Hugging Face's logo

Qwen
/
Qwen2-57B-A14B-Instruct

Text Generation
Transformers
Safetensors
English
qwen2_moe
chat
conversational
Inference Endpoints
Model card Files Community
7
yangapku commited on
Commit
5aca2a2
•
1 Parent(s): 8ad0289

Initial commit

Browse files
Files changed (38) hide show
  1. config.json +35 -0
  2. configuration.json +5 -0
  3. generation_config.json +9 -0
  4. merges.txt +0 -0
  5. model-00001-of-00029.safetensors +3 -0
  6. model-00002-of-00029.safetensors +3 -0
  7. model-00003-of-00029.safetensors +3 -0
  8. model-00004-of-00029.safetensors +3 -0
  9. model-00005-of-00029.safetensors +3 -0
  10. model-00006-of-00029.safetensors +3 -0
  11. model-00007-of-00029.safetensors +3 -0
  12. model-00008-of-00029.safetensors +3 -0
  13. model-00009-of-00029.safetensors +3 -0
  14. model-00010-of-00029.safetensors +3 -0
  15. model-00011-of-00029.safetensors +3 -0
  16. model-00012-of-00029.safetensors +3 -0
  17. model-00013-of-00029.safetensors +3 -0
  18. model-00014-of-00029.safetensors +3 -0
  19. model-00015-of-00029.safetensors +3 -0
  20. model-00016-of-00029.safetensors +3 -0
  21. model-00017-of-00029.safetensors +3 -0
  22. model-00018-of-00029.safetensors +3 -0
  23. model-00019-of-00029.safetensors +3 -0
  24. model-00020-of-00029.safetensors +3 -0
  25. model-00021-of-00029.safetensors +3 -0
  26. model-00022-of-00029.safetensors +3 -0
  27. model-00023-of-00029.safetensors +3 -0
  28. model-00024-of-00029.safetensors +3 -0
  29. model-00025-of-00029.safetensors +3 -0
  30. model-00026-of-00029.safetensors +3 -0
  31. model-00027-of-00029.safetensors +3 -0
  32. model-00028-of-00029.safetensors +3 -0
  33. model-00029-of-00029.safetensors +3 -0
  34. model.safetensors.index.json +0 -0
  35. special_tokens_map.json +16 -0
  36. tokenizer.json +0 -0
  37. tokenizer_config.json +41 -0
  38. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2MoeForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "decoder_sparse_step": 1,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2_moe",
16
+ "moe_intermediate_size": 2560,
17
+ "norm_topk_prob": false,
18
+ "num_attention_heads": 28,
19
+ "num_experts": 64,
20
+ "num_experts_per_tok": 8,
21
+ "num_hidden_layers": 28,
22
+ "num_key_value_heads": 4,
23
+ "output_router_logits": false,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_theta": 1000000.0,
26
+ "router_aux_loss_coef": 0.001,
27
+ "shared_expert_intermediate_size": 20480,
28
+ "sliding_window": 4096,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.40.1",
32
+ "use_cache": true,
33
+ "use_sliding_window": false,
34
+ "vocab_size": 151936
35
+ }
configuration.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "framework": "pytorch",
3
+ "task": "fill-mask",
4
+ "allow_remote": true
5
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "pad_token_id": 151643,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
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-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca57fe6af12e0eebbc6b11ac31c9b5fde6ef8a9aec1fca0de2ebd02e39f19ca7
3
+ size 3992548152
model-00002-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cad09ebbea5214022fa0f73fe91852a6feb3e6a1c68de2505cc5466cc2807c4
3
+ size 3986152016
model-00003-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf68771367ee467e7967258f2156e605430dd81bdc36823baca1020efa57435
3
+ size 3986152008
model-00004-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be00366cf4fcb199761096f14eba5ea3ce8caada6d6f1b7cfedf43eadc4034d8
3
+ size 3986152008
model-00005-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27013e94dbcd23d8bcdd490f819fc2f9de05ee69550417a1c256ef58b78be842
3
+ size 3986152000
model-00006-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed03d2ec20aeae9b4b2007e263aed073149178690c2d074bb96f0ee10542f55
3
+ size 3986152000
model-00007-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0055a3131247962127bc8271bc3e4f46cb2c876747409fb7f2722bc3a54148cb
3
+ size 3986151992
model-00008-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac20942deef743a792cf532220e02abec93ee1895fec96434471ebad77d2f46
3
+ size 3986151992
model-00009-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7381a2b1c884a2f27a09b25b82bc188daa0ec2abcf91ba3635f95ae293d9aa5
3
+ size 3986151992
model-00010-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c18cdf3ce711a84cb7e0d8f497124325151f3b6fdca01c069706d35e134333b7
3
+ size 3986151984
model-00011-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551629128f3114371279d7829e562a94ca13ad2a32214625a18b346c7fab7360
3
+ size 3986152136
model-00012-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68dbd946665e5fa8070fe14b03adb068cd5164fed3426254533ccef2ff1463a
3
+ size 3986152184
model-00013-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da784966842a5ae8b7dd4e98abac253cde5519e65ff07bfc78e289d784bc1b75
3
+ size 3986152184
model-00014-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478cdfec9f23b7f01e1cf8672f0413cb6dc3d406d47b758835155f349f7268e9
3
+ size 3986152184
model-00015-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9dc320656f785de6adbe3dab74baa4642405c097820ed15ca11879e632f64e3
3
+ size 3986152184
model-00016-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95c0b003ed37940c82ea7d4d9cb663abb2bcf51df2cd75827d151419b6ddbb5
3
+ size 3986152184
model-00017-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed01b9e8d28ac0d316865370809cc216f4c54cf30653ef22d9ff0ea91904af9f
3
+ size 3986152184
model-00018-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5d53a73eaffa278345c74a0536442d10823b05d7963a83877050bb48bd4172
3
+ size 3986152184
model-00019-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d5932ca2510dd2d2a9fbd2f164f861e47ce5deb41ad4ce86dece35c45afccf
3
+ size 3986152184
model-00020-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0c35e57b2128bf21026a87a3b238fbe56759ae134ce3c8451e1a5f3c030ceb
3
+ size 3986152184
model-00021-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca80cc7a23e3ce928f254cff6b6160f866a7f1685c1863aef81d23fac4e1dcd
3
+ size 3986152184
model-00022-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ca4608bd3f00e4122d78ec96b7a27ff63b02b69fcc696a4398d8e45ca370b3
3
+ size 3986152184
model-00023-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e5fcacaacb0034c8cb6acd195d5c3e5723be6dd1ee0d28b35952b2aa1155c9
3
+ size 3986152184
model-00024-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487c571d36af5f13956dfd6d30a0f9009281d54beb6502881147504fb03db48c
3
+ size 3986152184
model-00025-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5851c675ffa0ce6c7d77d657b0a110132e805446c25c03044be8f4c2148bb945
3
+ size 3986152184
model-00026-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c54cddfa6132e13d207d66a0da788cd12426000ef634599606fa13ac89df490
3
+ size 3986152184
model-00027-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b04c7b37ea8b5f957f52392a8306abddb02c3df7e1d09e3bf81aead3c6710a
3
+ size 3986152184
model-00028-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80df1ae3934022c0eee8fbc68a78db2886137519e93d58e4a777a67fe264edb7
3
+ size 3986152184
model-00029-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d0e8bd5d23f13821e30a37dae9340decb05af405ea44c4f293384984f706a8
3
+ size 3199377488
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": ["<|im_start|>", "<|im_end|>"],
30
+ "bos_token": null,
31
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|endoftext|>",
34
+ "errors": "replace",
35
+ "model_max_length": 32768,
36
+ "pad_token": "<|endoftext|>",
37
+ "split_special_tokens": false,
38
+ "tokenizer_class": "Qwen2Tokenizer",
39
+ "unk_token": null
40
+ }
41
+
vocab.json ADDED
The diff for this file is too large to render. See raw diff