Hugging Face's logo

mm-o1
/
Qwen2VL-72B-sft-v2

Image-Text-to-Text
Transformers
Safetensors
qwen2_vl
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1
Sicong commited on
Commit
52640ba
·
verified ·
1 Parent(s): a11c94f

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +16 -0
  3. all_results.json +8 -0
  4. chat_template.json +3 -0
  5. checkpoint-3089/added_tokens.json +16 -0
  6. checkpoint-3089/chat_template.json +3 -0
  7. checkpoint-3089/config.json +48 -0
  8. checkpoint-3089/generation_config.json +13 -0
  9. checkpoint-3089/global_step3089/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
  10. checkpoint-3089/global_step3089/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
  11. checkpoint-3089/global_step3089/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  12. checkpoint-3089/global_step3089/zero_pp_rank_10_mp_rank_00_model_states.pt +3 -0
  13. checkpoint-3089/global_step3089/zero_pp_rank_11_mp_rank_00_model_states.pt +3 -0
  14. checkpoint-3089/global_step3089/zero_pp_rank_12_mp_rank_00_model_states.pt +3 -0
  15. checkpoint-3089/global_step3089/zero_pp_rank_13_mp_rank_00_model_states.pt +3 -0
  16. checkpoint-3089/global_step3089/zero_pp_rank_14_mp_rank_00_model_states.pt +3 -0
  17. checkpoint-3089/global_step3089/zero_pp_rank_15_mp_rank_00_model_states.pt +3 -0
  18. checkpoint-3089/global_step3089/zero_pp_rank_16_mp_rank_00_model_states.pt +3 -0
  19. checkpoint-3089/global_step3089/zero_pp_rank_17_mp_rank_00_model_states.pt +3 -0
  20. checkpoint-3089/global_step3089/zero_pp_rank_18_mp_rank_00_model_states.pt +3 -0
  21. checkpoint-3089/global_step3089/zero_pp_rank_19_mp_rank_00_model_states.pt +3 -0
  22. checkpoint-3089/global_step3089/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  23. checkpoint-3089/global_step3089/zero_pp_rank_20_mp_rank_00_model_states.pt +3 -0
  24. checkpoint-3089/global_step3089/zero_pp_rank_21_mp_rank_00_model_states.pt +3 -0
  25. checkpoint-3089/global_step3089/zero_pp_rank_22_mp_rank_00_model_states.pt +3 -0
  26. checkpoint-3089/global_step3089/zero_pp_rank_23_mp_rank_00_model_states.pt +3 -0
  27. checkpoint-3089/global_step3089/zero_pp_rank_24_mp_rank_00_model_states.pt +3 -0
  28. checkpoint-3089/global_step3089/zero_pp_rank_25_mp_rank_00_model_states.pt +3 -0
  29. checkpoint-3089/global_step3089/zero_pp_rank_26_mp_rank_00_model_states.pt +3 -0
  30. checkpoint-3089/global_step3089/zero_pp_rank_27_mp_rank_00_model_states.pt +3 -0
  31. checkpoint-3089/global_step3089/zero_pp_rank_28_mp_rank_00_model_states.pt +3 -0
  32. checkpoint-3089/global_step3089/zero_pp_rank_29_mp_rank_00_model_states.pt +3 -0
  33. checkpoint-3089/global_step3089/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  34. checkpoint-3089/global_step3089/zero_pp_rank_30_mp_rank_00_model_states.pt +3 -0
  35. checkpoint-3089/global_step3089/zero_pp_rank_31_mp_rank_00_model_states.pt +3 -0
  36. checkpoint-3089/global_step3089/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  37. checkpoint-3089/global_step3089/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  38. checkpoint-3089/global_step3089/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  39. checkpoint-3089/global_step3089/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  40. checkpoint-3089/global_step3089/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  41. checkpoint-3089/global_step3089/zero_pp_rank_8_mp_rank_00_model_states.pt +3 -0
  42. checkpoint-3089/global_step3089/zero_pp_rank_9_mp_rank_00_model_states.pt +3 -0
  43. checkpoint-3089/latest +1 -0
  44. checkpoint-3089/merges.txt +0 -0
  45. checkpoint-3089/model-00001-of-00031.safetensors +3 -0
  46. checkpoint-3089/model-00002-of-00031.safetensors +3 -0
  47. checkpoint-3089/model-00003-of-00031.safetensors +3 -0
  48. checkpoint-3089/model-00004-of-00031.safetensors +3 -0
  49. checkpoint-3089/model-00005-of-00031.safetensors +3 -0
  50. checkpoint-3089/model-00006-of-00031.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 3876169351954432.0,
4
+ "train_loss": 0.8143089480599218,
5
+ "train_runtime": 151234.6723,
6
+ "train_samples_per_second": 2.614,
7
+ "train_steps_per_second": 0.02
8
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
checkpoint-3089/added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
checkpoint-3089/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
checkpoint-3089/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/zhangh/sicong/vl3_data/checkpoints/Qwen/Qwen2-VL-72B-Instruct",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 29568,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 80,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.0",
35
+ "use_cache": false,
36
+ "use_sliding_window": false,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "hidden_size": 8192,
40
+ "in_chans": 3,
41
+ "model_type": "qwen2_vl",
42
+ "spatial_patch_size": 14
43
+ },
44
+ "vision_end_token_id": 151653,
45
+ "vision_start_token_id": 151652,
46
+ "vision_token_id": 151654,
47
+ "vocab_size": 152064
48
+ }
checkpoint-3089/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.46.0"
13
+ }
checkpoint-3089/global_step3089/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9af1bdd887a1da4b3a35821b9c173ad288d30d6bb27169f9c389484f75ec90
3
+ size 27264832986
checkpoint-3089/global_step3089/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0549f952cf6f55d73bd5593e80f1153ef9f97516270a218b09e18020cee7220c
3
+ size 27264832986
checkpoint-3089/global_step3089/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e41434a5ad731a78a8dad2b1ef56d4d1cb8e41fca57d3e782e00822b3fb2621
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_10_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ad25e50e28a70dd80e67648f833b84b88b8baf0f27c478fd14cb34e7489905
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_11_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c049a00ebf7e1e30fbeb2c4b6d6da7bd69cf27459b7886b7aafd75aea3f301b
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_12_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f8c19548fae28f04bf6d71a44c3bbee777173465e1208c48ed4d75665f1106
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_13_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965f500adc9dc48d10e97f0cd1f6c82eb16b2cdb1dd6174484475175406265d3
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_14_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ada2cbfa52a5681bbfd03b7215e0f7e2840a12a039fcac4e3eabd9d63c1c40c
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_15_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c882f6a86a3bebf481a99fef4f3eefcf7c1e692f7b9405268c3735dccbe5f8d2
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_16_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ef144674ef9452e04a1175468dcf6d9305b0e61564788bbe87da7cc3c2888c
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_17_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223d7ab37dbba4a4b14873b2fe86dec125bd8fd9e265620942831da2915fb994
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_18_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c97513b431c66edbe12d2a70006952368038c67fc2cb272900e6d0e66b9709
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_19_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5120dcc9bf408d6ca670be98e16670574b1ac931d7ee4fd4aae9ed8d316aa0
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a67ce8ae0efcc851dfb916eed74e99a33f3d3f70a1248549b5f4119eadc907
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_20_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd189deeee01907e169f047d7eead0ed03b473722e88fbeb16aa2a81becafea1
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_21_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe70438be54b97ce124c0002c8dbfc5819a99df7f819a8fa8609d3ecc7954b7
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_22_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ec1550f4a8bca06d9b3f45ac9d2954e093260e4a9c126eea126c5d7d98ba04
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_23_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add5a9277b6d6272ad6c9f7a2b92d33cc0b558aca26fdfc00869d81f38e12c4f
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_24_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4de61fde067204c4b1fd75c14baac50576b32b0c70403cdf8b150d53e25304
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_25_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c06aa5093120584a1efed49d1e45bc5054476c945f54e5c2ccd9f75a7d11d1
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_26_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4605ae8b1913f100eb953def115012e0612a9eca6e19f7d1a425262a84313477
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_27_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1996d756bf4976e4bf688a8f13a6ceb8e1bb9f89b447eded990ae372ef54b4b1
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_28_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b7a06abcddc4c3af4a0d3aa86bd0be13b2320587dc7a868a176dfc8d93eb5b
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_29_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34a62b2e4e0178139b92da488ed9f08ad4c3db98eb19586599340562af8a33fc
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbfcfff5dd0ea8985741ec5dc10efd4849babff293148f29d6c4962dfe31f3f1
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_30_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f446e13e565029ee5a6c917cfea46acc17128c270d4603a496504c52c541c6
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_31_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edacd886404b1ec1847ff0f1fa276de3c712cd80d92d8b8199c16ef5484595f
3
+ size 44481433
checkpoint-3089/global_step3089/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef52638e3827b7f3c5c2eed9001269e03c337c780988d905a8830734587117d2
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2521dee64bae1393a9d70aec44f82a261302f907ace41e785081036c9e4c3e6c
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a89df309ddc9916c596386daf668786315c6fc124d5045467aab5f9618a77a8
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a495a92d5551d5d5c4a0b8e51b4ac6e0fee89e5788d90948b66bce8c0ab14c
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63d0db21fcd77d865910e86142b2ec7bb949d9cce83117c164900a97de0b28b3
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_8_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fceef47d85c46b79db9195110086d58c47ee466661067bc16d9b40fe026305
3
+ size 44479684
checkpoint-3089/global_step3089/zero_pp_rank_9_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2ad852d3fe75b8bd0e1a811e0462c18fac478bcf0075b6ef7b013ce3604b617
3
+ size 44479684
checkpoint-3089/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step3089
checkpoint-3089/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3089/model-00001-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a35db42a610fa0177bed31f85747ea9c6753f50e424c5a2033fc0bbb5531c8d
3
+ size 4676624560
checkpoint-3089/model-00002-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d75f14db98499d917166ea549a2590fda0ef8646303d87009f5a6f3385b865e3
3
+ size 4781670320
checkpoint-3089/model-00003-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02cf6ba2f44a0b8ec9921255d7ab0b7b7b7cb62c186ca5d9074aac0eba45362
3
+ size 4964101384
checkpoint-3089/model-00004-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b5dc8de56dcf15b7f46c058cda975edd3a0d3595563c815bfe515ca77987af
3
+ size 4781637328
checkpoint-3089/model-00005-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200b6d5d9230fd0de547eb1ae87210faf45fc35a6793bad03d4b19222c408b87
3
+ size 4781670344
checkpoint-3089/model-00006-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e65e1295c4f183300eaeda92bd9b8c1544898cbb3fb9eb5ca021e4d2b99019
3
+ size 4781670360