Hugging Face's logo

guanning-ai
/
SmolLM-p-normalization-32rollouts

Model card Files
xet
 Community
guanning commited on
Commit
d2bc999
·
verified ·
1 Parent(s): d59415b

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_1500/actor/chat_template.jinja +6 -0
  2. global_step_1500/actor/config.json +38 -0
  3. global_step_1500/actor/extra_state_world_size_16_rank_0.pt +3 -0
  4. global_step_1500/actor/extra_state_world_size_16_rank_1.pt +3 -0
  5. global_step_1500/actor/extra_state_world_size_16_rank_10.pt +3 -0
  6. global_step_1500/actor/extra_state_world_size_16_rank_11.pt +3 -0
  7. global_step_1500/actor/extra_state_world_size_16_rank_12.pt +3 -0
  8. global_step_1500/actor/extra_state_world_size_16_rank_13.pt +3 -0
  9. global_step_1500/actor/extra_state_world_size_16_rank_14.pt +3 -0
  10. global_step_1500/actor/extra_state_world_size_16_rank_15.pt +3 -0
  11. global_step_1500/actor/extra_state_world_size_16_rank_2.pt +3 -0
  12. global_step_1500/actor/extra_state_world_size_16_rank_3.pt +3 -0
  13. global_step_1500/actor/extra_state_world_size_16_rank_4.pt +3 -0
  14. global_step_1500/actor/extra_state_world_size_16_rank_5.pt +3 -0
  15. global_step_1500/actor/extra_state_world_size_16_rank_6.pt +3 -0
  16. global_step_1500/actor/extra_state_world_size_16_rank_7.pt +3 -0
  17. global_step_1500/actor/extra_state_world_size_16_rank_8.pt +3 -0
  18. global_step_1500/actor/extra_state_world_size_16_rank_9.pt +3 -0
  19. global_step_1500/actor/generation_config.json +7 -0
  20. global_step_1500/actor/merges.txt +0 -0
  21. global_step_1500/actor/model_world_size_16_rank_0.pt +3 -0
  22. global_step_1500/actor/model_world_size_16_rank_1.pt +3 -0
  23. global_step_1500/actor/model_world_size_16_rank_10.pt +3 -0
  24. global_step_1500/actor/model_world_size_16_rank_11.pt +3 -0
  25. global_step_1500/actor/model_world_size_16_rank_12.pt +3 -0
  26. global_step_1500/actor/model_world_size_16_rank_13.pt +3 -0
  27. global_step_1500/actor/model_world_size_16_rank_14.pt +3 -0
  28. global_step_1500/actor/model_world_size_16_rank_15.pt +3 -0
  29. global_step_1500/actor/model_world_size_16_rank_2.pt +3 -0
  30. global_step_1500/actor/model_world_size_16_rank_3.pt +3 -0
  31. global_step_1500/actor/model_world_size_16_rank_4.pt +3 -0
  32. global_step_1500/actor/model_world_size_16_rank_5.pt +3 -0
  33. global_step_1500/actor/model_world_size_16_rank_6.pt +3 -0
  34. global_step_1500/actor/model_world_size_16_rank_7.pt +3 -0
  35. global_step_1500/actor/model_world_size_16_rank_8.pt +3 -0
  36. global_step_1500/actor/model_world_size_16_rank_9.pt +3 -0
  37. global_step_1500/actor/optim_world_size_16_rank_0.pt +3 -0
  38. global_step_1500/actor/optim_world_size_16_rank_1.pt +3 -0
  39. global_step_1500/actor/optim_world_size_16_rank_10.pt +3 -0
  40. global_step_1500/actor/optim_world_size_16_rank_11.pt +3 -0
  41. global_step_1500/actor/optim_world_size_16_rank_12.pt +3 -0
  42. global_step_1500/actor/optim_world_size_16_rank_13.pt +3 -0
  43. global_step_1500/actor/optim_world_size_16_rank_14.pt +3 -0
  44. global_step_1500/actor/optim_world_size_16_rank_15.pt +3 -0
  45. global_step_1500/actor/optim_world_size_16_rank_2.pt +3 -0
  46. global_step_1500/actor/optim_world_size_16_rank_3.pt +3 -0
  47. global_step_1500/actor/optim_world_size_16_rank_4.pt +3 -0
  48. global_step_1500/actor/optim_world_size_16_rank_5.pt +3 -0
  49. global_step_1500/actor/optim_world_size_16_rank_6.pt +3 -0
  50. global_step_1500/actor/optim_world_size_16_rank_7.pt +3 -0
global_step_1500/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_1500/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_1500/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 sha256:00b7b468ec9e8493534708db8063af7ade28d57793824096248e86d394896848
3
+ size 15085
