Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +237 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/added_tokens.json +24 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/chat_template.json +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/config.json +50 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/generation_config.json +14 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/mp_rank_00_model_states.pt +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/latest +1 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/merges.txt +0 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model-00001-of-00004.safetensors +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model-00002-of-00004.safetensors +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model-00003-of-00004.safetensors +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model-00004-of-00004.safetensors +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model.safetensors.index.json +736 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/preprocessor_config.json +29 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_0.pth +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_1.pth +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_2.pth +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_3.pth +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_4.pth +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_5.pth +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_6.pth +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_7.pth +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/special_tokens_map.json +31 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/tokenizer.json +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/tokenizer_config.json +209 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/trainer_state.json +0 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/training_args.bin +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/vocab.json +0 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/zero_to_fp32.py +674 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000000_call_0000000_sample_00_20260304_065934_031603.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000001_call_0000001_sample_00_20260304_070203_270330.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000002_call_0000002_sample_00_20260304_070441_629095.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000003_call_0000003_sample_00_20260304_070732_079519.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000004_call_0000004_sample_00_20260304_071006_508777.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000005_call_0000005_sample_00_20260304_071219_813475.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000006_call_0000006_sample_00_20260304_071451_706380.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000007_call_0000007_sample_00_20260304_071723_356255.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000008_call_0000008_sample_00_20260304_071955_246959.png +0 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000009_call_0000009_sample_00_20260304_072248_820807.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000010_call_0000010_sample_00_20260304_072522_834795.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000011_call_0000011_sample_00_20260304_072755_705550.png +3 -0
- grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000012_call_0000012_sample_00_20260304_073037_950716.png +3 -0
.gitattributes
CHANGED
|
@@ -7967,3 +7967,240 @@ grpo-pure-multistep-7b-0302-005/rollout_visualizations/rollout_step_0000306_call
|
|
| 7967 |
grpo-pure-multistep-7b-0302-005/rollout_visualizations/rollout_step_0000307_call_0000307_sample_00_20260304_054720_820491.png filter=lfs diff=lfs merge=lfs -text
|
| 7968 |
grpo-pure-multistep-7b-0302-005/rollout_visualizations/rollout_step_0000308_call_0000308_sample_00_20260304_054756_883593.png filter=lfs diff=lfs merge=lfs -text
|
| 7969 |
sft-multistep-cot-7b-0303-40epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7967 |
grpo-pure-multistep-7b-0302-005/rollout_visualizations/rollout_step_0000307_call_0000307_sample_00_20260304_054720_820491.png filter=lfs diff=lfs merge=lfs -text
|
| 7968 |
grpo-pure-multistep-7b-0302-005/rollout_visualizations/rollout_step_0000308_call_0000308_sample_00_20260304_054756_883593.png filter=lfs diff=lfs merge=lfs -text
|
| 7969 |
sft-multistep-cot-7b-0303-40epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 7970 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 7971 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000000_call_0000000_sample_00_20260304_065934_031603.png filter=lfs diff=lfs merge=lfs -text
|
| 7972 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000001_call_0000001_sample_00_20260304_070203_270330.png filter=lfs diff=lfs merge=lfs -text
|
| 7973 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000002_call_0000002_sample_00_20260304_070441_629095.png filter=lfs diff=lfs merge=lfs -text
|
| 7974 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000003_call_0000003_sample_00_20260304_070732_079519.png filter=lfs diff=lfs merge=lfs -text
|
| 7975 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000004_call_0000004_sample_00_20260304_071006_508777.png filter=lfs diff=lfs merge=lfs -text
|
| 7976 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000005_call_0000005_sample_00_20260304_071219_813475.png filter=lfs diff=lfs merge=lfs -text
|
| 7977 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000006_call_0000006_sample_00_20260304_071451_706380.png filter=lfs diff=lfs merge=lfs -text
|
| 7978 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000007_call_0000007_sample_00_20260304_071723_356255.png filter=lfs diff=lfs merge=lfs -text
|
| 7979 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000009_call_0000009_sample_00_20260304_072248_820807.png filter=lfs diff=lfs merge=lfs -text
|
| 7980 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000010_call_0000010_sample_00_20260304_072522_834795.png filter=lfs diff=lfs merge=lfs -text
|
| 7981 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000011_call_0000011_sample_00_20260304_072755_705550.png filter=lfs diff=lfs merge=lfs -text
|
| 7982 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000012_call_0000012_sample_00_20260304_073037_950716.png filter=lfs diff=lfs merge=lfs -text
|
| 7983 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000013_call_0000013_sample_00_20260304_073313_489605.png filter=lfs diff=lfs merge=lfs -text
|
| 7984 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000014_call_0000014_sample_00_20260304_073524_209534.png filter=lfs diff=lfs merge=lfs -text
|
| 7985 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000015_call_0000015_sample_00_20260304_073808_797532.png filter=lfs diff=lfs merge=lfs -text
|
| 7986 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000016_call_0000016_sample_00_20260304_074026_859643.png filter=lfs diff=lfs merge=lfs -text
|
| 7987 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000017_call_0000017_sample_00_20260304_074306_245572.png filter=lfs diff=lfs merge=lfs -text
|
| 7988 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000018_call_0000018_sample_00_20260304_074449_967198.png filter=lfs diff=lfs merge=lfs -text
|
| 7989 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000019_call_0000019_sample_00_20260304_074729_376915.png filter=lfs diff=lfs merge=lfs -text
|
| 7990 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000020_call_0000020_sample_00_20260304_075007_166248.png filter=lfs diff=lfs merge=lfs -text
|
| 7991 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000021_call_0000021_sample_00_20260304_075255_099963.png filter=lfs diff=lfs merge=lfs -text
|
| 7992 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000022_call_0000022_sample_00_20260304_075539_479773.png filter=lfs diff=lfs merge=lfs -text
|
| 7993 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000023_call_0000023_sample_00_20260304_075823_414693.png filter=lfs diff=lfs merge=lfs -text
|
| 7994 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000024_call_0000024_sample_00_20260304_080057_218098.png filter=lfs diff=lfs merge=lfs -text
|
| 7995 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000025_call_0000025_sample_00_20260304_080321_383047.png filter=lfs diff=lfs merge=lfs -text
|
| 7996 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000026_call_0000026_sample_00_20260304_080544_795525.png filter=lfs diff=lfs merge=lfs -text
|
| 7997 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000027_call_0000027_sample_00_20260304_080825_900441.png filter=lfs diff=lfs merge=lfs -text
|
| 7998 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000028_call_0000028_sample_00_20260304_081101_825470.png filter=lfs diff=lfs merge=lfs -text
|
| 7999 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000029_call_0000029_sample_00_20260304_081353_293652.png filter=lfs diff=lfs merge=lfs -text
|
| 8000 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000030_call_0000030_sample_00_20260304_081628_366362.png filter=lfs diff=lfs merge=lfs -text
|
| 8001 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000031_call_0000031_sample_00_20260304_081848_148944.png filter=lfs diff=lfs merge=lfs -text
|
| 8002 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000032_call_0000032_sample_00_20260304_082122_490621.png filter=lfs diff=lfs merge=lfs -text
|
| 8003 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000033_call_0000033_sample_00_20260304_082343_335206.png filter=lfs diff=lfs merge=lfs -text
|
| 8004 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000034_call_0000034_sample_00_20260304_082607_460362.png filter=lfs diff=lfs merge=lfs -text
|
| 8005 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000035_call_0000035_sample_00_20260304_082828_810323.png filter=lfs diff=lfs merge=lfs -text
|
| 8006 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000036_call_0000036_sample_00_20260304_083122_111219.png filter=lfs diff=lfs merge=lfs -text
|
| 8007 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000037_call_0000037_sample_00_20260304_083418_612678.png filter=lfs diff=lfs merge=lfs -text
|
| 8008 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000039_call_0000039_sample_00_20260304_083847_082286.png filter=lfs diff=lfs merge=lfs -text
|
| 8009 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000040_call_0000040_sample_00_20260304_084117_541941.png filter=lfs diff=lfs merge=lfs -text
|
| 8010 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000041_call_0000041_sample_00_20260304_084339_887535.png filter=lfs diff=lfs merge=lfs -text
|
| 8011 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000042_call_0000042_sample_00_20260304_084619_785406.png filter=lfs diff=lfs merge=lfs -text
|
| 8012 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000043_call_0000043_sample_00_20260304_084845_008647.png filter=lfs diff=lfs merge=lfs -text
|
| 8013 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000046_call_0000046_sample_00_20260304_085527_928419.png filter=lfs diff=lfs merge=lfs -text
|
| 8014 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000047_call_0000047_sample_00_20260304_085744_031370.png filter=lfs diff=lfs merge=lfs -text
|
| 8015 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000048_call_0000048_sample_00_20260304_085950_675827.png filter=lfs diff=lfs merge=lfs -text
|
| 8016 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000049_call_0000049_sample_00_20260304_090205_843461.png filter=lfs diff=lfs merge=lfs -text
|
| 8017 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000050_call_0000050_sample_00_20260304_090439_491074.png filter=lfs diff=lfs merge=lfs -text
|
| 8018 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000051_call_0000051_sample_00_20260304_090711_049622.png filter=lfs diff=lfs merge=lfs -text
|
| 8019 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000052_call_0000052_sample_00_20260304_090919_467509.png filter=lfs diff=lfs merge=lfs -text
|
| 8020 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000053_call_0000053_sample_00_20260304_091136_536330.png filter=lfs diff=lfs merge=lfs -text
|
| 8021 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000054_call_0000054_sample_00_20260304_091431_551713.png filter=lfs diff=lfs merge=lfs -text
|
| 8022 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000055_call_0000055_sample_00_20260304_091652_487084.png filter=lfs diff=lfs merge=lfs -text
|
| 8023 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000056_call_0000056_sample_00_20260304_091917_202344.png filter=lfs diff=lfs merge=lfs -text
|
| 8024 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000058_call_0000058_sample_00_20260304_092434_866365.png filter=lfs diff=lfs merge=lfs -text
|
| 8025 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000059_call_0000059_sample_00_20260304_092712_489735.png filter=lfs diff=lfs merge=lfs -text
|
| 8026 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000060_call_0000060_sample_00_20260304_093016_425378.png filter=lfs diff=lfs merge=lfs -text
|
| 8027 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000061_call_0000061_sample_00_20260304_093252_985349.png filter=lfs diff=lfs merge=lfs -text
|
| 8028 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000062_call_0000062_sample_00_20260304_093553_140216.png filter=lfs diff=lfs merge=lfs -text
|
| 8029 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000063_call_0000063_sample_00_20260304_093808_075819.png filter=lfs diff=lfs merge=lfs -text
|
| 8030 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000064_call_0000064_sample_00_20260304_094106_315188.png filter=lfs diff=lfs merge=lfs -text
|
| 8031 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000065_call_0000065_sample_00_20260304_094348_165116.png filter=lfs diff=lfs merge=lfs -text
|
| 8032 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000066_call_0000066_sample_00_20260304_094531_583391.png filter=lfs diff=lfs merge=lfs -text
|
| 8033 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000067_call_0000067_sample_00_20260304_094743_825347.png filter=lfs diff=lfs merge=lfs -text
|
| 8034 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000068_call_0000068_sample_00_20260304_095019_613967.png filter=lfs diff=lfs merge=lfs -text
|
| 8035 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000069_call_0000069_sample_00_20260304_095213_989780.png filter=lfs diff=lfs merge=lfs -text
|
| 8036 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000070_call_0000070_sample_00_20260304_095413_949931.png filter=lfs diff=lfs merge=lfs -text
|
| 8037 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000071_call_0000071_sample_00_20260304_095621_062269.png filter=lfs diff=lfs merge=lfs -text
|
| 8038 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000072_call_0000072_sample_00_20260304_095823_178553.png filter=lfs diff=lfs merge=lfs -text
|
| 8039 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000073_call_0000073_sample_00_20260304_100042_598488.png filter=lfs diff=lfs merge=lfs -text
|
| 8040 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000074_call_0000074_sample_00_20260304_100234_801918.png filter=lfs diff=lfs merge=lfs -text
|
| 8041 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000077_call_0000077_sample_00_20260304_100819_465124.png filter=lfs diff=lfs merge=lfs -text
|
| 8042 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000078_call_0000078_sample_00_20260304_101020_194637.png filter=lfs diff=lfs merge=lfs -text
|
| 8043 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000079_call_0000079_sample_00_20260304_101231_498970.png filter=lfs diff=lfs merge=lfs -text
|
| 8044 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000080_call_0000080_sample_00_20260304_101442_883385.png filter=lfs diff=lfs merge=lfs -text
|
| 8045 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000081_call_0000081_sample_00_20260304_101649_526957.png filter=lfs diff=lfs merge=lfs -text
|
| 8046 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000084_call_0000084_sample_00_20260304_102149_846665.png filter=lfs diff=lfs merge=lfs -text
|
| 8047 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000085_call_0000085_sample_00_20260304_102339_839898.png filter=lfs diff=lfs merge=lfs -text
|
| 8048 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000087_call_0000087_sample_00_20260304_102750_359737.png filter=lfs diff=lfs merge=lfs -text
|
| 8049 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000088_call_0000088_sample_00_20260304_102945_226569.png filter=lfs diff=lfs merge=lfs -text
|
| 8050 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000089_call_0000089_sample_00_20260304_103134_997476.png filter=lfs diff=lfs merge=lfs -text
|
| 8051 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000092_call_0000092_sample_00_20260304_103616_320941.png filter=lfs diff=lfs merge=lfs -text
|
| 8052 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000093_call_0000093_sample_00_20260304_103800_184445.png filter=lfs diff=lfs merge=lfs -text
|
| 8053 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000094_call_0000094_sample_00_20260304_103932_329727.png filter=lfs diff=lfs merge=lfs -text
|
| 8054 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000095_call_0000095_sample_00_20260304_104113_874922.png filter=lfs diff=lfs merge=lfs -text
|
| 8055 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000098_call_0000098_sample_00_20260304_104704_202610.png filter=lfs diff=lfs merge=lfs -text
|
| 8056 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000099_call_0000099_sample_00_20260304_104932_756234.png filter=lfs diff=lfs merge=lfs -text
|
| 8057 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000100_call_0000100_sample_00_20260304_105049_358738.png filter=lfs diff=lfs merge=lfs -text
|
| 8058 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000101_call_0000101_sample_00_20260304_105225_194719.png filter=lfs diff=lfs merge=lfs -text
|
| 8059 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000102_call_0000102_sample_00_20260304_105404_621825.png filter=lfs diff=lfs merge=lfs -text
|
| 8060 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000103_call_0000103_sample_00_20260304_105613_356449.png filter=lfs diff=lfs merge=lfs -text
|
| 8061 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000105_call_0000105_sample_00_20260304_110006_370503.png filter=lfs diff=lfs merge=lfs -text
|
| 8062 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000106_call_0000106_sample_00_20260304_110154_840736.png filter=lfs diff=lfs merge=lfs -text
|
| 8063 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000107_call_0000107_sample_00_20260304_110326_119775.png filter=lfs diff=lfs merge=lfs -text
|
| 8064 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000108_call_0000108_sample_00_20260304_110501_041674.png filter=lfs diff=lfs merge=lfs -text
|
| 8065 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000110_call_0000110_sample_00_20260304_110744_699047.png filter=lfs diff=lfs merge=lfs -text
|
| 8066 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000113_call_0000113_sample_00_20260304_111211_167506.png filter=lfs diff=lfs merge=lfs -text
|
| 8067 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000114_call_0000114_sample_00_20260304_111342_201923.png filter=lfs diff=lfs merge=lfs -text
|
| 8068 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000116_call_0000116_sample_00_20260304_111629_530656.png filter=lfs diff=lfs merge=lfs -text
|
| 8069 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000117_call_0000117_sample_00_20260304_111752_798789.png filter=lfs diff=lfs merge=lfs -text
|
| 8070 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000120_call_0000120_sample_00_20260304_112140_114393.png filter=lfs diff=lfs merge=lfs -text
|
| 8071 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000121_call_0000121_sample_00_20260304_112254_164366.png filter=lfs diff=lfs merge=lfs -text
|
| 8072 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000122_call_0000122_sample_00_20260304_112412_189546.png filter=lfs diff=lfs merge=lfs -text
|
| 8073 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000123_call_0000123_sample_00_20260304_112525_511024.png filter=lfs diff=lfs merge=lfs -text
|
| 8074 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000124_call_0000124_sample_00_20260304_112637_215289.png filter=lfs diff=lfs merge=lfs -text
|
| 8075 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000125_call_0000125_sample_00_20260304_112749_324764.png filter=lfs diff=lfs merge=lfs -text
|
| 8076 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000126_call_0000126_sample_00_20260304_112906_770246.png filter=lfs diff=lfs merge=lfs -text
|
| 8077 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000127_call_0000127_sample_00_20260304_113026_757080.png filter=lfs diff=lfs merge=lfs -text
|
| 8078 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000128_call_0000128_sample_00_20260304_113158_152636.png filter=lfs diff=lfs merge=lfs -text
|
| 8079 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000129_call_0000129_sample_00_20260304_113317_018547.png filter=lfs diff=lfs merge=lfs -text
|
| 8080 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000132_call_0000132_sample_00_20260304_113709_211179.png filter=lfs diff=lfs merge=lfs -text
|
| 8081 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000133_call_0000133_sample_00_20260304_113823_522395.png filter=lfs diff=lfs merge=lfs -text
|
| 8082 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000134_call_0000134_sample_00_20260304_113941_799745.png filter=lfs diff=lfs merge=lfs -text
|
| 8083 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000135_call_0000135_sample_00_20260304_114052_808876.png filter=lfs diff=lfs merge=lfs -text
|
| 8084 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000136_call_0000136_sample_00_20260304_114156_443042.png filter=lfs diff=lfs merge=lfs -text
|
| 8085 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000137_call_0000137_sample_00_20260304_114319_155898.png filter=lfs diff=lfs merge=lfs -text
|
| 8086 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000139_call_0000139_sample_00_20260304_114548_632400.png filter=lfs diff=lfs merge=lfs -text
|
| 8087 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000140_call_0000140_sample_00_20260304_114659_216187.png filter=lfs diff=lfs merge=lfs -text
|
| 8088 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000142_call_0000142_sample_00_20260304_114925_747643.png filter=lfs diff=lfs merge=lfs -text
|
| 8089 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000143_call_0000143_sample_00_20260304_115047_634657.png filter=lfs diff=lfs merge=lfs -text
|
| 8090 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000145_call_0000145_sample_00_20260304_115311_100414.png filter=lfs diff=lfs merge=lfs -text
|
| 8091 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000147_call_0000147_sample_00_20260304_115526_917563.png filter=lfs diff=lfs merge=lfs -text
|
| 8092 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000148_call_0000148_sample_00_20260304_115633_572107.png filter=lfs diff=lfs merge=lfs -text
|
| 8093 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000149_call_0000149_sample_00_20260304_115731_710326.png filter=lfs diff=lfs merge=lfs -text
|
| 8094 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000151_call_0000151_sample_00_20260304_115947_918105.png filter=lfs diff=lfs merge=lfs -text
|
| 8095 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000153_call_0000153_sample_00_20260304_120206_953825.png filter=lfs diff=lfs merge=lfs -text
|
| 8096 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000155_call_0000155_sample_00_20260304_120425_058876.png filter=lfs diff=lfs merge=lfs -text
|
| 8097 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000156_call_0000156_sample_00_20260304_120535_740889.png filter=lfs diff=lfs merge=lfs -text
|
| 8098 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000157_call_0000157_sample_00_20260304_120646_729188.png filter=lfs diff=lfs merge=lfs -text
|
| 8099 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000158_call_0000158_sample_00_20260304_120754_604958.png filter=lfs diff=lfs merge=lfs -text
|
| 8100 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000159_call_0000159_sample_00_20260304_120904_456830.png filter=lfs diff=lfs merge=lfs -text
|
| 8101 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000161_call_0000161_sample_00_20260304_121122_275799.png filter=lfs diff=lfs merge=lfs -text
|
| 8102 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000162_call_0000162_sample_00_20260304_121238_789973.png filter=lfs diff=lfs merge=lfs -text
|
| 8103 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000163_call_0000163_sample_00_20260304_121348_844914.png filter=lfs diff=lfs merge=lfs -text
|
| 8104 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000164_call_0000164_sample_00_20260304_121455_624110.png filter=lfs diff=lfs merge=lfs -text
|
| 8105 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000165_call_0000165_sample_00_20260304_121606_020400.png filter=lfs diff=lfs merge=lfs -text
|
| 8106 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000166_call_0000166_sample_00_20260304_121715_462826.png filter=lfs diff=lfs merge=lfs -text
|
| 8107 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000167_call_0000167_sample_00_20260304_121819_543060.png filter=lfs diff=lfs merge=lfs -text
|
| 8108 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000168_call_0000168_sample_00_20260304_121934_714125.png filter=lfs diff=lfs merge=lfs -text
|
| 8109 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000170_call_0000170_sample_00_20260304_122158_976300.png filter=lfs diff=lfs merge=lfs -text
|
| 8110 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000171_call_0000171_sample_00_20260304_122312_779480.png filter=lfs diff=lfs merge=lfs -text
|
| 8111 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000172_call_0000172_sample_00_20260304_122429_473603.png filter=lfs diff=lfs merge=lfs -text
|
| 8112 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000174_call_0000174_sample_00_20260304_122700_944084.png filter=lfs diff=lfs merge=lfs -text
|
| 8113 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000175_call_0000175_sample_00_20260304_122826_296352.png filter=lfs diff=lfs merge=lfs -text
|
| 8114 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000176_call_0000176_sample_00_20260304_122951_349727.png filter=lfs diff=lfs merge=lfs -text
|
| 8115 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000177_call_0000177_sample_00_20260304_123112_055844.png filter=lfs diff=lfs merge=lfs -text
|
| 8116 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000178_call_0000178_sample_00_20260304_123230_662807.png filter=lfs diff=lfs merge=lfs -text
|
| 8117 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000180_call_0000180_sample_00_20260304_123515_028018.png filter=lfs diff=lfs merge=lfs -text
|
| 8118 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000181_call_0000181_sample_00_20260304_123631_401719.png filter=lfs diff=lfs merge=lfs -text
|
| 8119 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000182_call_0000182_sample_00_20260304_123745_402970.png filter=lfs diff=lfs merge=lfs -text
|
| 8120 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000183_call_0000183_sample_00_20260304_123850_563138.png filter=lfs diff=lfs merge=lfs -text
|
| 8121 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000184_call_0000184_sample_00_20260304_123959_023019.png filter=lfs diff=lfs merge=lfs -text
|
| 8122 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000185_call_0000185_sample_00_20260304_124109_591401.png filter=lfs diff=lfs merge=lfs -text
|
| 8123 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000186_call_0000186_sample_00_20260304_124216_692505.png filter=lfs diff=lfs merge=lfs -text
|
| 8124 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000187_call_0000187_sample_00_20260304_124322_136493.png filter=lfs diff=lfs merge=lfs -text
|
| 8125 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000188_call_0000188_sample_00_20260304_124433_049375.png filter=lfs diff=lfs merge=lfs -text
|
| 8126 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000189_call_0000189_sample_00_20260304_124541_714578.png filter=lfs diff=lfs merge=lfs -text
|
| 8127 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000190_call_0000190_sample_00_20260304_124645_279991.png filter=lfs diff=lfs merge=lfs -text
|
| 8128 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000191_call_0000191_sample_00_20260304_124757_205327.png filter=lfs diff=lfs merge=lfs -text
|
| 8129 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000192_call_0000192_sample_00_20260304_124906_626724.png filter=lfs diff=lfs merge=lfs -text
|
| 8130 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000193_call_0000193_sample_00_20260304_125016_548094.png filter=lfs diff=lfs merge=lfs -text
|
| 8131 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000195_call_0000195_sample_00_20260304_125236_424407.png filter=lfs diff=lfs merge=lfs -text
|
| 8132 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000196_call_0000196_sample_00_20260304_125348_734636.png filter=lfs diff=lfs merge=lfs -text
|
| 8133 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000197_call_0000197_sample_00_20260304_125501_442600.png filter=lfs diff=lfs merge=lfs -text
|
| 8134 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000198_call_0000198_sample_00_20260304_125609_137937.png filter=lfs diff=lfs merge=lfs -text
|
| 8135 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000200_call_0000200_sample_00_20260304_125829_677611.png filter=lfs diff=lfs merge=lfs -text
|
| 8136 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000201_call_0000201_sample_00_20260304_125934_648201.png filter=lfs diff=lfs merge=lfs -text
|
| 8137 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000202_call_0000202_sample_00_20260304_130045_310947.png filter=lfs diff=lfs merge=lfs -text
|
| 8138 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000203_call_0000203_sample_00_20260304_130201_384374.png filter=lfs diff=lfs merge=lfs -text
|
| 8139 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000204_call_0000204_sample_00_20260304_130309_602371.png filter=lfs diff=lfs merge=lfs -text
|
| 8140 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000205_call_0000205_sample_00_20260304_130421_013618.png filter=lfs diff=lfs merge=lfs -text
|
| 8141 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000206_call_0000206_sample_00_20260304_130528_650285.png filter=lfs diff=lfs merge=lfs -text
|
| 8142 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000207_call_0000207_sample_00_20260304_130634_928316.png filter=lfs diff=lfs merge=lfs -text
|
| 8143 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000209_call_0000209_sample_00_20260304_130845_401799.png filter=lfs diff=lfs merge=lfs -text
|
| 8144 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000210_call_0000210_sample_00_20260304_130954_823265.png filter=lfs diff=lfs merge=lfs -text
|
| 8145 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000211_call_0000211_sample_00_20260304_131058_719229.png filter=lfs diff=lfs merge=lfs -text
|
| 8146 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000212_call_0000212_sample_00_20260304_131208_680519.png filter=lfs diff=lfs merge=lfs -text
|
| 8147 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000213_call_0000213_sample_00_20260304_131309_919799.png filter=lfs diff=lfs merge=lfs -text
|
| 8148 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000214_call_0000214_sample_00_20260304_131411_122493.png filter=lfs diff=lfs merge=lfs -text
|
| 8149 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000215_call_0000215_sample_00_20260304_131513_711792.png filter=lfs diff=lfs merge=lfs -text
|
| 8150 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000216_call_0000216_sample_00_20260304_131615_456253.png filter=lfs diff=lfs merge=lfs -text
|
| 8151 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000217_call_0000217_sample_00_20260304_131720_744735.png filter=lfs diff=lfs merge=lfs -text
|
| 8152 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000219_call_0000219_sample_00_20260304_131918_454477.png filter=lfs diff=lfs merge=lfs -text
|
| 8153 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000220_call_0000220_sample_00_20260304_132015_692421.png filter=lfs diff=lfs merge=lfs -text
|
| 8154 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000221_call_0000221_sample_00_20260304_132113_693588.png filter=lfs diff=lfs merge=lfs -text
|
| 8155 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000222_call_0000222_sample_00_20260304_132221_647433.png filter=lfs diff=lfs merge=lfs -text
|
| 8156 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000223_call_0000223_sample_00_20260304_132319_536195.png filter=lfs diff=lfs merge=lfs -text
|
| 8157 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000225_call_0000225_sample_00_20260304_132521_196149.png filter=lfs diff=lfs merge=lfs -text
|
| 8158 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000226_call_0000226_sample_00_20260304_132621_128729.png filter=lfs diff=lfs merge=lfs -text
|
| 8159 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000228_call_0000228_sample_00_20260304_132825_503616.png filter=lfs diff=lfs merge=lfs -text
|
| 8160 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000229_call_0000229_sample_00_20260304_132933_225065.png filter=lfs diff=lfs merge=lfs -text
|
| 8161 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000230_call_0000230_sample_00_20260304_133041_266513.png filter=lfs diff=lfs merge=lfs -text
|
| 8162 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000231_call_0000231_sample_00_20260304_133142_921467.png filter=lfs diff=lfs merge=lfs -text
|
| 8163 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000232_call_0000232_sample_00_20260304_133247_092699.png filter=lfs diff=lfs merge=lfs -text
|
| 8164 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000233_call_0000233_sample_00_20260304_133345_894219.png filter=lfs diff=lfs merge=lfs -text
|
| 8165 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000234_call_0000234_sample_00_20260304_133443_296105.png filter=lfs diff=lfs merge=lfs -text
|
| 8166 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000235_call_0000235_sample_00_20260304_133556_632682.png filter=lfs diff=lfs merge=lfs -text
|
| 8167 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000236_call_0000236_sample_00_20260304_133654_825545.png filter=lfs diff=lfs merge=lfs -text
|
| 8168 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000237_call_0000237_sample_00_20260304_133802_180263.png filter=lfs diff=lfs merge=lfs -text
|
| 8169 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000241_call_0000241_sample_00_20260304_134157_072458.png filter=lfs diff=lfs merge=lfs -text
|
| 8170 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000242_call_0000242_sample_00_20260304_134303_644965.png filter=lfs diff=lfs merge=lfs -text
|
| 8171 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000243_call_0000243_sample_00_20260304_134414_309345.png filter=lfs diff=lfs merge=lfs -text
|
| 8172 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000244_call_0000244_sample_00_20260304_134509_351764.png filter=lfs diff=lfs merge=lfs -text
|
| 8173 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000245_call_0000245_sample_00_20260304_134605_669256.png filter=lfs diff=lfs merge=lfs -text
|
| 8174 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000246_call_0000246_sample_00_20260304_134706_369444.png filter=lfs diff=lfs merge=lfs -text
|
| 8175 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000247_call_0000247_sample_00_20260304_134801_446708.png filter=lfs diff=lfs merge=lfs -text
|
| 8176 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000249_call_0000249_sample_00_20260304_134949_644530.png filter=lfs diff=lfs merge=lfs -text
|
| 8177 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000250_call_0000250_sample_00_20260304_135050_483020.png filter=lfs diff=lfs merge=lfs -text
|
| 8178 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000251_call_0000251_sample_00_20260304_135151_927654.png filter=lfs diff=lfs merge=lfs -text
|
| 8179 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000252_call_0000252_sample_00_20260304_135248_957992.png filter=lfs diff=lfs merge=lfs -text
|
| 8180 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000253_call_0000253_sample_00_20260304_135348_970776.png filter=lfs diff=lfs merge=lfs -text
|
| 8181 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000254_call_0000254_sample_00_20260304_135447_694267.png filter=lfs diff=lfs merge=lfs -text
|
| 8182 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000255_call_0000255_sample_00_20260304_135542_798589.png filter=lfs diff=lfs merge=lfs -text
|
| 8183 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000256_call_0000256_sample_00_20260304_135646_316962.png filter=lfs diff=lfs merge=lfs -text
|
| 8184 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000257_call_0000257_sample_00_20260304_135839_882719.png filter=lfs diff=lfs merge=lfs -text
|
| 8185 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000258_call_0000258_sample_00_20260304_135937_093856.png filter=lfs diff=lfs merge=lfs -text
|
| 8186 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000259_call_0000259_sample_00_20260304_140034_985159.png filter=lfs diff=lfs merge=lfs -text
|
| 8187 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000260_call_0000260_sample_00_20260304_140140_200435.png filter=lfs diff=lfs merge=lfs -text
|
| 8188 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000262_call_0000262_sample_00_20260304_140348_326483.png filter=lfs diff=lfs merge=lfs -text
|
| 8189 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000263_call_0000263_sample_00_20260304_140446_511598.png filter=lfs diff=lfs merge=lfs -text
|
| 8190 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000264_call_0000264_sample_00_20260304_140551_075017.png filter=lfs diff=lfs merge=lfs -text
|
| 8191 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000265_call_0000265_sample_00_20260304_140657_218715.png filter=lfs diff=lfs merge=lfs -text
|
| 8192 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000266_call_0000266_sample_00_20260304_140809_832854.png filter=lfs diff=lfs merge=lfs -text
|
| 8193 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000268_call_0000268_sample_00_20260304_141026_481824.png filter=lfs diff=lfs merge=lfs -text
|
| 8194 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000269_call_0000269_sample_00_20260304_141131_260327.png filter=lfs diff=lfs merge=lfs -text
|
| 8195 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000273_call_0000273_sample_00_20260304_141545_723357.png filter=lfs diff=lfs merge=lfs -text
|
| 8196 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000274_call_0000274_sample_00_20260304_141649_844038.png filter=lfs diff=lfs merge=lfs -text
|
| 8197 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000276_call_0000276_sample_00_20260304_141853_273061.png filter=lfs diff=lfs merge=lfs -text
|
| 8198 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000277_call_0000277_sample_00_20260304_141953_509007.png filter=lfs diff=lfs merge=lfs -text
|
| 8199 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000278_call_0000278_sample_00_20260304_142055_047258.png filter=lfs diff=lfs merge=lfs -text
|
| 8200 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000281_call_0000281_sample_00_20260304_142343_198718.png filter=lfs diff=lfs merge=lfs -text
|
| 8201 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000282_call_0000282_sample_00_20260304_142444_825509.png filter=lfs diff=lfs merge=lfs -text
|
| 8202 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000286_call_0000286_sample_00_20260304_142827_680960.png filter=lfs diff=lfs merge=lfs -text
|
| 8203 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000287_call_0000287_sample_00_20260304_142922_829771.png filter=lfs diff=lfs merge=lfs -text
|
| 8204 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000288_call_0000288_sample_00_20260304_143024_227808.png filter=lfs diff=lfs merge=lfs -text
|
| 8205 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000289_call_0000289_sample_00_20260304_143124_033339.png filter=lfs diff=lfs merge=lfs -text
|
| 8206 |
+
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000290_call_0000290_sample_00_20260304_143230_631937.png filter=lfs diff=lfs merge=lfs -text
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/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 |
+
}
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 18944,
|
| 14 |
+
"max_position_embeddings": 128000,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen2_5_vl",
|
| 17 |
+
"num_attention_heads": 28,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 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": "4.49.0",
|
| 35 |
+
"use_cache": false,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"video_token_id": 151656,
|
| 38 |
+
"vision_config": {
|
| 39 |
+
"hidden_size": 1280,
|
| 40 |
+
"in_chans": 3,
|
| 41 |
+
"model_type": "qwen2_5_vl",
|
| 42 |
+
"spatial_patch_size": 14,
|
| 43 |
+
"tokens_per_second": 2,
|
| 44 |
+
"torch_dtype": "bfloat16"
|
| 45 |
+
},
|
| 46 |
+
"vision_end_token_id": 151653,
|
| 47 |
+
"vision_start_token_id": 151652,
|
| 48 |
+
"vision_token_id": 151654,
|
| 49 |
+
"vocab_size": 152064
|
| 50 |
+
}
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attn_implementation": "flash_attention_2",
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"repetition_penalty": 1.05,
|
| 11 |
+
"temperature": 1e-06,
|
| 12 |
+
"transformers_version": "4.49.0",
|
| 13 |
+
"use_cache": false
|
| 14 |
+
}
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3bf688b84493be06d5a25209a9b444f686e204d6d3487175d0eff176ed033ce
|
| 3 |
+
size 11423430609
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9beffdc04c0251fa8bf2bf6b22b40df2e54565d9a680658c3ebd914ce9db160
|
| 3 |
+
size 11423432465
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:415bbe8d1d979f3ccd44ff9b27c86d0d888c87b96436c8fa14e4c5489a506288
|
| 3 |
+
size 11423432465
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2bae8696a558f1e847e11ece23f66c012149829bb4b1b2e78243ba27fa05515
|
| 3 |
+
size 11423432721
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6de520661c15ef88e7ed4e363c38b0a419e11c43b346b38f75a54371ad0be6d
|
| 3 |
+
size 11423432977
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ba6f9526b595d12b7994e7891d1448aafecf624bc3e09b3aa45a8d34cf95298
|
| 3 |
+
size 11423432593
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9868e43c4623b7477feca772365295955027769523f9c910df8ad9c641e6e6d5
|
| 3 |
+
size 11423432529
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:015f5d1cd8c7955082b4cd1bf04d8227970d0b951fbf07d801d5584205b3070f
|
| 3 |
+
size 11423430289
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/global_step257/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adf08edd5fc4667776cab59d1639a70008539346891648d71bdb18c49fe6f71f
|
| 3 |
+
size 17937826449
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step257
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50d1a81c71b32fb42bd2519064834f030690e520a522cbb72234a4db1c67c108
|
| 3 |
+
size 4968243304
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec768cb47ab9148cebedd234846536b08005aff50a66d73c822d9d3f369adc9b
|
| 3 |
+
size 4991495816
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0a2ab42d95d7db68aaed7f021dc1a703a9eba1e6ce372adb70f865e688d3e0f
|
| 3 |
+
size 4932751040
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee6b16fbf958aebc20e666742fec5bd965571c8dad8af806c00554bb3e475449
|
| 3 |
+
size 1691924384
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,736 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16584333312
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00004-of-00004.safetensors",
|
| 345 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 346 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 348 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 350 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 352 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 354 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 358 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 360 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 362 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 364 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 366 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 370 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 372 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 374 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 376 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 378 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 382 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 384 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 386 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 388 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 390 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 394 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 395 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 396 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 398 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 400 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 402 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 406 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 407 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 408 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 409 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 410 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 411 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 412 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 413 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 414 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 415 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 417 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 418 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 419 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 420 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 421 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 422 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 423 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 424 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 425 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 426 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 427 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 429 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 430 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 431 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 432 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 433 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 434 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 435 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 436 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 437 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 438 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 439 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 441 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 442 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 443 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 444 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 445 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 446 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 447 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 448 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 449 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 450 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 451 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 453 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 454 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 455 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 456 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 457 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 458 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 459 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 460 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 461 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 462 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 463 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 465 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 466 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 467 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 468 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 469 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 470 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 471 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 472 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 473 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 474 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 475 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 477 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 478 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 479 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 480 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 481 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 482 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 483 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 484 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 485 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 486 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 487 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 489 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 490 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 491 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 492 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 493 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 494 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 495 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 496 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 497 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 498 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 499 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 501 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 502 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 503 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 504 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 505 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 506 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 507 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 508 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 509 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 510 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 511 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 513 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 514 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 515 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 516 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 517 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 518 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 519 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 520 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 521 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 522 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 523 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 525 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 526 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 527 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 528 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 529 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 530 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 531 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 532 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 533 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 534 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 535 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 537 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 538 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 539 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 540 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 541 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 542 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 543 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 544 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 545 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 546 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 547 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 549 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 550 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 551 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 552 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 553 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 554 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 555 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 556 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 557 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 558 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 559 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 561 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 562 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 563 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 564 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 565 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 566 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 567 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 568 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 569 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 570 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 571 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 573 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 574 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 575 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 576 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 577 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 578 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 579 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 580 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 581 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 582 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 583 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 585 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 586 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 587 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 588 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 589 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 590 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 591 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 592 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 593 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 594 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 595 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
| 597 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 598 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 599 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 600 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 601 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 602 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 603 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 604 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 605 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 606 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 607 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
|
| 609 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 610 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 611 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 612 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 613 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 614 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 615 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 616 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 617 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 618 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 619 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
| 621 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 622 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 623 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 624 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 625 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 626 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 627 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 628 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 629 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 630 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 631 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 633 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 634 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 635 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 636 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 637 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 638 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 639 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 640 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 641 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 642 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 643 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
|
| 645 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 646 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 647 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 648 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 649 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 650 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 651 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 652 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 653 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 654 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 655 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
| 657 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 658 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 659 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 660 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 661 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 662 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 663 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 664 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 665 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 666 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 667 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 669 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 670 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 671 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 672 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 673 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 674 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 675 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 676 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 677 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 678 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 679 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 681 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 682 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 683 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 684 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 685 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 686 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 687 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 688 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 689 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 690 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 691 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 693 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 694 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 695 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 696 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 697 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 698 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 699 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 700 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 701 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 702 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 703 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 705 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 706 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 707 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 708 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 709 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 710 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 711 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 712 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 713 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 714 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 715 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 717 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 718 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 719 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 720 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 721 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 722 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 723 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 724 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 725 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 726 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 727 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 729 |
+
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
| 730 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
| 731 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
| 732 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
| 733 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
| 734 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
|
| 735 |
+
}
|
| 736 |
+
}
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7507ffe6f4a6591619e4735538a4c63b34c18c28f61275ca6911c85fc606036
|
| 3 |
+
size 16389
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df961d42a597c7259774efa7dac6734fc6af8a6969b50dc0cbcef39e228af96a
|
| 3 |
+
size 16389
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f86b3213692e6123689fab0fde5b5f71a49448f4a1d36a536f77c0de693f4a31
|
| 3 |
+
size 16389
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31cea409c99480f93b7f40d6ed98b3651a94aad7aebe85859c2e26e55b7c69ec
|
| 3 |
+
size 16389
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20bf4744b5cebbb0cac729040d30372131fa458af64cc5047c34f2c011e3437a
|
| 3 |
+
size 16389
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:975630b320624ead998e8f6ad54cf6d2c72bf508356e4d8e6b2f052770345b9d
|
| 3 |
+
size 16389
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:042df4f201d7835d4ae9b210f4078c0ad3a390fe1c62603899d11adb871cdfc2
|
| 3 |
+
size 16389
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7705cc3dcef29e30e8aeb775e724d6478ed64a04c43d9e6cc7d3237d14d3a7f
|
| 3 |
+
size 16325
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/tokenizer_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"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 %}",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null
|
| 209 |
+
}
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:552ef98f41c36c2607409b34c80c8283a97f484a067b6d5c73ff2c9b3f0b1e40
|
| 3 |
+
size 8657
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/checkpoint-257/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,674 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import json
|
| 25 |
+
from tqdm import tqdm
|
| 26 |
+
from collections import OrderedDict
|
| 27 |
+
from dataclasses import dataclass
|
| 28 |
+
|
| 29 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 30 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 31 |
+
from deepspeed.utils import logger
|
| 32 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 33 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 34 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
@dataclass
|
| 38 |
+
class zero_model_state:
|
| 39 |
+
buffers: dict()
|
| 40 |
+
param_shapes: dict()
|
| 41 |
+
shared_params: list
|
| 42 |
+
ds_version: int
|
| 43 |
+
frozen_param_shapes: dict()
|
| 44 |
+
frozen_param_fragments: dict()
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
debug = 0
|
| 48 |
+
|
| 49 |
+
# load to cpu
|
| 50 |
+
device = torch.device('cpu')
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
def atoi(text):
|
| 54 |
+
return int(text) if text.isdigit() else text
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
def natural_keys(text):
|
| 58 |
+
'''
|
| 59 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 60 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 61 |
+
(See Toothy's implementation in the comments)
|
| 62 |
+
'''
|
| 63 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 67 |
+
if not os.path.isdir(checkpoint_dir):
|
| 68 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 69 |
+
|
| 70 |
+
# there should be only one file
|
| 71 |
+
if zero_stage <= 2:
|
| 72 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 73 |
+
elif zero_stage == 3:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 75 |
+
|
| 76 |
+
if not os.path.exists(file):
|
| 77 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 78 |
+
|
| 79 |
+
return file
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 83 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 84 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 85 |
+
|
| 86 |
+
if len(ckpt_files) == 0:
|
| 87 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 88 |
+
|
| 89 |
+
return ckpt_files
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
def get_optim_files(checkpoint_dir):
|
| 93 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
def get_model_state_files(checkpoint_dir):
|
| 97 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
def parse_model_states(files):
|
| 101 |
+
zero_model_states = []
|
| 102 |
+
for file in files:
|
| 103 |
+
state_dict = torch.load(file, map_location=device)
|
| 104 |
+
|
| 105 |
+
if BUFFER_NAMES not in state_dict:
|
| 106 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 107 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 108 |
+
if debug:
|
| 109 |
+
print("Found buffers:", buffer_names)
|
| 110 |
+
|
| 111 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 112 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 113 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 114 |
+
|
| 115 |
+
# collect parameters that are included in param_shapes
|
| 116 |
+
param_names = []
|
| 117 |
+
for s in param_shapes:
|
| 118 |
+
for name in s.keys():
|
| 119 |
+
param_names.append(name)
|
| 120 |
+
|
| 121 |
+
# update with frozen parameters
|
| 122 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 123 |
+
if frozen_param_shapes is not None:
|
| 124 |
+
if debug:
|
| 125 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 126 |
+
param_names += list(frozen_param_shapes.keys())
|
| 127 |
+
|
| 128 |
+
# handle shared params
|
| 129 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 130 |
+
|
| 131 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 132 |
+
|
| 133 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 134 |
+
|
| 135 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 136 |
+
param_shapes=param_shapes,
|
| 137 |
+
shared_params=shared_params,
|
| 138 |
+
ds_version=ds_version,
|
| 139 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 140 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 141 |
+
zero_model_states.append(z_model_state)
|
| 142 |
+
|
| 143 |
+
return zero_model_states
|
| 144 |
+
|
| 145 |
+
|
| 146 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 147 |
+
total_files = len(files)
|
| 148 |
+
state_dicts = []
|
| 149 |
+
for f in files:
|
| 150 |
+
state_dict = torch.load(f, map_location=device)
|
| 151 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 152 |
+
# and also handle the case where it was already removed by another helper script
|
| 153 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 154 |
+
state_dicts.append(state_dict)
|
| 155 |
+
|
| 156 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 157 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 158 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 159 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 160 |
+
|
| 161 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 162 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 163 |
+
# use the max of the partition_count to get the dp world_size.
|
| 164 |
+
|
| 165 |
+
if type(world_size) is list:
|
| 166 |
+
world_size = max(world_size)
|
| 167 |
+
|
| 168 |
+
if world_size != total_files:
|
| 169 |
+
raise ValueError(
|
| 170 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 171 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 172 |
+
)
|
| 173 |
+
|
| 174 |
+
# the groups are named differently in each stage
|
| 175 |
+
if zero_stage <= 2:
|
| 176 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 177 |
+
elif zero_stage == 3:
|
| 178 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 179 |
+
else:
|
| 180 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 181 |
+
|
| 182 |
+
if zero_stage <= 2:
|
| 183 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 184 |
+
elif zero_stage == 3:
|
| 185 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 186 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 187 |
+
#
|
| 188 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 189 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 190 |
+
|
| 191 |
+
fp32_flat_groups = [
|
| 192 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 193 |
+
]
|
| 194 |
+
|
| 195 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 196 |
+
|
| 197 |
+
|
| 198 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 199 |
+
"""
|
| 200 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 201 |
+
|
| 202 |
+
Args:
|
| 203 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 204 |
+
|
| 205 |
+
"""
|
| 206 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 207 |
+
|
| 208 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 209 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 210 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 211 |
+
|
| 212 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 213 |
+
|
| 214 |
+
zero_model_states = parse_model_states(model_files)
|
| 215 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 216 |
+
|
| 217 |
+
if zero_stage <= 2:
|
| 218 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 219 |
+
exclude_frozen_parameters)
|
| 220 |
+
elif zero_stage == 3:
|
| 221 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 222 |
+
exclude_frozen_parameters)
|
| 223 |
+
|
| 224 |
+
|
| 225 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 226 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 227 |
+
return
|
| 228 |
+
|
| 229 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 230 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 231 |
+
|
| 232 |
+
if debug:
|
| 233 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 234 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 235 |
+
|
| 236 |
+
wanted_params = len(frozen_param_shapes)
|
| 237 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 238 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 239 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 240 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 241 |
+
|
| 242 |
+
total_params = 0
|
| 243 |
+
total_numel = 0
|
| 244 |
+
for name, shape in frozen_param_shapes.items():
|
| 245 |
+
total_params += 1
|
| 246 |
+
unpartitioned_numel = shape.numel()
|
| 247 |
+
total_numel += unpartitioned_numel
|
| 248 |
+
|
| 249 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 250 |
+
|
| 251 |
+
if debug:
|
| 252 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 253 |
+
|
| 254 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 255 |
+
|
| 256 |
+
|
| 257 |
+
def _has_callable(obj, fn):
|
| 258 |
+
attr = getattr(obj, fn, None)
|
| 259 |
+
return callable(attr)
|
| 260 |
+
|
| 261 |
+
|
| 262 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 263 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 264 |
+
|
| 265 |
+
# Reconstruction protocol:
|
| 266 |
+
#
|
| 267 |
+
# XXX: document this
|
| 268 |
+
|
| 269 |
+
if debug:
|
| 270 |
+
for i in range(world_size):
|
| 271 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 272 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 273 |
+
|
| 274 |
+
# XXX: memory usage doubles here (zero2)
|
| 275 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 276 |
+
merged_single_partition_of_fp32_groups = []
|
| 277 |
+
for i in range(num_param_groups):
|
| 278 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 279 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 280 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 281 |
+
avail_numel = sum(
|
| 282 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 283 |
+
|
| 284 |
+
if debug:
|
| 285 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 286 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 287 |
+
# not asserting if there is a mismatch due to possible padding
|
| 288 |
+
print(f"Have {avail_numel} numels to process.")
|
| 289 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 290 |
+
|
| 291 |
+
# params
|
| 292 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 293 |
+
# out-of-core computing solution
|
| 294 |
+
total_numel = 0
|
| 295 |
+
total_params = 0
|
| 296 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 297 |
+
offset = 0
|
| 298 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 299 |
+
for name, shape in shapes.items():
|
| 300 |
+
|
| 301 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 302 |
+
total_numel += unpartitioned_numel
|
| 303 |
+
total_params += 1
|
| 304 |
+
|
| 305 |
+
if debug:
|
| 306 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 307 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 308 |
+
offset += unpartitioned_numel
|
| 309 |
+
|
| 310 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 311 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 312 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 313 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 314 |
+
align_to = 2 * world_size
|
| 315 |
+
|
| 316 |
+
def zero2_align(x):
|
| 317 |
+
return align_to * math.ceil(x / align_to)
|
| 318 |
+
|
| 319 |
+
if debug:
|
| 320 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 321 |
+
|
| 322 |
+
offset = zero2_align(offset)
|
| 323 |
+
avail_numel = zero2_align(avail_numel)
|
| 324 |
+
|
| 325 |
+
if debug:
|
| 326 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 327 |
+
|
| 328 |
+
# Sanity check
|
| 329 |
+
if offset != avail_numel:
|
| 330 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 331 |
+
|
| 332 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 333 |
+
|
| 334 |
+
|
| 335 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 336 |
+
exclude_frozen_parameters):
|
| 337 |
+
state_dict = OrderedDict()
|
| 338 |
+
|
| 339 |
+
# buffers
|
| 340 |
+
buffers = zero_model_states[0].buffers
|
| 341 |
+
state_dict.update(buffers)
|
| 342 |
+
if debug:
|
| 343 |
+
print(f"added {len(buffers)} buffers")
|
| 344 |
+
|
| 345 |
+
if not exclude_frozen_parameters:
|
| 346 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 347 |
+
|
| 348 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 349 |
+
|
| 350 |
+
# recover shared parameters
|
| 351 |
+
for pair in zero_model_states[0].shared_params:
|
| 352 |
+
if pair[1] in state_dict:
|
| 353 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 354 |
+
|
| 355 |
+
return state_dict
|
| 356 |
+
|
| 357 |
+
|
| 358 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 359 |
+
remainder = unpartitioned_numel % world_size
|
| 360 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 361 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 362 |
+
return partitioned_numel, padding_numel
|
| 363 |
+
|
| 364 |
+
|
| 365 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 366 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 367 |
+
return
|
| 368 |
+
|
| 369 |
+
if debug:
|
| 370 |
+
for i in range(world_size):
|
| 371 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 372 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 373 |
+
|
| 374 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 375 |
+
wanted_params = len(frozen_param_shapes)
|
| 376 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 377 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 378 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 379 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 380 |
+
|
| 381 |
+
total_params = 0
|
| 382 |
+
total_numel = 0
|
| 383 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 384 |
+
total_params += 1
|
| 385 |
+
unpartitioned_numel = shape.numel()
|
| 386 |
+
total_numel += unpartitioned_numel
|
| 387 |
+
|
| 388 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 389 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 390 |
+
|
| 391 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 392 |
+
|
| 393 |
+
if debug:
|
| 394 |
+
print(
|
| 395 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 396 |
+
)
|
| 397 |
+
|
| 398 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 399 |
+
|
| 400 |
+
|
| 401 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 402 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 403 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 404 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 405 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 406 |
+
|
| 407 |
+
# merge list of dicts, preserving order
|
| 408 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 409 |
+
|
| 410 |
+
if debug:
|
| 411 |
+
for i in range(world_size):
|
| 412 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 413 |
+
|
| 414 |
+
wanted_params = len(param_shapes)
|
| 415 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 416 |
+
# not asserting if there is a mismatch due to possible padding
|
| 417 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 418 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 419 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 420 |
+
|
| 421 |
+
# params
|
| 422 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 423 |
+
# out-of-core computing solution
|
| 424 |
+
offset = 0
|
| 425 |
+
total_numel = 0
|
| 426 |
+
total_params = 0
|
| 427 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
|
| 428 |
+
unpartitioned_numel = shape.numel()
|
| 429 |
+
total_numel += unpartitioned_numel
|
| 430 |
+
total_params += 1
|
| 431 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 432 |
+
|
| 433 |
+
if debug:
|
| 434 |
+
print(
|
| 435 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 436 |
+
)
|
| 437 |
+
|
| 438 |
+
# XXX: memory usage doubles here
|
| 439 |
+
state_dict[name] = torch.cat(
|
| 440 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 441 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 442 |
+
offset += partitioned_numel
|
| 443 |
+
|
| 444 |
+
offset *= world_size
|
| 445 |
+
|
| 446 |
+
# Sanity check
|
| 447 |
+
if offset != avail_numel:
|
| 448 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 449 |
+
|
| 450 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 451 |
+
|
| 452 |
+
|
| 453 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 454 |
+
exclude_frozen_parameters):
|
| 455 |
+
state_dict = OrderedDict()
|
| 456 |
+
|
| 457 |
+
# buffers
|
| 458 |
+
buffers = zero_model_states[0].buffers
|
| 459 |
+
state_dict.update(buffers)
|
| 460 |
+
if debug:
|
| 461 |
+
print(f"added {len(buffers)} buffers")
|
| 462 |
+
|
| 463 |
+
if not exclude_frozen_parameters:
|
| 464 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 465 |
+
|
| 466 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 467 |
+
|
| 468 |
+
# recover shared parameters
|
| 469 |
+
for pair in zero_model_states[0].shared_params:
|
| 470 |
+
if pair[1] in state_dict:
|
| 471 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 472 |
+
|
| 473 |
+
return state_dict
|
| 474 |
+
|
| 475 |
+
|
| 476 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
| 477 |
+
"""
|
| 478 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 479 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 480 |
+
via a model hub.
|
| 481 |
+
|
| 482 |
+
Args:
|
| 483 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 484 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 485 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 486 |
+
|
| 487 |
+
Returns:
|
| 488 |
+
- pytorch ``state_dict``
|
| 489 |
+
|
| 490 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 491 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 492 |
+
the checkpoint.
|
| 493 |
+
|
| 494 |
+
A typical usage might be ::
|
| 495 |
+
|
| 496 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 497 |
+
# do the training and checkpoint saving
|
| 498 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 499 |
+
model = model.cpu() # move to cpu
|
| 500 |
+
model.load_state_dict(state_dict)
|
| 501 |
+
# submit to model hub or save the model to share with others
|
| 502 |
+
|
| 503 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 504 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 505 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 506 |
+
|
| 507 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 508 |
+
|
| 509 |
+
"""
|
| 510 |
+
if tag is None:
|
| 511 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 512 |
+
if os.path.isfile(latest_path):
|
| 513 |
+
with open(latest_path, 'r') as fd:
|
| 514 |
+
tag = fd.read().strip()
|
| 515 |
+
else:
|
| 516 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 517 |
+
|
| 518 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 519 |
+
|
| 520 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 521 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 522 |
+
|
| 523 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 524 |
+
|
| 525 |
+
|
| 526 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 527 |
+
output_dir,
|
| 528 |
+
max_shard_size="5GB",
|
| 529 |
+
safe_serialization=False,
|
| 530 |
+
tag=None,
|
| 531 |
+
exclude_frozen_parameters=False):
|
| 532 |
+
"""
|
| 533 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 534 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 535 |
+
|
| 536 |
+
Args:
|
| 537 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 538 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 539 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 540 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 541 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 542 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 543 |
+
"""
|
| 544 |
+
# Dependency pre-check
|
| 545 |
+
if safe_serialization:
|
| 546 |
+
try:
|
| 547 |
+
from safetensors.torch import save_file
|
| 548 |
+
except ImportError:
|
| 549 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 550 |
+
raise
|
| 551 |
+
if max_shard_size is not None:
|
| 552 |
+
try:
|
| 553 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 554 |
+
except ImportError:
|
| 555 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 556 |
+
raise
|
| 557 |
+
|
| 558 |
+
# Convert zero checkpoint to state_dict
|
| 559 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
| 560 |
+
|
| 561 |
+
# Shard the model if it is too big.
|
| 562 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 563 |
+
if max_shard_size is not None:
|
| 564 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 565 |
+
state_dict_split = split_torch_state_dict_into_shards(state_dict,
|
| 566 |
+
filename_pattern=filename_pattern,
|
| 567 |
+
max_shard_size=max_shard_size)
|
| 568 |
+
else:
|
| 569 |
+
from collections import namedtuple
|
| 570 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 571 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 572 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 573 |
+
|
| 574 |
+
# Save the model
|
| 575 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 576 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 577 |
+
shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
|
| 578 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 579 |
+
if safe_serialization:
|
| 580 |
+
save_file(shard, output_path, metadata={"format": "pt"})
|
| 581 |
+
else:
|
| 582 |
+
torch.save(shard, output_path)
|
| 583 |
+
|
| 584 |
+
# Save index if sharded
|
| 585 |
+
if state_dict_split.is_sharded:
|
| 586 |
+
index = {
|
| 587 |
+
"metadata": state_dict_split.metadata,
|
| 588 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 589 |
+
}
|
| 590 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 591 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 592 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 593 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 594 |
+
f.write(content)
|
| 595 |
+
|
| 596 |
+
|
| 597 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 598 |
+
"""
|
| 599 |
+
1. Put the provided model to cpu
|
| 600 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 601 |
+
3. Load it into the provided model
|
| 602 |
+
|
| 603 |
+
Args:
|
| 604 |
+
- ``model``: the model object to update
|
| 605 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 606 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 607 |
+
|
| 608 |
+
Returns:
|
| 609 |
+
- ``model`: modified model
|
| 610 |
+
|
| 611 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 612 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 613 |
+
conveniently placed for you in the checkpoint folder.
|
| 614 |
+
|
| 615 |
+
A typical usage might be ::
|
| 616 |
+
|
| 617 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 618 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 619 |
+
# submit to model hub or save the model to share with others
|
| 620 |
+
|
| 621 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 622 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 623 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 624 |
+
|
| 625 |
+
"""
|
| 626 |
+
logger.info(f"Extracting fp32 weights")
|
| 627 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 628 |
+
|
| 629 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 630 |
+
model = model.cpu()
|
| 631 |
+
model.load_state_dict(state_dict, strict=False)
|
| 632 |
+
|
| 633 |
+
return model
|
| 634 |
+
|
| 635 |
+
|
| 636 |
+
if __name__ == "__main__":
|
| 637 |
+
parser = argparse.ArgumentParser()
|
| 638 |
+
parser.add_argument("checkpoint_dir",
|
| 639 |
+
type=str,
|
| 640 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 641 |
+
parser.add_argument("output_dir",
|
| 642 |
+
type=str,
|
| 643 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 644 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 645 |
+
parser.add_argument(
|
| 646 |
+
"--max_shard_size",
|
| 647 |
+
type=str,
|
| 648 |
+
default="5GB",
|
| 649 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 650 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 651 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 652 |
+
"without CPU OOM issues.")
|
| 653 |
+
parser.add_argument(
|
| 654 |
+
"--safe_serialization",
|
| 655 |
+
default=False,
|
| 656 |
+
action='store_true',
|
| 657 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 658 |
+
parser.add_argument("-t",
|
| 659 |
+
"--tag",
|
| 660 |
+
type=str,
|
| 661 |
+
default=None,
|
| 662 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 663 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 664 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 665 |
+
args = parser.parse_args()
|
| 666 |
+
|
| 667 |
+
debug = args.debug
|
| 668 |
+
|
| 669 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 670 |
+
args.output_dir,
|
| 671 |
+
max_shard_size=args.max_shard_size,
|
| 672 |
+
safe_serialization=args.safe_serialization,
|
| 673 |
+
tag=args.tag,
|
| 674 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000000_call_0000000_sample_00_20260304_065934_031603.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000001_call_0000001_sample_00_20260304_070203_270330.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000002_call_0000002_sample_00_20260304_070441_629095.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000003_call_0000003_sample_00_20260304_070732_079519.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000004_call_0000004_sample_00_20260304_071006_508777.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000005_call_0000005_sample_00_20260304_071219_813475.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000006_call_0000006_sample_00_20260304_071451_706380.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000007_call_0000007_sample_00_20260304_071723_356255.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000008_call_0000008_sample_00_20260304_071955_246959.png
ADDED
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000009_call_0000009_sample_00_20260304_072248_820807.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000010_call_0000010_sample_00_20260304_072522_834795.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000011_call_0000011_sample_00_20260304_072755_705550.png
ADDED
|
Git LFS Details
|
grpo-pure-multistep-7b-0302-005-cam-extrinsic/rollout_visualizations/rollout_step_0000012_call_0000012_sample_00_20260304_073037_950716.png
ADDED
|
Git LFS Details
|