Hugging Face's logo

xinlai
/
Qwen2-57B-A14B-SFT

Text Generation
Transformers
Safetensors
qwen2_moe
conversational
Inference Endpoints
Model card Files Community
xinlai commited on
Commit
7fd3f01
•
1 Parent(s): 4291a03

upload model

Browse files
Files changed (32) hide show
  1. .gitattributes +23 -0
  2. added_tokens.json +5 -0
  3. config.json +41 -0
  4. generation_config.json +9 -0
  5. merges.txt +0 -0
  6. model-00001-of-00023.safetensors +3 -0
  7. model-00002-of-00023.safetensors +3 -0
  8. model-00003-of-00023.safetensors +3 -0
  9. model-00004-of-00023.safetensors +3 -0
  10. model-00005-of-00023.safetensors +3 -0
  11. model-00006-of-00023.safetensors +3 -0
  12. model-00007-of-00023.safetensors +3 -0
  13. model-00008-of-00023.safetensors +3 -0
  14. model-00009-of-00023.safetensors +3 -0
  15. model-00010-of-00023.safetensors +3 -0
  16. model-00011-of-00023.safetensors +3 -0
  17. model-00012-of-00023.safetensors +3 -0
  18. model-00013-of-00023.safetensors +3 -0
  19. model-00014-of-00023.safetensors +3 -0
  20. model-00015-of-00023.safetensors +3 -0
  21. model-00016-of-00023.safetensors +3 -0
  22. model-00017-of-00023.safetensors +3 -0
  23. model-00018-of-00023.safetensors +3 -0
  24. model-00019-of-00023.safetensors +3 -0
  25. model-00020-of-00023.safetensors +3 -0
  26. model-00021-of-00023.safetensors +3 -0
  27. model-00022-of-00023.safetensors +3 -0
  28. model-00023-of-00023.safetensors +3 -0
  29. model.safetensors.index.json +0 -0
  30. special_tokens_map.json +20 -0
  31. tokenizer_config.json +44 -0
  32. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,26 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model-00002-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ model-00005-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ model-00012-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
39
+ model-00013-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
40
+ model-00015-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
41
+ model-00022-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
42
+ model-00023-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
43
+ model-00001-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
44
+ model-00010-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
45
+ model-00014-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
46
+ model-00017-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
47
+ model-00007-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
48
+ model-00008-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
49
+ model-00011-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
50
+ model-00003-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
51
+ model-00006-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
52
+ model-00009-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
53
+ model-00016-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
54
+ model-00018-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
55
+ model-00019-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
56
+ model-00020-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
57
+ model-00021-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
58
+ model-00004-of-00023.safetensors filter=lfs diff=lfs merge=lfs -text
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/dataset/industry_gpt/llm_infer/MetaMath/output/qwen2-57b-distill-data-374k-bs32-lr5e-6-linear-fix-sample0.8-sharded",
3
+ "architectures": [
4
+ "Qwen2MoeForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151643,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3584,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 131072,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_moe",
17
+ "moe_intermediate_size": 2560,
18
+ "norm_topk_prob": false,
19
+ "num_attention_heads": 28,
20
+ "num_experts": 64,
21
+ "num_experts_per_tok": 8,
22
+ "num_hidden_layers": 28,
23
+ "num_key_value_heads": 4,
24
+ "output_router_logits": false,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_scaling": {
27
+ "factor": 2.0,
28
+ "original_max_position_embeddings": 32768,
29
+ "type": "yarn"
30
+ },
31
+ "rope_theta": 1000000.0,
32
+ "router_aux_loss_coef": 0.001,
33
+ "shared_expert_intermediate_size": 20480,
34
+ "sliding_window": 131072,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.40.0.dev0",
38
+ "use_cache": false,
39
+ "use_sliding_window": false,
40
+ "vocab_size": 151936
41
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "transformers_version": "4.40.0.dev0"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716023a4a5991cd8ff19fda4f7dca61692cd09789bed531a753b8be59c9cb2f6
3
+ size 4965107248
model-00002-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b874307d9c6cdee51976e3d99889807da21707c3bfc2a56274013ddaf5d13246
3
+ size 4999572712
model-00003-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:effd5aa8deb9906fd1c68a541f42005fc107795304292b6caa33d2387e6b440c
3
+ size 4995413224
model-00004-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6006729d13089234b730cbbdec6233e9514ea3e094eb83920184c682ab2a840d
3
+ size 4995413224
model-00005-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba3485630f4bf6968e2390015483bd9da4518fb2e766b44789634536b929066
3
+ size 4977062168
model-00006-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:203e1d855dc3e97ebe207163fd123a0952082cc6544a12076afbe6c6fca84682
3
+ size 4999571856
model-00007-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67824c71f071cae22c2b51f4bdbbbede2ef5230291b456f87ecbb04a9930260e
3
+ size 4995413224
model-00008-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:955c5cf64b5343629843df80bbe22bfbafc2d99332847fc7e6bcc3e97b285011
3
+ size 4995413224
model-00009-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72362012a6f9b2cf07110b2971ab6521deb0cac68a41bd704b3d0d88dc987bb
3
+ size 4977063232
model-00010-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ee0f24658789ddd793c7a71f8e855d5acee602f16242ea564ee14b681a03a0
3
+ size 4999571256
model-00011-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c2f3a5efea51cf95fc258086374aad87ba658e6accf235c891e1e1ebbce0b6
3
+ size 4995413480
model-00012-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e58e5d93fbf1f6717ad50b93679db37abaf3db78d97e607b8cb6aabc2dfae1
3
+ size 4995413480
model-00013-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:813a3f93c609db7b52b56855c10575d15b3606fb827382d6ce928edc2524039e
3
+ size 4995413480
model-00014-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4520ae700c20526c248734cbe511c52967479a2f73fee90ed6d31bca7401cec8
3
+ size 4999571256
model-00015-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6b6142336acaf5b9bb20137b0e6eba313de580ec2f3669894ef758de157dd7b
3
+ size 4995413472
model-00016-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f620c367061a984154cd60d898ec0c99effb5a5d857f5f60dec79d13a53092f
3
+ size 4995413480
model-00017-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c649de873fee2d9da931bb9c175a240a52b28cbb7df2a1a901c3024a48bae3
3
+ size 4995413480
model-00018-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c9529bb620141c05fdf800c727f5a4e9926dca9c9322890473931c626db25cf
3
+ size 4999571256
model-00019-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556d60bba17dea62e43388ed2457323689d8b8f58434c914fe51b8a52646bb65
3
+ size 4995413464
model-00020-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c076bfc7404b7f779e3965934cd2a6c942e8c75e1add61ea8127cbe5a10c25f
3
+ size 4995413480
model-00021-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b234969fdd75f5b18414eb624074bf7ebda5f5593b72237fdd2e5de8ef66893
3
+ size 4995413480
model-00022-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b08bafc42149cd576bf7994c6066f199dec2d83524505826678f71ae57d93b
3
+ size 4999571264
model-00023-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc98afc1f98eea5276e49a1cd8359555660945c911f2c0a1155933185e5cd1d7
3
+ size 4960997176
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 512,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff