Hugging Face's logo

TheBlackCat22
/
cache_models

Model card Files
xet
 Community
TheBlackCat22 commited on
Commit
0a8df6e
·
verified ·
1 Parent(s): eaecbed

Delete cache_hotpotqa_qwen4b_ablation_noadvantage

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/added_tokens.json +0 -28
  2. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/config.json +0 -31
  3. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_0.pt +0 -3
  4. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_1.pt +0 -3
  5. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_2.pt +0 -3
  6. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_3.pt +0 -3
  7. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_4.pt +0 -3
  8. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_5.pt +0 -3
  9. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_6.pt +0 -3
  10. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_7.pt +0 -3
  11. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/generation_config.json +0 -13
  12. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/merges.txt +0 -0
  13. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_0.pt +0 -3
  14. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_1.pt +0 -3
  15. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_2.pt +0 -3
  16. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_3.pt +0 -3
  17. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_4.pt +0 -3
  18. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_5.pt +0 -3
  19. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_6.pt +0 -3
  20. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_7.pt +0 -3
  21. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_0.pt +0 -3
  22. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_1.pt +0 -3
  23. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_2.pt +0 -3
  24. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_3.pt +0 -3
  25. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_4.pt +0 -3
  26. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_5.pt +0 -3
  27. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_6.pt +0 -3
  28. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_7.pt +0 -3
  29. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/special_tokens_map.json +0 -31
  30. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/tokenizer.json +0 -3
  31. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/tokenizer_config.json +0 -240
  32. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/vocab.json +0 -0
  33. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/data.pt +0 -3
  34. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/added_tokens.json +0 -28
  35. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/config.json +0 -31
  36. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_0.pt +0 -3
  37. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_1.pt +0 -3
  38. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_2.pt +0 -3
  39. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_3.pt +0 -3
  40. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_4.pt +0 -3
  41. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_5.pt +0 -3
  42. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_6.pt +0 -3
  43. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_7.pt +0 -3
  44. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/generation_config.json +0 -13
  45. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/merges.txt +0 -0
  46. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_0.pt +0 -3
  47. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_1.pt +0 -3
  48. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_2.pt +0 -3
  49. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_3.pt +0 -3
  50. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_4.pt +0 -3
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_attn_implementation_autoset": true,
3
- "architectures": [
4
- "Qwen3ForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "eos_token_id": 151645,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 2560,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 9728,
14
- "max_position_embeddings": 40960,
15
- "max_window_layers": 36,
16
- "model_type": "qwen3",
17
- "num_attention_heads": 32,
18
- "num_hidden_layers": 36,
19
- "num_key_value_heads": 8,
20
- "pad_token_id": 151643,
21
- "rms_norm_eps": 1e-06,
22
- "rope_scaling": null,
23
- "rope_theta": 1000000,
24
- "sliding_window": null,
25
- "tie_word_embeddings": true,
26
- "torch_dtype": "float32",
27
- "transformers_version": "4.51.3",
28
- "use_cache": true,
29
- "use_sliding_window": false,
30
- "vocab_size": 151936
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc14f7204d6fc130f80c7bb6c4fd804b5e96a573a6224859212e7c211ea6f90b
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c27f2106ba6c26ef193b5d0577e329d7632aa829078556aed896a29ddf6d92ad
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_2.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6638977110689fa355fde4b7aa94e0caa05f8ff69807ca9ddbe603a9c00ab6e2
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_3.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:54627ca22a11e38f4ab7e818861d9ddbfafb41a4a4354764040f25e37962ed87
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_4.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad26d3d8a77527068885415f0fe20377f2d4e201d2db2dab981bba744b38b64d
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_5.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:084648afa1455fb04eff004a007db3e696475202a53e64a5bcc906d756537812
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_6.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbffdf595550026d97c55e05f352e09fd9c35344fc2587fb372a32923fca2ad2
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/extra_state_world_size_8_rank_7.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:13f55abcbb8552bb0a36fed723a5187a61123d2865f8392a01215418a759a665
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/generation_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "4.51.3"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d6cbe95ae3ef4782ba6e5200d488ac79e973a03fa5ac78154433ff13522640e
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e61f45ed30a61d79b4c7f91aa37c7ae4fbd091044636ddede72232ebf50c5134
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_2.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce1c0aa51f97fa75d2dd8647b6300ac96f05581851a55a26ee19db9474d3269d
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_3.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:88b0f8def96ffe3627aa3d2765f00843a7184c716606f5fa747470f3b98a81de
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_4.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f5603c31cdffa40985e74f407164c92310fba45aea37242b168bedfa0ad95a1
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_5.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa561614a0af41494e7726668cce8f9cc41585b2eb9fe307dd0189336e08ff61
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_6.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16bfdbfad0fc2675f18aac0f80f0d5cfd9450f9063cc82dd85e259c5e06c6f12
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/model_world_size_8_rank_7.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fd0d3a6acf68135546800203d4403abd9c0c9a78f8caa26fbf8f5187f8cbb1d
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb6286d2907499a80a0404d5698f67fb8a4fb613d0ff86c132a06dff877dc818
3
- size 4022501290
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b2df2616171a914a1d8558ce5741caf28c62e5df996731ca995f610d61f4231
3
- size 4022501290
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_2.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:935c6cad63293f4c9099f4c88cba138e7d95884dc1f254bb8b9feeacf7be2058
3
- size 4022501290
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_3.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ab91a4fdc1ec8d77abf2dd9de38cadb01b396b0e0ac40f6f93f15a9f75a0684
3
- size 4022501290
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_4.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe80643a68fe42277880ac0dcd508f85927ca570560719683e977c0ab72afced
3
- size 4022501290
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_5.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0594277c7adfaee529a4bc5386e1fa33661c7d3a9d4952ae0bf1c1764ea5435c
3
- size 4022501290
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_6.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d86b227734b6fecb5ec8ae6e6272774c64e549d2dc5fc5fa2f2020a48ad5653c
3
- size 4022501290
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/optim_world_size_8_rank_7.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9703c41c936dc3bd1065f046d3cf40b24b6287324aec38ce7db634bf55b28728
3
- size 4022501290
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/special_tokens_map.json DELETED
@@ -1,31 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/tokenizer_config.json DELETED
@@ -1,240 +0,0 @@
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
- "151665": {
182
- "content": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|im_start|>",
216
- "<|im_end|>",
217
- "<|object_ref_start|>",
218
- "<|object_ref_end|>",
219
- "<|box_start|>",
220
- "<|box_end|>",
221
- "<|quad_start|>",
222
- "<|quad_end|>",
223
- "<|vision_start|>",
224
- "<|vision_end|>",
225
- "<|vision_pad|>",
226
- "<|image_pad|>",
227
- "<|video_pad|>"
228
- ],
229
- "bos_token": null,
230
- "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
- "clean_up_tokenization_spaces": false,
232
- "eos_token": "<|im_end|>",
233
- "errors": "replace",
234
- "extra_special_tokens": {},
235
- "model_max_length": 131072,
236
- "pad_token": "<|endoftext|>",
237
- "split_special_tokens": false,
238
- "tokenizer_class": "Qwen2Tokenizer",
239
- "unk_token": null
240
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/actor/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_100/data.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e6f3a66997f282def8eded3e45f1d132042a6e4a92cf04685e35585ee2c0ccd
3
- size 1492
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_attn_implementation_autoset": true,
3
- "architectures": [
4
- "Qwen3ForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "eos_token_id": 151645,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 2560,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 9728,
14
- "max_position_embeddings": 40960,
15
- "max_window_layers": 36,
16
- "model_type": "qwen3",
17
- "num_attention_heads": 32,
18
- "num_hidden_layers": 36,
19
- "num_key_value_heads": 8,
20
- "pad_token_id": 151643,
21
- "rms_norm_eps": 1e-06,
22
- "rope_scaling": null,
23
- "rope_theta": 1000000,
24
- "sliding_window": null,
25
- "tie_word_embeddings": true,
26
- "torch_dtype": "float32",
27
- "transformers_version": "4.51.3",
28
- "use_cache": true,
29
- "use_sliding_window": false,
30
- "vocab_size": 151936
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:de888a6dd198649d87e9d2b45c0b280b152bfe79090491107335d26d5c4e0d2c
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e86411ccf7f9d32801356316e23ff5edd03987164780bdc7d2382092f65e100
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_2.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6c0f7b2350f84bfa03db29b0138366c2a03c57030c8d67bb171c45a47d66f9d
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_3.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8824b12f54e637f3841f9a8b41c20eddc9d1c1cb38c1679563c985985ddda30
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_4.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:278d57a72eda73e557e96f5a4a9869494a1751bf3596fc160808cb8e84aa26df
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_5.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:15e6d1a7103e85bda2b0628c64b2235c3d54fabd4ec9e460e9c0196884e0db65
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_6.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b72d83002f7dd3c9c50e4d65324e927d3222f4a739dd77a11aba6b75ac60865
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/extra_state_world_size_8_rank_7.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:af6bf5af07d0c1af97c786c89447268d945b739e0f2ab1bcd3e3e3f09ce9f95d
3
- size 14632
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/generation_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "4.51.3"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b566820460dcb51e6e5771a73512f60d7c1a503fd0890ad3753e36931a3c4cfd
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:288e6abd47891358f9b8b7359aec88fb53889459c092fe9bcc2a0c80d75ad05d
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_2.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d0bd135b3e628036829fd7e3d5aca22cf1522dc75d798da44a8871a5ca1bd70
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_3.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e86ef09101a1cbf93dd81b0cacb4c6b063423dfcbedfe735208cfb00e7eff4bd
3
- size 2205945402
 
 
 
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_50/actor/model_world_size_8_rank_4.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:06ce58190bb047a45e9968bb3d0969bb8c0820821934e54b10b8afe8d15b2249
3
- size 2205945402