetensors +3 -0
- model-00003-of-00009.safetensors +3 -0
- model-00004-of-00009.safetensors +3 -0
- model-00005-of-00009.safetensors +3 -0
- model-00006-of-00009.safetensors +3 -0
- model-00007-of-00009.safetensors +3 -0
- model-00008-of-00009.safetensors +3 -0
- model-00009-of-00009.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2-72B",
|
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": 8192,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 29568,
|
13 |
+
"max_position_embeddings": 131072,
|
14 |
+
"max_window_layers": 80,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 64,
|
17 |
+
"num_hidden_layers": 80,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"quantization_config": {
|
20 |
+
"_load_in_4bit": true,
|
21 |
+
"_load_in_8bit": false,
|
22 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
23 |
+
"bnb_4bit_quant_storage": "uint8",
|
24 |
+
"bnb_4bit_quant_type": "nf4",
|
25 |
+
"bnb_4bit_use_double_quant": true,
|
26 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
27 |
+
"llm_int8_has_fp16_weight": false,
|
28 |
+
"llm_int8_skip_modules": null,
|
29 |
+
"llm_int8_threshold": 6.0,
|
30 |
+
"load_in_4bit": true,
|
31 |
+
"load_in_8bit": false,
|
32 |
+
"quant_method": "bitsandbytes"
|
33 |
+
},
|
34 |
+
"rms_norm_eps": 1e-05,
|
35 |
+
"rope_theta": 1000000.0,
|
36 |
+
"sliding_window": 131072,
|
37 |
+
"tie_word_embeddings": false,
|
38 |
+
"torch_dtype": "bfloat16",
|
39 |
+
"transformers_version": "4.42.4",
|
40 |
+
"use_cache": true,
|
41 |
+
"use_sliding_window": false,
|
42 |
+
"vocab_size": 152064
|
43 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"eos_token_id": 151643,
|
4 |
+
"max_new_tokens": 2048,
|
5 |
+
"transformers_version": "4.42.4"
|
6 |
+
}
|
model-00001-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:141e99912587796275d018724429d3613deec50c86d92d2bdc2e25857f0fe28a
|
3 |
+
size 4958417273
|
model-00002-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aae104ccb62874a55af6a483bdba12851ce4a0217c30bb3dd3d8eefe6aaa9e3
|
3 |
+
size 4981068150
|
model-00003-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1811d5e5fc170e97c870bc07a9fabfc02e339fd711efae03071fe267bdd10fbf
|
3 |
+
size 4981068369
|
model-00004-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9babdd87659c1d4908868c735681b39c24d4d5402510160d7567842dc2676b8b
|
3 |
+
size 4981068373
|
model-00005-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7586687f7d5bbe603541b66dc9da36b0316121f236b60e689b260304a01c92e8
|
3 |
+
size 4981068377
|
model-00006-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb1dc2c40085edff3b092edfa6854b310fe3a8d6c28bf68e8740e8b0f1f84d78
|
3 |
+
size 4981068374
|
model-00007-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:993bacb033dc6c5b24f5741afc659bb57c78ad584fd68f5e44200fe21669cf36
|
3 |
+
size 4981068380
|
model-00008-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79974502dc61590c3e8e8373de9e48df5c8f2540650677f3b5718275f0faf314
|
3 |
+
size 3872557274
|
model-00009-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1992b4740fd4ad466591dc503056502a8851c61fb34d28e39e143c7f49385e2e
|
3 |
+
size 2491416704
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|