Jnx03 commited on
Commit
567bd96
·
verified ·
1 Parent(s): d2fb088

v55-deepseek-clean-seed-micro-delta-final: sft-lora

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
4
+ license: apache-2.0
5
+ tags:
6
+ - thai
7
+ - kanitakorn
8
+ - single-model
9
+ - greedy-eval
10
+ language:
11
+ - th
12
+ - en
13
+ ---
14
+
15
+ # Jnx03/kanitakorn-v55-deepseek-clean-seed-micro-delta-final
16
+
17
+ Kanitakorn 2026-06-13 campaign artifact.
18
+
19
+ - Base: `deepseek-ai/DeepSeek-R1-Distill-Qwen-14B`
20
+ - Version: `v55-deepseek-clean-seed-micro-delta-final`
21
+ - Method: `sft-lora`
22
+ - Final-claim policy: one model, no BoN, no self-consistency, no ensemble, no model routing.
23
+ - Date: 2026-06-15
24
+
25
+ ## Scores
26
+
27
+ | Benchmark | Score | Target | Status |
28
+ |---|---:|---:|---|
29
+ | aime24_th | pending | >15.0 | pending |
30
+ | aime24 | pending | >25.0 | pending |
31
+ | math500_th | pending | >56.0 | pending |
32
+ | math500 | pending | >82.0 | pending |
33
+ | livecodebench_th | pending | >35.0 | pending |
34
+ | livecodebench | pending | >60.0 | pending |
35
+ | openthaieval | pending | >80.0 | pending |
36
+ | hotpotqa_th_en | pending | >46.0 | pending |
37
+ | instruction_following_th_en | pending | >57.0 | pending |
38
+ | mt_bench_th_en | pending | >85.0 | pending |
39
+ | thaiexam | pending | >70.0 | pending |
40
+ | ifeval_th | pending | >82.0 | pending |
41
+
42
+ ## Notes
43
+
44
+ Automatic checkpoint publish from runs/20260615_deepseek_v55_clean_seed_micro_delta_from_a0p90_lr2e8_2/final. Single-model artifact; no BoN/self-consistency.
adapter_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 32,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "gate_proj",
39
+ "q_proj",
40
+ "k_proj",
41
+ "o_proj",
42
+ "up_proj",
43
+ "down_proj"
44
+ ],
45
+ "target_parameters": null,
46
+ "task_type": "CAUSAL_LM",
47
+ "trainable_token_indices": null,
48
+ "use_bdlora": null,
49
+ "use_dora": false,
50
+ "use_qalora": false,
51
+ "use_rslora": false
52
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:826bf8e7dddc2072ab16aeab79953c857971413d946f74cbc98e4d5e6bd95268
3
+ size 550593184
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\n'}}{% endif %}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72d364a37413ca00a9000b2d2cff0be9c4511c6d1565263dcca665c5911c4ca
3
+ size 11422968
tokenizer_config.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|begin▁of▁sentence|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|end▁of▁sentence|>",
7
+ "from_slow": true,
8
+ "is_local": false,
9
+ "legacy": false,
10
+ "model_max_length": 131072,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "left",
13
+ "sp_model_kwargs": {},
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": null,
16
+ "use_default_system_prompt": false,
17
+ "added_tokens_decoder": {
18
+ "151643": {
19
+ "content": "<|end▁of▁sentence|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": false,
24
+ "special": true
25
+ },
26
+ "151644": {
27
+ "content": "<|User|>",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false,
32
+ "special": false
33
+ },
34
+ "151645": {
35
+ "content": "<|Assistant|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": false
41
+ },
42
+ "151646": {
43
+ "content": "<|begin▁of▁sentence|>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "151647": {
51
+ "content": "<|EOT|>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": false
57
+ },
58
+ "151648": {
59
+ "content": "<think>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": false
65
+ },
66
+ "151649": {
67
+ "content": "</think>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": false
73
+ },
74
+ "151650": {
75
+ "content": "<|quad_start|>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "151651": {
83
+ "content": "<|quad_end|>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "151652": {
91
+ "content": "<|vision_start|>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "151653": {
99
+ "content": "<|vision_end|>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "151654": {
107
+ "content": "<|vision_pad|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "151655": {
115
+ "content": "<|image_pad|>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "151656": {
123
+ "content": "<|video_pad|>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "151657": {
131
+ "content": "<tool_call>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": false
137
+ },
138
+ "151658": {
139
+ "content": "</tool_call>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": false
145
+ },
146
+ "151659": {
147
+ "content": "<|fim_prefix|>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": false
153
+ },
154
+ "151660": {
155
+ "content": "<|fim_middle|>",
156
+ "single_word": false,
157
+ "lstrip": false,
158
+ "rstrip": false,
159
+ "normalized": false,
160
+ "special": false
161
+ },
162
+ "151661": {
163
+ "content": "<|fim_suffix|>",
164
+ "single_word": false,
165
+ "lstrip": false,
166
+ "rstrip": false,
167
+ "normalized": false,
168
+ "special": false
169
+ },
170
+ "151662": {
171
+ "content": "<|fim_pad|>",
172
+ "single_word": false,
173
+ "lstrip": false,
174
+ "rstrip": false,
175
+ "normalized": false,
176
+ "special": false
177
+ },
178
+ "151663": {
179
+ "content": "<|repo_name|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ "151664": {
187
+ "content": "<|file_sep|>",
188
+ "single_word": false,
189
+ "lstrip": false,
190
+ "rstrip": false,
191
+ "normalized": false,
192
+ "special": false
193
+ },
194
+ "151665": {
195
+ "content": "<|PAD_TOKEN|>",
196
+ "single_word": false,
197
+ "lstrip": false,
198
+ "rstrip": false,
199
+ "normalized": false,
200
+ "special": true
201
+ }
202
+ }
203
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e996c88459a98f2aec83176d1b9e0a32709f1250134a38a0ca92ca58b575894
3
+ size 5777