Hugging Face's logo

yinyil
/
ckpt

Safetensors
Model card Files
xet
 Community
yinyil commited on
Commit
c315de0
·
verified ·
1 Parent(s): 3d5768e

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -0
  2. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/README.md +201 -0
  3. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/adapter_config.json +34 -0
  4. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/adapter_model.safetensors +3 -0
  5. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/added_tokens.json +28 -0
  6. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/added_tokens.json +28 -0
  7. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/config.json +30 -0
  8. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/generation_config.json +13 -0
  9. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/merges.txt +0 -0
  10. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00001-of-00027.safetensors +3 -0
  11. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00002-of-00027.safetensors +3 -0
  12. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00003-of-00027.safetensors +3 -0
  13. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00004-of-00027.safetensors +3 -0
  14. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00005-of-00027.safetensors +3 -0
  15. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00006-of-00027.safetensors +3 -0
  16. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00007-of-00027.safetensors +3 -0
  17. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00008-of-00027.safetensors +3 -0
  18. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00009-of-00027.safetensors +3 -0
  19. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00010-of-00027.safetensors +3 -0
  20. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00011-of-00027.safetensors +3 -0
  21. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00012-of-00027.safetensors +3 -0
  22. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00013-of-00027.safetensors +3 -0
  23. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00014-of-00027.safetensors +3 -0
  24. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00015-of-00027.safetensors +3 -0
  25. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00016-of-00027.safetensors +3 -0
  26. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00017-of-00027.safetensors +3 -0
  27. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00018-of-00027.safetensors +3 -0
  28. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00019-of-00027.safetensors +3 -0
  29. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00020-of-00027.safetensors +3 -0
  30. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00021-of-00027.safetensors +3 -0
  31. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00022-of-00027.safetensors +3 -0
  32. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00023-of-00027.safetensors +3 -0
  33. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00024-of-00027.safetensors +3 -0
  34. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00025-of-00027.safetensors +3 -0
  35. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00026-of-00027.safetensors +3 -0
  36. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00027-of-00027.safetensors +3 -0
  37. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model.safetensors.index.json +714 -0
  38. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/special_tokens_map.json +31 -0
  39. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/tokenizer.json +3 -0
  40. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/tokenizer_config.json +240 -0
  41. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/vocab.json +0 -0
  42. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/README.md +202 -0
  43. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/adapter_config.json +34 -0
  44. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/adapter_model.safetensors +3 -0
  45. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/added_tokens.json +28 -0
  46. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/merges.txt +0 -0
  47. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/special_tokens_map.json +25 -0
  48. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/tokenizer.json +3 -0
  49. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/tokenizer_config.json +240 -0
  50. kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/trainer_state.json +118 -0
.gitattributes CHANGED
@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  kud-qwen3-32b_history_root_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  kud-qwen3-32b_history_root_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  kud-qwen3-32b_history_root_relearn_klr_gdr_history_100_512_2e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
36
  kud-qwen3-32b_history_root_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  kud-qwen3-32b_history_root_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  kud-qwen3-32b_history_root_relearn_klr_gdr_history_100_512_2e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/README.md ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+
5
+ # Model Card for Model ID
6
+
7
+ <!-- Provide a quick summary of what the model is/does. -->
8
+
9
+
10
+
11
+ ## Model Details
12
+
13
+ ### Model Description
14
+
15
+ <!-- Provide a longer summary of what this model is. -->
16
+
17
+
18
+
19
+ - **Developed by:** [More Information Needed]
20
+ - **Funded by [optional]:** [More Information Needed]
21
+ - **Shared by [optional]:** [More Information Needed]
22
+ - **Model type:** [More Information Needed]
23
+ - **Language(s) (NLP):** [More Information Needed]
24
+ - **License:** [More Information Needed]
25
+ - **Finetuned from model [optional]:** [More Information Needed]
26
+
27
+ ### Model Sources [optional]
28
+
29
+ <!-- Provide the basic links for the model. -->
30
+
31
+ - **Repository:** [More Information Needed]
32
+ - **Paper [optional]:** [More Information Needed]
33
+ - **Demo [optional]:** [More Information Needed]
34
+
35
+ ## Uses
36
+
37
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
+
39
+ ### Direct Use
40
+
41
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
+
43
+ [More Information Needed]
44
+
45
+ ### Downstream Use [optional]
46
+
47
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Out-of-Scope Use
52
+
53
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
+
55
+ [More Information Needed]
56
+
57
+ ## Bias, Risks, and Limitations
58
+
59
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ### Recommendations
64
+
65
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
+
67
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
+
69
+ ## How to Get Started with the Model
70
+
71
+ Use the code below to get started with the model.
72
+
73
+ [More Information Needed]
74
+
75
+ ## Training Details
76
+
77
+ ### Training Data
78
+
79
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
80
+
81
+ [More Information Needed]
82
+
83
+ ### Training Procedure
84
+
85
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
+
87
+ #### Preprocessing [optional]
88
+
89
+ [More Information Needed]
90
+
91
+
92
+ #### Training Hyperparameters
93
+
94
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
+
96
+ #### Speeds, Sizes, Times [optional]
97
+
98
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
+
100
+ [More Information Needed]
101
+
102
+ ## Evaluation
103
+
104
+ <!-- This section describes the evaluation protocols and provides the results. -->
105
+
106
+ ### Testing Data, Factors & Metrics
107
+
108
+ #### Testing Data
109
+
110
+ <!-- This should link to a Dataset Card if possible. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Factors
115
+
116
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Metrics
121
+
122
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
+
124
+ [More Information Needed]
125
+
126
+ ### Results
127
+
128
+ [More Information Needed]
129
+
130
+ #### Summary
131
+
132
+
133
+
134
+ ## Model Examination [optional]
135
+
136
+ <!-- Relevant interpretability work for the model goes here -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Environmental Impact
141
+
142
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
+
144
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
145
+
146
+ - **Hardware Type:** [More Information Needed]
147
+ - **Hours used:** [More Information Needed]
148
+ - **Cloud Provider:** [More Information Needed]
149
+ - **Compute Region:** [More Information Needed]
150
+ - **Carbon Emitted:** [More Information Needed]
151
+
152
+ ## Technical Specifications [optional]
153
+
154
+ ### Model Architecture and Objective
155
+
156
+ [More Information Needed]
157
+
158
+ ### Compute Infrastructure
159
+
160
+ [More Information Needed]
161
+
162
+ #### Hardware
163
+
164
+ [More Information Needed]
165
+
166
+ #### Software
167
+
168
+ [More Information Needed]
169
+
170
+ ## Citation [optional]
171
+
172
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
+
174
+ **BibTeX:**
175
+
176
+ [More Information Needed]
177
+
178
+ **APA:**
179
+
180
+ [More Information Needed]
181
+
182
+ ## Glossary [optional]
183
+
184
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
+
186
+ [More Information Needed]
187
+
188
+ ## More Information [optional]
189
+
190
+ [More Information Needed]
191
+
192
+ ## Model Card Authors [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Contact
197
+
198
+ [More Information Needed]
199
+ ### Framework versions
200
+
201
+ - PEFT 0.13.2
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/project/flame/haoc3/unlearning/EasyEdit/hugging_cache/Qwen3-32B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "o_proj",
27
+ "up_proj",
28
+ "q_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1974ca585a3e9a91fbc665c9611bad9db43e7986684347f43c9e590e370e886f
3
+ size 1073863208
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 25600,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 64,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 64,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.51.0",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.51.0"
13
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00001-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd5788f43c90238f21e1dc31a82b5bb4649ebae5f64a7bde4f9bd6e7f6da9af
3
+ size 4537714712
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00002-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf3676477a8467fabc901f170d5f8eea72853c1110de8486db282b129e1ed0e
3
+ size 4802607584
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00003-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deda406b3e5594b459da896759e9f2002c112bf690938e636589ed6665d07734
3
+ size 4949365440
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00004-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f63a65248c6f6391637ea4db0c0032bc7adee3edbe7239481ab5ad3091ecf24
3
+ size 4802607584
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00005-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359a684119a34ea4458ee168de318c7046d3669c9343f0fafee3ae5e4410f09a
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00006-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241b033981c9e9fcdaa7899d237a1a68fa6bca1a5965d651d0dfedb1511434c9
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00007-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:943ef5b576c347118ecbff2c3d5ebc5962e69961b9d5966efa0c39f75db50299
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00008-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b34d4dcd7efe0dde42aaee97b9af7914318815375db3ff5be94cdabd3293c8c9
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00009-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:497c24f9b6b7f642e2472c3ae98a9c29e51a56d6c9ad90436947c67389b51b01
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00010-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca9cc4f21a197aaebc4f964763aa196b7cf0903486169b62cd068361f50606c
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00011-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b99936b90176480955f6cf92964fec9127426bf667019aaf291c8aa92b90f5a
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00012-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b5817df9ff6da272df2c1cbbcb2480fc04230352fa35cebd23ae3d1e7b8c72
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00013-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4913f15a797ee16ad7e6a1d09bcee83dbe3f83dbe2e1d0d2647fc27b2ea3a7
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00014-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9c1927dbd721fe34972101949eeb4af0f2c095d895eb9312ece3f89610f687
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00015-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25301fc7a7e16460fade8dcc20c4866301666ff21f459c077a322fb7459c79ce
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00016-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a9e3f3de720a8061be8a6f9f49a5753a1f10e1d4a25d8dc9f1d5c32a68a43ca
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00017-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26f79ced005ad91a88a85ebb9fe3e9e6630a480bda764edece74fd70905323f
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00018-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd6baa0f04d79db325c60196eb065059979a20a41ad79f173572cfb63e98d34
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00019-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f8e1cc389c2e88df75065f4027b6dc4fbf655e6fdac4219ac1d28fb3584f0a
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00020-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21023a4e0e81db0ff679f634a925939e7235f0a5486a71457dc39a6e18bcacbd
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00021-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e687e0c9074fcba8e4b9de028f0dcb7319ac0fd9c6d911aebe4092105185a2
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00022-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11506925bb632586e26ce5e54b499ac2f866dd86c68b40d21e39aae50da30842
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00023-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16bbb620f79d306b62849f06bb1746cf0a4ecdc1b09ba65b5bf4833ea08bcf93
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00024-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4712042d3fb752cda0b8699b534638cd1aa5fa052133fc5cfc2d300ab1fda8e3
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00025-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7541537b1d21b7888afddcf99c8eb6c1d229204c2ebd0f93346f48f6199679fa
3
+ size 4949365464
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00026-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60fa83b02a05f7fe5be6da1701c4a8c5efd71c83d5a061b903d20727adc137b0
3
+ size 4802607616
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model-00027-of-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77452b31b85750fed096066022893ba4163eae9d7bcca1af5fa8cfed1913aa5a
3
+ size 4684575512
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/model.safetensors.index.json ADDED
@@ -0,0 +1,714 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 131048493056
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00027-of-00027.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00027.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00027.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00027.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00027.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00027.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00027.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00006-of-00027.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00005-of-00027.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00005-of-00027.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00006-of-00027.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00027.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00007-of-00027.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00007-of-00027.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00007-of-00027.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00007-of-00027.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00008-of-00027.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00007-of-00027.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00007-of-00027.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00008-of-00027.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00008-of-00027.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00009-of-00027.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00009-of-00027.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00009-of-00027.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00009-of-00027.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00027.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00010-of-00027.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00009-of-00027.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00009-of-00027.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00010-of-00027.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00010-of-00027.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00011-of-00027.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00011-of-00027.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00011-of-00027.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00011-of-00027.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00012-of-00027.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00011-of-00027.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00011-of-00027.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00012-of-00027.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00012-of-00027.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00013-of-00027.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00013-of-00027.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00013-of-00027.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00013-of-00027.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00003-of-00027.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00014-of-00027.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00013-of-00027.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00013-of-00027.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00014-of-00027.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00014-of-00027.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00015-of-00027.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00015-of-00027.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00015-of-00027.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00015-of-00027.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00016-of-00027.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00015-of-00027.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00015-of-00027.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
338
+ "model.layers.36.input_layernorm.weight": "model-00016-of-00027.safetensors",
339
+ "model.layers.36.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
340
+ "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
341
+ "model.layers.36.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
342
+ "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
343
+ "model.layers.36.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
344
+ "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
345
+ "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
346
+ "model.layers.36.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
347
+ "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
348
+ "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
349
+ "model.layers.37.input_layernorm.weight": "model-00016-of-00027.safetensors",
350
+ "model.layers.37.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
351
+ "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
352
+ "model.layers.37.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
353
+ "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
354
+ "model.layers.37.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
355
+ "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
356
+ "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
357
+ "model.layers.37.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
358
+ "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
359
+ "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
360
+ "model.layers.38.input_layernorm.weight": "model-00017-of-00027.safetensors",
361
+ "model.layers.38.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
362
+ "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
363
+ "model.layers.38.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
364
+ "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
365
+ "model.layers.38.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
366
+ "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
367
+ "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
368
+ "model.layers.38.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
369
+ "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
370
+ "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
371
+ "model.layers.39.input_layernorm.weight": "model-00017-of-00027.safetensors",
372
+ "model.layers.39.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
373
+ "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
374
+ "model.layers.39.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
375
+ "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
376
+ "model.layers.39.self_attn.k_norm.weight": "model-00017-of-00027.safetensors",
377
+ "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
378
+ "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
379
+ "model.layers.39.self_attn.q_norm.weight": "model-00017-of-00027.safetensors",
380
+ "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
381
+ "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
382
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00027.safetensors",
383
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
384
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
385
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
386
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
387
+ "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00027.safetensors",
388
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
389
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
390
+ "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00027.safetensors",
391
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
392
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
393
+ "model.layers.40.input_layernorm.weight": "model-00018-of-00027.safetensors",
394
+ "model.layers.40.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
395
+ "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
396
+ "model.layers.40.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
397
+ "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
398
+ "model.layers.40.self_attn.k_norm.weight": "model-00017-of-00027.safetensors",
399
+ "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
400
+ "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
401
+ "model.layers.40.self_attn.q_norm.weight": "model-00017-of-00027.safetensors",
402
+ "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
403
+ "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
404
+ "model.layers.41.input_layernorm.weight": "model-00018-of-00027.safetensors",
405
+ "model.layers.41.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
406
+ "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
407
+ "model.layers.41.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
408
+ "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
409
+ "model.layers.41.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
410
+ "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
411
+ "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
412
+ "model.layers.41.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
413
+ "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
414
+ "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
415
+ "model.layers.42.input_layernorm.weight": "model-00018-of-00027.safetensors",
416
+ "model.layers.42.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
417
+ "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
418
+ "model.layers.42.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
419
+ "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
420
+ "model.layers.42.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
421
+ "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
422
+ "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
423
+ "model.layers.42.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
424
+ "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
425
+ "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
426
+ "model.layers.43.input_layernorm.weight": "model-00019-of-00027.safetensors",
427
+ "model.layers.43.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
428
+ "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
429
+ "model.layers.43.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
430
+ "model.layers.43.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
431
+ "model.layers.43.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
432
+ "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
433
+ "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
434
+ "model.layers.43.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
435
+ "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
436
+ "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
437
+ "model.layers.44.input_layernorm.weight": "model-00019-of-00027.safetensors",
438
+ "model.layers.44.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
439
+ "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
440
+ "model.layers.44.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
441
+ "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
442
+ "model.layers.44.self_attn.k_norm.weight": "model-00019-of-00027.safetensors",
443
+ "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
444
+ "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
445
+ "model.layers.44.self_attn.q_norm.weight": "model-00019-of-00027.safetensors",
446
+ "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
447
+ "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
448
+ "model.layers.45.input_layernorm.weight": "model-00020-of-00027.safetensors",
449
+ "model.layers.45.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
450
+ "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
451
+ "model.layers.45.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
452
+ "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
453
+ "model.layers.45.self_attn.k_norm.weight": "model-00019-of-00027.safetensors",
454
+ "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
455
+ "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
456
+ "model.layers.45.self_attn.q_norm.weight": "model-00019-of-00027.safetensors",
457
+ "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
458
+ "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
459
+ "model.layers.46.input_layernorm.weight": "model-00020-of-00027.safetensors",
460
+ "model.layers.46.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
461
+ "model.layers.46.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
462
+ "model.layers.46.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
463
+ "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
464
+ "model.layers.46.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
465
+ "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
466
+ "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
467
+ "model.layers.46.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
468
+ "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
469
+ "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
470
+ "model.layers.47.input_layernorm.weight": "model-00020-of-00027.safetensors",
471
+ "model.layers.47.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
472
+ "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
473
+ "model.layers.47.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
474
+ "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
475
+ "model.layers.47.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
476
+ "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
477
+ "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
478
+ "model.layers.47.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
479
+ "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
480
+ "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
481
+ "model.layers.48.input_layernorm.weight": "model-00021-of-00027.safetensors",
482
+ "model.layers.48.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
483
+ "model.layers.48.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
484
+ "model.layers.48.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
485
+ "model.layers.48.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
486
+ "model.layers.48.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
487
+ "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
488
+ "model.layers.48.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
489
+ "model.layers.48.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
490
+ "model.layers.48.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
491
+ "model.layers.48.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
492
+ "model.layers.49.input_layernorm.weight": "model-00021-of-00027.safetensors",
493
+ "model.layers.49.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
494
+ "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
495
+ "model.layers.49.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
496
+ "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
497
+ "model.layers.49.self_attn.k_norm.weight": "model-00021-of-00027.safetensors",
498
+ "model.layers.49.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
499
+ "model.layers.49.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
500
+ "model.layers.49.self_attn.q_norm.weight": "model-00021-of-00027.safetensors",
501
+ "model.layers.49.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
502
+ "model.layers.49.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
503
+ "model.layers.5.input_layernorm.weight": "model-00004-of-00027.safetensors",
504
+ "model.layers.5.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
505
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
506
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
507
+ "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
508
+ "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00027.safetensors",
509
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
510
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
511
+ "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00027.safetensors",
512
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
513
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
514
+ "model.layers.50.input_layernorm.weight": "model-00022-of-00027.safetensors",
515
+ "model.layers.50.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
516
+ "model.layers.50.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
517
+ "model.layers.50.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
518
+ "model.layers.50.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
519
+ "model.layers.50.self_attn.k_norm.weight": "model-00021-of-00027.safetensors",
520
+ "model.layers.50.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
521
+ "model.layers.50.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
522
+ "model.layers.50.self_attn.q_norm.weight": "model-00021-of-00027.safetensors",
523
+ "model.layers.50.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
524
+ "model.layers.50.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
525
+ "model.layers.51.input_layernorm.weight": "model-00022-of-00027.safetensors",
526
+ "model.layers.51.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
527
+ "model.layers.51.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
528
+ "model.layers.51.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
529
+ "model.layers.51.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
530
+ "model.layers.51.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
531
+ "model.layers.51.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
532
+ "model.layers.51.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
533
+ "model.layers.51.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
534
+ "model.layers.51.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
535
+ "model.layers.51.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
536
+ "model.layers.52.input_layernorm.weight": "model-00022-of-00027.safetensors",
537
+ "model.layers.52.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
538
+ "model.layers.52.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
539
+ "model.layers.52.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
540
+ "model.layers.52.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
541
+ "model.layers.52.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
542
+ "model.layers.52.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
543
+ "model.layers.52.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
544
+ "model.layers.52.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
545
+ "model.layers.52.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
546
+ "model.layers.52.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
547
+ "model.layers.53.input_layernorm.weight": "model-00023-of-00027.safetensors",
548
+ "model.layers.53.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
549
+ "model.layers.53.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
550
+ "model.layers.53.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
551
+ "model.layers.53.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
552
+ "model.layers.53.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
553
+ "model.layers.53.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
554
+ "model.layers.53.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
555
+ "model.layers.53.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
556
+ "model.layers.53.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
557
+ "model.layers.53.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
558
+ "model.layers.54.input_layernorm.weight": "model-00023-of-00027.safetensors",
559
+ "model.layers.54.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
560
+ "model.layers.54.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
561
+ "model.layers.54.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
562
+ "model.layers.54.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
563
+ "model.layers.54.self_attn.k_norm.weight": "model-00023-of-00027.safetensors",
564
+ "model.layers.54.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
565
+ "model.layers.54.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
566
+ "model.layers.54.self_attn.q_norm.weight": "model-00023-of-00027.safetensors",
567
+ "model.layers.54.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
568
+ "model.layers.54.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
569
+ "model.layers.55.input_layernorm.weight": "model-00024-of-00027.safetensors",
570
+ "model.layers.55.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
571
+ "model.layers.55.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
572
+ "model.layers.55.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
573
+ "model.layers.55.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
574
+ "model.layers.55.self_attn.k_norm.weight": "model-00023-of-00027.safetensors",
575
+ "model.layers.55.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
576
+ "model.layers.55.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
577
+ "model.layers.55.self_attn.q_norm.weight": "model-00023-of-00027.safetensors",
578
+ "model.layers.55.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
579
+ "model.layers.55.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
580
+ "model.layers.56.input_layernorm.weight": "model-00024-of-00027.safetensors",
581
+ "model.layers.56.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
582
+ "model.layers.56.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
583
+ "model.layers.56.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
584
+ "model.layers.56.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
585
+ "model.layers.56.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
586
+ "model.layers.56.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
587
+ "model.layers.56.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
588
+ "model.layers.56.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
589
+ "model.layers.56.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
590
+ "model.layers.56.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
591
+ "model.layers.57.input_layernorm.weight": "model-00024-of-00027.safetensors",
592
+ "model.layers.57.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
593
+ "model.layers.57.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
594
+ "model.layers.57.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
595
+ "model.layers.57.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
596
+ "model.layers.57.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
597
+ "model.layers.57.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
598
+ "model.layers.57.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
599
+ "model.layers.57.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
600
+ "model.layers.57.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
601
+ "model.layers.57.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
602
+ "model.layers.58.input_layernorm.weight": "model-00025-of-00027.safetensors",
603
+ "model.layers.58.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
604
+ "model.layers.58.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
605
+ "model.layers.58.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
606
+ "model.layers.58.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
607
+ "model.layers.58.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
608
+ "model.layers.58.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
609
+ "model.layers.58.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
610
+ "model.layers.58.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
611
+ "model.layers.58.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
612
+ "model.layers.58.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
613
+ "model.layers.59.input_layernorm.weight": "model-00025-of-00027.safetensors",
614
+ "model.layers.59.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
615
+ "model.layers.59.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
616
+ "model.layers.59.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
617
+ "model.layers.59.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
618
+ "model.layers.59.self_attn.k_norm.weight": "model-00025-of-00027.safetensors",
619
+ "model.layers.59.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
620
+ "model.layers.59.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
621
+ "model.layers.59.self_attn.q_norm.weight": "model-00025-of-00027.safetensors",
622
+ "model.layers.59.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
623
+ "model.layers.59.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
624
+ "model.layers.6.input_layernorm.weight": "model-00004-of-00027.safetensors",
625
+ "model.layers.6.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
626
+ "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
627
+ "model.layers.6.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
628
+ "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
629
+ "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
630
+ "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
631
+ "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
632
+ "model.layers.6.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
633
+ "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
634
+ "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
635
+ "model.layers.60.input_layernorm.weight": "model-00026-of-00027.safetensors",
636
+ "model.layers.60.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
637
+ "model.layers.60.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
638
+ "model.layers.60.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
639
+ "model.layers.60.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
640
+ "model.layers.60.self_attn.k_norm.weight": "model-00025-of-00027.safetensors",
641
+ "model.layers.60.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
642
+ "model.layers.60.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
643
+ "model.layers.60.self_attn.q_norm.weight": "model-00025-of-00027.safetensors",
644
+ "model.layers.60.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
645
+ "model.layers.60.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
646
+ "model.layers.61.input_layernorm.weight": "model-00026-of-00027.safetensors",
647
+ "model.layers.61.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
648
+ "model.layers.61.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
649
+ "model.layers.61.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
650
+ "model.layers.61.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
651
+ "model.layers.61.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
652
+ "model.layers.61.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
653
+ "model.layers.61.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
654
+ "model.layers.61.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
655
+ "model.layers.61.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
656
+ "model.layers.61.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
