guanning commited on
Commit
d59415b
·
verified ·
1 Parent(s): f853c3a

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. global_step_1000/actor/chat_template.jinja +6 -0
  2. global_step_1000/actor/config.json +38 -0
  3. global_step_1000/actor/extra_state_world_size_16_rank_0.pt +3 -0
  4. global_step_1000/actor/extra_state_world_size_16_rank_1.pt +3 -0
  5. global_step_1000/actor/extra_state_world_size_16_rank_10.pt +3 -0
  6. global_step_1000/actor/extra_state_world_size_16_rank_11.pt +3 -0
  7. global_step_1000/actor/extra_state_world_size_16_rank_12.pt +3 -0
  8. global_step_1000/actor/extra_state_world_size_16_rank_13.pt +3 -0
  9. global_step_1000/actor/extra_state_world_size_16_rank_14.pt +3 -0
  10. global_step_1000/actor/extra_state_world_size_16_rank_15.pt +3 -0
  11. global_step_1000/actor/extra_state_world_size_16_rank_2.pt +3 -0
  12. global_step_1000/actor/extra_state_world_size_16_rank_3.pt +3 -0
  13. global_step_1000/actor/extra_state_world_size_16_rank_4.pt +3 -0
  14. global_step_1000/actor/extra_state_world_size_16_rank_5.pt +3 -0
  15. global_step_1000/actor/extra_state_world_size_16_rank_6.pt +3 -0
  16. global_step_1000/actor/extra_state_world_size_16_rank_7.pt +3 -0
  17. global_step_1000/actor/extra_state_world_size_16_rank_8.pt +3 -0
  18. global_step_1000/actor/extra_state_world_size_16_rank_9.pt +3 -0
  19. global_step_1000/actor/generation_config.json +7 -0
  20. global_step_1000/actor/merges.txt +0 -0
  21. global_step_1000/actor/model_world_size_16_rank_0.pt +3 -0
  22. global_step_1000/actor/model_world_size_16_rank_1.pt +3 -0
  23. global_step_1000/actor/model_world_size_16_rank_10.pt +3 -0
  24. global_step_1000/actor/model_world_size_16_rank_11.pt +3 -0
  25. global_step_1000/actor/model_world_size_16_rank_12.pt +3 -0
  26. global_step_1000/actor/model_world_size_16_rank_13.pt +3 -0
  27. global_step_1000/actor/model_world_size_16_rank_14.pt +3 -0
  28. global_step_1000/actor/model_world_size_16_rank_15.pt +3 -0
  29. global_step_1000/actor/model_world_size_16_rank_2.pt +3 -0
  30. global_step_1000/actor/model_world_size_16_rank_3.pt +3 -0
  31. global_step_1000/actor/model_world_size_16_rank_4.pt +3 -0
  32. global_step_1000/actor/model_world_size_16_rank_5.pt +3 -0
  33. global_step_1000/actor/model_world_size_16_rank_6.pt +3 -0
  34. global_step_1000/actor/model_world_size_16_rank_7.pt +3 -0
  35. global_step_1000/actor/model_world_size_16_rank_8.pt +3 -0
  36. global_step_1000/actor/model_world_size_16_rank_9.pt +3 -0
  37. global_step_1000/actor/optim_world_size_16_rank_0.pt +3 -0
  38. global_step_1000/actor/optim_world_size_16_rank_1.pt +3 -0
  39. global_step_1000/actor/optim_world_size_16_rank_10.pt +3 -0
  40. global_step_1000/actor/optim_world_size_16_rank_11.pt +3 -0
  41. global_step_1000/actor/optim_world_size_16_rank_12.pt +3 -0
  42. global_step_1000/actor/optim_world_size_16_rank_13.pt +3 -0
  43. global_step_1000/actor/optim_world_size_16_rank_14.pt +3 -0
  44. global_step_1000/actor/optim_world_size_16_rank_15.pt +3 -0
  45. global_step_1000/actor/optim_world_size_16_rank_2.pt +3 -0
  46. global_step_1000/actor/optim_world_size_16_rank_3.pt +3 -0
  47. global_step_1000/actor/optim_world_size_16_rank_4.pt +3 -0
  48. global_step_1000/actor/optim_world_size_16_rank_5.pt +3 -0
  49. global_step_1000/actor/optim_world_size_16_rank_6.pt +3 -0
  50. global_step_1000/actor/optim_world_size_16_rank_7.pt +3 -0
global_step_1000/actor/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
global_step_1000/actor/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 960,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2560,
14
+ "is_llama_config": true,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 15,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 5,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 100000,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "float32",
29
+ "transformers.js_config": {
30
+ "kv_cache_dtype": {
31
+ "fp16": "float16",
32
+ "q4f16": "float16"
33
+ }
34
+ },
35
+ "transformers_version": "4.54.1",
36
+ "use_cache": true,
37
+ "vocab_size": 49152
38
+ }
global_step_1000/actor/extra_state_world_size_16_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba9983550c5198e5ad3fd83509f47f727861e8736403336227441c4dfcdd91a4
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d5b5288c9c910c74aa36de3086b571f6d8ebbe3e55f8e79aaa283935990730
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_10.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e616a88d8bb50079d2675d1ba6b504c6759a24d1abe72d1579accc5a9499af06
3
+ size 15093
global_step_1000/actor/extra_state_world_size_16_rank_11.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc64695049f5712d9b6c6da6344f108bb4b7a04c7d2e924d4569854bf9c355ef
3
+ size 15093
global_step_1000/actor/extra_state_world_size_16_rank_12.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b994a0fc797ed33499f7db234cd807efb752724d01e5bc0c775e43a16ff2da
3
+ size 15093
global_step_1000/actor/extra_state_world_size_16_rank_13.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a072f8417b8654c093391aae298ce4f8e0457d94ac0e7437764e5176ca8e90
3
+ size 15093
global_step_1000/actor/extra_state_world_size_16_rank_14.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874dfa3891b3cdfa093e63ae99c119d5b201710113a28b3a9735b0cb483b858c
3
+ size 15093
global_step_1000/actor/extra_state_world_size_16_rank_15.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e556f5e1f53e7c5c3886c03b363544c11f3d2a582c4c70dca0dd6ad46db76e59
3
+ size 15093
global_step_1000/actor/extra_state_world_size_16_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46678e96b8b62c6ac20bdff82d2f7f2232a47f054c7373cf9174889d5c6a11de
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bdc28e0470105c5219c49db018c8a1ae418b4c932076f10dfd11147065c23ad
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3c630a9511ac9716c9c1c53f65c59afd3dce53af4de723b366a51ab6319c9a
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642b5266df767ec34f164fdde178b77784ce2d6e22a13452a24519651542731b
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0283a5fa97e9bcf2d9ae7bb921558f97bece6c7c9733ee9dc56f8e76849dd7
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fab0145a806cd0c7f8adf6adeaa5469c670ba529e908cadb45bd8afc3caacb
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_8.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426724fcd875325e2dcfc87329688914880bc5bd1b01ded936ed8f426f4dd9d4
3
+ size 15085
global_step_1000/actor/extra_state_world_size_16_rank_9.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73afc3da1bfcdd10402bffc903b4a98893fe25c83b093c8c2839f52f9d9c34f8
3
+ size 15085
global_step_1000/actor/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.54.1"
7
+ }
global_step_1000/actor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
global_step_1000/actor/model_world_size_16_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb30d67143a58967746b1cc4aa0cd70c4471fe0b579a48435b16aca19967b8a4
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba92eb15ca8296b8ae45c396c19fb153e50731f4b1fda06755d6354f430b387
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_10.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0834f5379feceae2427edf8cae66a7bebb1b7782356e44d89008406cc8673511
3
+ size 102426687
global_step_1000/actor/model_world_size_16_rank_11.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa448acdde63862e5f996db39a1d89fbc4ba2782d30320381486035e52cb3f0d
3
+ size 102426687
global_step_1000/actor/model_world_size_16_rank_12.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900fdebea177897f8941c1a5d760444343632d3fd63aaf03c07934a5d30e2bbc
3
+ size 102426687
global_step_1000/actor/model_world_size_16_rank_13.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac0934647bd855079c5dafca42920fde58264b8bbb784ba41822768a71dc5c0
3
+ size 102426687
global_step_1000/actor/model_world_size_16_rank_14.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec06fc8abcc0c6ffa6ca4b2ac3633e10d0b5b310d6a79c05453f6585ae07013
3
+ size 102426687
global_step_1000/actor/model_world_size_16_rank_15.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df94db5a795f9de42c107acffff95d61ff73030f3bb006c2e4261f0b7e9f340
3
+ size 102426687
global_step_1000/actor/model_world_size_16_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3084cbea4d1f82c82085480ddfe70b110714b907aca14b8412ffa4215b88ffb9
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc176d6c9054ffc61cd5a89eccaf5e8333fa6a129af71848f0582cacd6a77c8
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606659ac4e3eed1f0333bd968fbd9f1c14d9a93e580e5326027e1b0b2a9aae7f
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be2658a98cda586f821a3044b4f91654740965430702d235df406014ce61c9e
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1b292ce0f1545490a283e8f4c5fb8b5970982b2d6036b43ef65c20f602bfd8
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474c2bdf98551f4964c1be74ca7b6f2dc8c61dfcb66c43bbde34a071f6529e36
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_8.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdaa08ab16c861a29280bd07fdcb40845a189da5a23b8e7d515686b823c1b09
3
+ size 102426389
global_step_1000/actor/model_world_size_16_rank_9.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e833cea77a4d0668d9e90ce384dc8529fd7a421d057e3dc0815837fac936bb5
3
+ size 102426389
global_step_1000/actor/optim_world_size_16_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265c2857a31a78decdc3d7de2a09cca3b5cff4c2f3e2a7b5c94b278dd86f6165
3
+ size 180938821
global_step_1000/actor/optim_world_size_16_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a350e8e5d23a6092d6d0d11f7ebf85a523c951174bb33183394e2fa0a6ced6fa
3
+ size 180938821
global_step_1000/actor/optim_world_size_16_rank_10.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed283fff5b654bfd42477c91e765162e2d1e1b9c08707bddce554174c567ae15
3
+ size 180938926
global_step_1000/actor/optim_world_size_16_rank_11.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d615de90c1dae85fb10c50c5f91f268e8eb8e15ae50486bad6ea6510544e778
3
+ size 180938926
global_step_1000/actor/optim_world_size_16_rank_12.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c126e448b412d6dc756ec1a765cee3cf303ecfc485c1a42bdd2697c2fbe2698
3
+ size 180938926
global_step_1000/actor/optim_world_size_16_rank_13.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd77a98f98e6ef2b5f93a144ca858264e543edad4e3debb8d649be33f47be69c
3
+ size 180938926
global_step_1000/actor/optim_world_size_16_rank_14.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780fa716eb626b3cc9d173a5076e861bb95941a602431a81e8c17c27809e21c1
3
+ size 180938926
global_step_1000/actor/optim_world_size_16_rank_15.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6349571850894f9ff1abc71017dde68ccdc7cf9c9214548c4057d52a2991b7c1
3
+ size 180938926
global_step_1000/actor/optim_world_size_16_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da840fc1966d4beb30d25a85e5759b69700e0c978e1bb2dd5a2fa9c742f7ff57
3
+ size 180938821
global_step_1000/actor/optim_world_size_16_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7cf7242d40bc255fa2a7ac821aa74a7de40bc8ad7086c22a86eb01be029b32
3
+ size 180938821
global_step_1000/actor/optim_world_size_16_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d25798a1e97cdcf56a5517567d2b94d902ea292a9b0dcd99ddf7f6839462d33
3
+ size 180938821
global_step_1000/actor/optim_world_size_16_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6438b31efdbe079dd5d57a818ffe24895febb707376db63c0a83f2223dda996f
3
+ size 180938821
global_step_1000/actor/optim_world_size_16_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ddb747286c896c5a789c393285d52a41626d680d8e04e9c2c7850dfa530a87
3
+ size 180938821
global_step_1000/actor/optim_world_size_16_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e202db8625e0c0b10836664fbc9d14c61c4737c6717e18afbe626169010906
3
+ size 180938821