global_step_1500/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:ad7649469d9de798195a0dbf711284a2f98d99a944f04e8278c9599bf45c1565
3
+ size 15085
global_step_1500/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 sha256:329d6089d5a4873c84575e9d50d092fd6139c1bbf47a38b250a34ee282042bf5
3
+ size 15093
global_step_1500/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 sha256:714f1967405815fe1e0553d54dd9bc360168ee845f145b648366cc8dba9e361b
3
+ size 15093
global_step_1500/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 sha256:839c13266633fb1c1306dd9b8c1f27c80ceb31c3bf9c10bb61b42489c3a259a8
3
+ size 15093
global_step_1500/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:ec3868b9292e85f1d1183e3103486036b1a4e01ed1e3be2ff8e996bdf9324ca1
3
+ size 15093
global_step_1500/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:ad6d2e7814e961a88df67ea00e5a3e7e62abb7458689000a04081c2e337b5e0b
3
+ size 15093
global_step_1500/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:e13c43e548c1a74ddca85473cf95bc35e43ab97c47f13f659fc39de991436b2c
3
+ size 15093
global_step_1500/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 sha256:7291f14e64fc4aa6d1508a21d7f8034b05871662bb0a57d5eb917b1322096a71
3
+ size 15085
global_step_1500/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:f380759d72f40ba93d61ed1ce5b599b4079df80ed3c29790c6be201135270835
3
+ size 15085
global_step_1500/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 sha256:7a9f6850ba272661b812f1d460bb336e0eab1041d2a528bbc8d74d632a682a9b
3
+ size 15085
global_step_1500/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 sha256:451c99b32823e624634cfad9d3ec578dc65a756f19b54fbdbc54977f02781ef2
3
+ size 15085
global_step_1500/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 sha256:8a9ed7504384e59782e7b6d6e08794015169f6356d70ee4d73c9ca205f210609
3
+ size 15085
global_step_1500/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:c3399f69b768eff13d26d3ba1dffa8b0aba59f710bfa69f3e99b6d2514568a42
3
+ size 15085
global_step_1500/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 sha256:5f28ada86beb31a0ae8f03f12c073280f4fd0ec0a393533e8affabe6f7c20717
3
+ size 15085
global_step_1500/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 sha256:68a9332f8ac6b75605576b15966258d23e802640c3d243fd9bbfb39acbf05083
3
+ size 15085
global_step_1500/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_1500/actor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
global_step_1500/actor/model_world_size_16_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:675bcd8fc44da1ff9aaf6f79bb2e0ff5bfa1fe3909df5cb7883328a4cbf07f2b
3
+ size 102426389
global_step_1500/actor/model_world_size_16_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0493d262f4c03a114be259cd4afccc057605c32b5371c324af300b83e08a1031
3
+ size 102426389
global_step_1500/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:acec88dd076f0ab5950a4c6e5b279026445bf95f663726c5841200471e141658
3
+ size 102426687
global_step_1500/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:eca005706dc94b9aaaf6da32826e1ba67b042fae10d7299d9a6020fb29157795
3
+ size 102426687
global_step_1500/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:cd3bafd2aa5760967d9c3646c078eb73a216a93221c4a864c21165e054226961
3
+ size 102426687
global_step_1500/actor/model_world_size_16_rank_13.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806c6baebac9a99a0f856945caa4ce415fff51033a4779b797eaac9e78f61d84
3
+ size 102426687
global_step_1500/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:c130f08858b7d50fe2290ae5e993f1afecb89eec669f31e9a787568b13283d3d
3
+ size 102426687
global_step_1500/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:a1a177f2a53540ad27fa1f188a12c08efe4a40db223d657380cf138f3af3fea1
3
+ size 102426687
global_step_1500/actor/model_world_size_16_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0d81bcd04882a2e6cb46d7630c185bb0ab00b663b529b0e5a0b714468927a5
3
+ size 102426389
global_step_1500/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:e57e35890cf5853667f40d1cbeb21f511e68ebbdd4c616f781da4427663f1d66
3
+ size 102426389
global_step_1500/actor/model_world_size_16_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf4475a8991a93f9da13d9a5084968927e6f3b405aac29ecbad312eac2d38c5
3
+ size 102426389
global_step_1500/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:eda3ab004357ddc24618f3e7e74721ce13850cae6ef2cefaff8f10d2e2a1eb36
3
+ size 102426389
global_step_1500/actor/model_world_size_16_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4406fdbc33dc53dbeff014d4ddd15cced1d53c9e629b41eb4a5f13b2e98a67
3
+ size 102426389
global_step_1500/actor/model_world_size_16_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058c64e971076baa4984cc1ff24d09c39867cbf166264e13112dde5e868e1b2d
3
+ size 102426389
global_step_1500/actor/model_world_size_16_rank_8.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b2f8c7c268cdf3993e82bcec47b87d4f20acd93da4abe85b67e69b81d56e1cd
3
+ size 102426389
global_step_1500/actor/model_world_size_16_rank_9.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a704d424a0f2e0c26a5d560768c930cc58dbc41e7be1d590ecbf342a98667d6
3
+ size 102426389
global_step_1500/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:c40bb43156a3e9556c4dea25ae40d26c212f860653fb6e11ecc4d380ba4b9bec
3
+ size 180938821
global_step_1500/actor/optim_world_size_16_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455ce678ee2c36a5cc40ea2cbb3f60843ccbab3edb58295c6a955a3f47c67708
3
+ size 180938821
global_step_1500/actor/optim_world_size_16_rank_10.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a316b2b8187854e00527c2c1e6c319278603f64b5f58318cdac31f078d3f8bf
3
+ size 180938926
global_step_1500/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:a3d5dec182452759971018209fa985cd8dd96f1271792277c8882defe936fbe8
3
+ size 180938926
global_step_1500/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:eb21eea3f6435f9413993a0c9a99aa4699f52f2e3febc9be0b92a072bc6e1290
3
+ size 180938926
global_step_1500/actor/optim_world_size_16_rank_13.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a727969590e37a352f1fcd9c4245748821627350aee54ed3fab8b87502e8285
3
+ size 180938926
global_step_1500/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:e8cfacc5d74449bce8d42dcfee9b029b17141efe93e2ad47b8b0e80619dd8538
3
+ size 180938926
global_step_1500/actor/optim_world_size_16_rank_15.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e9798f1279fd8de697fc99c1b5d5b6a44ef3788ce9df035f9409c017fb15474
3
+ size 180938926
global_step_1500/actor/optim_world_size_16_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75b2365e265d7afc7596db88bcbba1b1ef64c12d4404038bed3790068e024c0b
3
+ size 180938821
global_step_1500/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:c7608b8a83bf2f12e2ff6e3368bc6272453367fdee73bc5906952b105c81172f
3
+ size 180938821
global_step_1500/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:c2a5c6493687d082cacd486cfe92578c5277346b3d542fb542877d4b311793e1
3
+ size 180938821
global_step_1500/actor/optim_world_size_16_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:929a239c83080da9d3147deb334cf5ad3e24a0a6c3377ca09e3ca3aead63262c
3
+ size 180938821
global_step_1500/actor/optim_world_size_16_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92cfb51fa1e637b54e9f2b7123ca261b28b4cc5dd60b03520fcd068b529d3976
3
+ size 180938821
global_step_1500/actor/optim_world_size_16_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfd4976dbbe64db770d8a76bd4b392d252789bf77d0613f8ae480774d625c5e
3
+ size 180938821