657
+ "model.layers.62.input_layernorm.weight": "model-00026-of-00027.safetensors",
658
+ "model.layers.62.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
659
+ "model.layers.62.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
660
+ "model.layers.62.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
661
+ "model.layers.62.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
662
+ "model.layers.62.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
663
+ "model.layers.62.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
664
+ "model.layers.62.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
665
+ "model.layers.62.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
666
+ "model.layers.62.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
667
+ "model.layers.62.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
668
+ "model.layers.63.input_layernorm.weight": "model-00027-of-00027.safetensors",
669
+ "model.layers.63.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
670
+ "model.layers.63.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
671
+ "model.layers.63.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
672
+ "model.layers.63.post_attention_layernorm.weight": "model-00027-of-00027.safetensors",
673
+ "model.layers.63.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
674
+ "model.layers.63.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
675
+ "model.layers.63.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
676
+ "model.layers.63.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
677
+ "model.layers.63.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
678
+ "model.layers.63.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
679
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00027.safetensors",
680
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
681
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
682
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
683
+ "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
684
+ "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
685
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
686
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
687
+ "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
688
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
689
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
690
+ "model.layers.8.input_layernorm.weight": "model-00005-of-00027.safetensors",
691
+ "model.layers.8.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
692
+ "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
693
+ "model.layers.8.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
694
+ "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
695
+ "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
696
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
697
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
698
+ "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
699
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
700
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
701
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00027.safetensors",
702
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
703
+ "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
704
+ "model.layers.9.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
705
+ "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
706
+ "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00027.safetensors",
707
+ "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
708
+ "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
709
+ "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00027.safetensors",
710
+ "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
711
+ "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
712
+ "model.norm.weight": "model-00027-of-00027.safetensors"
713
+ }
714
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/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
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12-full/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /project/flame/haoc3/unlearning/EasyEdit/hugging_cache/Qwen3-32B
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/project/flame/haoc3/unlearning/EasyEdit/hugging_cache/Qwen3-32B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "o_proj",
27
+ "up_proj",
28
+ "q_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1974ca585a3e9a91fbc665c9611bad9db43e7986684347f43c9e590e370e886f
3
+ size 1073863208
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>"
25
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
kud-qwen3-32b_history_leaf_relearn_klr_gdr_history_100_512_2e-5/checkpoint-12/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.48,
6
+ "eval_steps": 3,
7
+ "global_step": 12,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04,
14
+ "grad_norm": 6.13517427444458,
15
+ "learning_rate": 0.0,
16
+ "loss": 23.3585,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.08,
21
+ "grad_norm": 8.376542091369629,
22
+ "learning_rate": 6.666666666666667e-06,
23
+ "loss": 25.7538,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.12,
28
+ "grad_norm": 5.800008296966553,
29
+ "learning_rate": 1.3333333333333333e-05,
30
+ "loss": 23.9407,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.16,
35
+ "grad_norm": 5.779591083526611,
36
+ "learning_rate": 2e-05,
37
+ "loss": 26.3629,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.2,
42
+ "grad_norm": 6.114522457122803,
43
+ "learning_rate": 1.7777777777777777e-05,
44
+ "loss": 25.4492,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.24,
49
+ "grad_norm": 7.265014171600342,
50
+ "learning_rate": 1.555555555555556e-05,
51
+ "loss": 26.2863,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.28,
56
+ "grad_norm": 6.454556941986084,
57
+ "learning_rate": 1.3333333333333333e-05,
58
+ "loss": 25.4923,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.32,
63
+ "grad_norm": 12.557967185974121,
64
+ "learning_rate": 1.1111111111111113e-05,
65
+ "loss": 26.4041,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.36,
70
+ "grad_norm": 7.597005844116211,
71
+ "learning_rate": 8.888888888888888e-06,
72
+ "loss": 25.6533,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.4,
77
+ "grad_norm": 13.574301719665527,
78
+ "learning_rate": 6.666666666666667e-06,
79
+ "loss": 26.3975,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.44,
84
+ "grad_norm": 8.249970436096191,
85
+ "learning_rate": 4.444444444444444e-06,
86
+ "loss": 25.7194,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.48,
91
+ "grad_norm": 7.311003684997559,
92
+ "learning_rate": 2.222222222222222e-06,
93
+ "loss": 23.5624,
94
+ "step": 12
95
+ }
96
+ ],
97
+ "logging_steps": 1,
98
+ "max_steps": 12,
99
+ "num_input_tokens_seen": 0,
100
+ "num_train_epochs": 1,
101
+ "save_steps": 3,
102
+ "stateful_callbacks": {
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": true
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 0.0,
115
+ "train_batch_size": 1,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }