RefalMachine
commited on
Commit
•
e7be766
1
Parent(s):
7fcbf9c
Upload folder using huggingface_hub
Browse files- .gitattributes +4 -0
- added_tokens.json +45 -0
- config.json +28 -0
- generation_config.json +10 -0
- llmtf_eval/daru_treewayabstractive.jsonl +0 -0
- llmtf_eval/daru_treewayabstractive_params.jsonl +54 -0
- llmtf_eval/daru_treewayabstractive_total.jsonl +8 -0
- llmtf_eval/daru_treewayextractive.jsonl +3 -0
- llmtf_eval/daru_treewayextractive_params.jsonl +54 -0
- llmtf_eval/daru_treewayextractive_total.jsonl +7 -0
- llmtf_eval/darumeru_MultiQ.jsonl +0 -0
- llmtf_eval/darumeru_MultiQ_params.jsonl +54 -0
- llmtf_eval/darumeru_MultiQ_total.jsonl +8 -0
- llmtf_eval/darumeru_PARus.jsonl +0 -0
- llmtf_eval/darumeru_PARus_params.jsonl +54 -0
- llmtf_eval/darumeru_PARus_total.jsonl +7 -0
- llmtf_eval/darumeru_RCB.jsonl +0 -0
- llmtf_eval/darumeru_RCB_params.jsonl +54 -0
- llmtf_eval/darumeru_RCB_total.jsonl +8 -0
- llmtf_eval/darumeru_RWSD.jsonl +0 -0
- llmtf_eval/darumeru_RWSD_params.jsonl +54 -0
- llmtf_eval/darumeru_RWSD_total.jsonl +7 -0
- llmtf_eval/darumeru_cp_para_ru.jsonl +0 -0
- llmtf_eval/darumeru_cp_para_ru_params.jsonl +54 -0
- llmtf_eval/darumeru_cp_para_ru_total.jsonl +9 -0
- llmtf_eval/darumeru_ruOpenBookQA.jsonl +0 -0
- llmtf_eval/darumeru_ruOpenBookQA_params.jsonl +54 -0
- llmtf_eval/darumeru_ruOpenBookQA_total.jsonl +8 -0
- llmtf_eval/darumeru_ruWorldTree.jsonl +0 -0
- llmtf_eval/darumeru_ruWorldTree_params.jsonl +54 -0
- llmtf_eval/darumeru_ruWorldTree_total.jsonl +8 -0
- llmtf_eval/evaluation_log.txt +251 -0
- llmtf_eval/evaluation_results.txt +2 -0
- llmtf_eval/nlpcoreteam_enMMLU.jsonl +3 -0
- llmtf_eval/nlpcoreteam_enMMLU_params.jsonl +54 -0
- llmtf_eval/nlpcoreteam_enMMLU_total.jsonl +7 -0
- llmtf_eval/nlpcoreteam_ruMMLU.jsonl +3 -0
- llmtf_eval/nlpcoreteam_ruMMLU_params.jsonl +54 -0
- llmtf_eval/nlpcoreteam_ruMMLU_total.jsonl +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +38 -0
- tokenizer.json +3 -0
- tokenizer_config.json +375 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,7 @@ 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 |
+
llmtf_eval/daru_treewayextractive.jsonl filter=lfs diff=lfs merge=lfs -text
|
37 |
+
llmtf_eval/nlpcoreteam_enMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
|
38 |
+
llmtf_eval/nlpcoreteam_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
|
39 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 145124,
|
3 |
+
"<tool_call>": 145123,
|
4 |
+
"<|box_end|>": 145115,
|
5 |
+
"<|box_start|>": 145114,
|
6 |
+
"<|endoftext|>": 145109,
|
7 |
+
"<|file_sep|>": 145130,
|
8 |
+
"<|fim_middle|>": 145126,
|
9 |
+
"<|fim_pad|>": 145128,
|
10 |
+
"<|fim_prefix|>": 145125,
|
11 |
+
"<|fim_suffix|>": 145127,
|
12 |
+
"<|free_token10|>": 145140,
|
13 |
+
"<|free_token11|>": 145141,
|
14 |
+
"<|free_token12|>": 145142,
|
15 |
+
"<|free_token13|>": 145143,
|
16 |
+
"<|free_token14|>": 145144,
|
17 |
+
"<|free_token15|>": 145145,
|
18 |
+
"<|free_token16|>": 145146,
|
19 |
+
"<|free_token17|>": 145147,
|
20 |
+
"<|free_token18|>": 145148,
|
21 |
+
"<|free_token19|>": 145149,
|
22 |
+
"<|free_token1|>": 145131,
|
23 |
+
"<|free_token20|>": 145150,
|
24 |
+
"<|free_token21|>": 145151,
|
25 |
+
"<|free_token2|>": 145132,
|
26 |
+
"<|free_token3|>": 145133,
|
27 |
+
"<|free_token4|>": 145134,
|
28 |
+
"<|free_token5|>": 145135,
|
29 |
+
"<|free_token6|>": 145136,
|
30 |
+
"<|free_token7|>": 145137,
|
31 |
+
"<|free_token8|>": 145138,
|
32 |
+
"<|free_token9|>": 145139,
|
33 |
+
"<|im_end|>": 145111,
|
34 |
+
"<|im_start|>": 145110,
|
35 |
+
"<|image_pad|>": 145121,
|
36 |
+
"<|object_ref_end|>": 145113,
|
37 |
+
"<|object_ref_start|>": 145112,
|
38 |
+
"<|quad_end|>": 145117,
|
39 |
+
"<|quad_start|>": 145116,
|
40 |
+
"<|repo_name|>": 145129,
|
41 |
+
"<|video_pad|>": 145122,
|
42 |
+
"<|vision_end|>": 145119,
|
43 |
+
"<|vision_pad|>": 145120,
|
44 |
+
"<|vision_start|>": 145118
|
45 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/kto1",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"eos_token_id": 145111,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 1536,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 8960,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 21,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 28,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": null,
|
22 |
+
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.45.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 145152
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_sample": true,
|
3 |
+
"eos_token_id": 145111,
|
4 |
+
"pad_token_id": 151643,
|
5 |
+
"repetition_penalty": 1.1,
|
6 |
+
"temperature": 0.7,
|
7 |
+
"top_k": 20,
|
8 |
+
"top_p": 0.8,
|
9 |
+
"transformers_version": "4.45.2"
|
10 |
+
}
|
llmtf_eval/daru_treewayabstractive.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llmtf_eval/daru_treewayabstractive_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 512,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 200,
|
52 |
+
"method": "generate"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/daru_treewayabstractive_total.jsonl
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "daru/treewayabstractive",
|
3 |
+
"results": {
|
4 |
+
"rouge1": 0.31023763628891676,
|
5 |
+
"rouge2": 0.09443696323171702
|
6 |
+
},
|
7 |
+
"leaderboard_result": 0.2023372997603169
|
8 |
+
}
|
llmtf_eval/daru_treewayextractive.jsonl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75cf70167322406bd8c1997ecfc9391b800f34de8cf75514b3d5394666e94263
|
3 |
+
size 212316130
|
llmtf_eval/daru_treewayextractive_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 1,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 1000,
|
52 |
+
"method": "calculate_logsoftmax"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/daru_treewayextractive_total.jsonl
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "daru/treewayextractive",
|
3 |
+
"results": {
|
4 |
+
"r-prec": 0.3782488455988456
|
5 |
+
},
|
6 |
+
"leaderboard_result": 0.3782488455988456
|
7 |
+
}
|
llmtf_eval/darumeru_MultiQ.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llmtf_eval/darumeru_MultiQ_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 64,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "generate"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/darumeru_MultiQ_total.jsonl
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "darumeru/MultiQ",
|
3 |
+
"results": {
|
4 |
+
"f1": 0.20613243758223346,
|
5 |
+
"em": 0.11281070745697896
|
6 |
+
},
|
7 |
+
"leaderboard_result": 0.1594715725196062
|
8 |
+
}
|
llmtf_eval/darumeru_PARus.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llmtf_eval/darumeru_PARus_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 64,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "calculate_tokens_proba"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/darumeru_PARus_total.jsonl
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "darumeru/PARus",
|
3 |
+
"results": {
|
4 |
+
"acc": 0.24
|
5 |
+
},
|
6 |
+
"leaderboard_result": 0.24
|
7 |
+
}
|
llmtf_eval/darumeru_RCB.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llmtf_eval/darumeru_RCB_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 64,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "calculate_tokens_proba"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/darumeru_RCB_total.jsonl
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "darumeru/RCB",
|
3 |
+
"results": {
|
4 |
+
"acc": 0.4727272727272727,
|
5 |
+
"f1_macro": 0.39356669305497743
|
6 |
+
},
|
7 |
+
"leaderboard_result": 0.4331469828911251
|
8 |
+
}
|
llmtf_eval/darumeru_RWSD.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llmtf_eval/darumeru_RWSD_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 64,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "calculate_tokens_proba"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/darumeru_RWSD_total.jsonl
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "darumeru/RWSD",
|
3 |
+
"results": {
|
4 |
+
"acc": 0.5098039215686274
|
5 |
+
},
|
6 |
+
"leaderboard_result": 0.5098039215686274
|
7 |
+
}
|
llmtf_eval/darumeru_cp_para_ru.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llmtf_eval/darumeru_cp_para_ru_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 1024,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "generate"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/darumeru_cp_para_ru_total.jsonl
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "darumeru/cp_para_ru",
|
3 |
+
"results": {
|
4 |
+
"symbol_per_token": 3.8978256135744003,
|
5 |
+
"len": 0.8764597602663033,
|
6 |
+
"lcs": 0.05
|
7 |
+
},
|
8 |
+
"leaderboard_result": 0.05
|
9 |
+
}
|
llmtf_eval/darumeru_ruOpenBookQA.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llmtf_eval/darumeru_ruOpenBookQA_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 64,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "calculate_tokens_proba"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/darumeru_ruOpenBookQA_total.jsonl
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "darumeru/ruOpenBookQA",
|
3 |
+
"results": {
|
4 |
+
"acc": 0.615979381443299,
|
5 |
+
"f1_macro": 0.6154023944317246
|
6 |
+
},
|
7 |
+
"leaderboard_result": 0.6156908879375118
|
8 |
+
}
|
llmtf_eval/darumeru_ruWorldTree.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llmtf_eval/darumeru_ruWorldTree_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 64,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "calculate_tokens_proba"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/darumeru_ruWorldTree_total.jsonl
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "darumeru/ruWorldTree",
|
3 |
+
"results": {
|
4 |
+
"acc": 0.7714285714285715,
|
5 |
+
"f1_macro": 0.7726851851851853
|
6 |
+
},
|
7 |
+
"leaderboard_result": 0.7720568783068784
|
8 |
+
}
|
llmtf_eval/evaluation_log.txt
ADDED
@@ -0,0 +1,251 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
INFO: 2024-11-18 14:18:48,851: llmtf.base.evaluator: Starting eval on ['darumeru/multiq']
|
2 |
+
INFO: 2024-11-18 14:18:48,852: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
3 |
+
INFO: 2024-11-18 14:18:48,852: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
4 |
+
INFO: 2024-11-18 14:18:50,653: llmtf.base.evaluator: Starting eval on ['darumeru/parus']
|
5 |
+
INFO: 2024-11-18 14:18:50,654: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
6 |
+
INFO: 2024-11-18 14:18:50,654: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
7 |
+
INFO: 2024-11-18 14:18:52,696: llmtf.base.darumeru/MultiQ: Loading Dataset: 3.84s
|
8 |
+
INFO: 2024-11-18 14:18:52,936: llmtf.base.evaluator: Starting eval on ['darumeru/rcb']
|
9 |
+
INFO: 2024-11-18 14:18:52,936: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
10 |
+
INFO: 2024-11-18 14:18:52,936: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
11 |
+
INFO: 2024-11-18 14:18:53,102: llmtf.base.darumeru/PARus: Loading Dataset: 2.45s
|
12 |
+
INFO: 2024-11-18 14:18:54,811: llmtf.base.evaluator: Starting eval on ['darumeru/ruopenbookqa']
|
13 |
+
INFO: 2024-11-18 14:18:54,811: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
14 |
+
INFO: 2024-11-18 14:18:54,811: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
15 |
+
INFO: 2024-11-18 14:18:55,708: llmtf.base.darumeru/RCB: Loading Dataset: 2.77s
|
16 |
+
INFO: 2024-11-18 14:18:56,455: llmtf.base.darumeru/PARus: Processing Dataset: 3.35s
|
17 |
+
INFO: 2024-11-18 14:18:56,457: llmtf.base.darumeru/PARus: Results for darumeru/PARus:
|
18 |
+
INFO: 2024-11-18 14:18:56,470: llmtf.base.darumeru/PARus: {'acc': 0.24}
|
19 |
+
INFO: 2024-11-18 14:18:56,471: llmtf.base.evaluator: Ended eval
|
20 |
+
INFO: 2024-11-18 14:18:56,474: llmtf.base.evaluator:
|
21 |
+
mean darumeru/PARus
|
22 |
+
0.240 0.240
|
23 |
+
INFO: 2024-11-18 14:18:56,487: llmtf.base.evaluator: Starting eval on ['darumeru/ruworldtree']
|
24 |
+
INFO: 2024-11-18 14:18:56,488: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
25 |
+
INFO: 2024-11-18 14:18:56,488: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
26 |
+
INFO: 2024-11-18 14:18:58,099: llmtf.base.darumeru/ruOpenBookQA: Loading Dataset: 3.29s
|
27 |
+
INFO: 2024-11-18 14:18:58,743: llmtf.base.evaluator: Starting eval on ['darumeru/rwsd']
|
28 |
+
INFO: 2024-11-18 14:18:58,744: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
29 |
+
INFO: 2024-11-18 14:18:58,744: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
30 |
+
INFO: 2024-11-18 14:18:58,925: llmtf.base.darumeru/ruWorldTree: Loading Dataset: 2.44s
|
31 |
+
INFO: 2024-11-18 14:19:00,968: llmtf.base.evaluator: Starting eval on ['daru/treewayextractive']
|
32 |
+
INFO: 2024-11-18 14:19:00,968: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
33 |
+
INFO: 2024-11-18 14:19:00,968: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
34 |
+
INFO: 2024-11-18 14:19:01,031: llmtf.base.darumeru/RCB: Processing Dataset: 5.32s
|
35 |
+
INFO: 2024-11-18 14:19:01,033: llmtf.base.darumeru/RCB: Results for darumeru/RCB:
|
36 |
+
INFO: 2024-11-18 14:19:01,040: llmtf.base.darumeru/RCB: {'acc': 0.4727272727272727, 'f1_macro': 0.39356669305497743}
|
37 |
+
INFO: 2024-11-18 14:19:01,041: llmtf.base.evaluator: Ended eval
|
38 |
+
INFO: 2024-11-18 14:19:01,044: llmtf.base.evaluator:
|
39 |
+
mean darumeru/PARus darumeru/RCB
|
40 |
+
0.337 0.240 0.433
|
41 |
+
INFO: 2024-11-18 14:19:01,497: llmtf.base.darumeru/RWSD: Loading Dataset: 2.75s
|
42 |
+
INFO: 2024-11-18 14:19:01,851: llmtf.base.darumeru/ruWorldTree: Processing Dataset: 2.92s
|
43 |
+
INFO: 2024-11-18 14:19:01,852: llmtf.base.darumeru/ruWorldTree: Results for darumeru/ruWorldTree:
|
44 |
+
INFO: 2024-11-18 14:19:01,859: llmtf.base.darumeru/ruWorldTree: {'acc': 0.7714285714285715, 'f1_macro': 0.7726851851851853}
|
45 |
+
INFO: 2024-11-18 14:19:01,859: llmtf.base.evaluator: Ended eval
|
46 |
+
INFO: 2024-11-18 14:19:01,863: llmtf.base.evaluator:
|
47 |
+
mean darumeru/PARus darumeru/RCB darumeru/ruWorldTree
|
48 |
+
0.482 0.240 0.433 0.772
|
49 |
+
INFO: 2024-11-18 14:19:02,889: llmtf.base.evaluator: Starting eval on ['daru/treewayabstractive']
|
50 |
+
INFO: 2024-11-18 14:19:02,890: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
51 |
+
INFO: 2024-11-18 14:19:02,890: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
52 |
+
INFO: 2024-11-18 14:19:03,199: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/rummlu']
|
53 |
+
INFO: 2024-11-18 14:19:03,199: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
54 |
+
INFO: 2024-11-18 14:19:03,199: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
55 |
+
INFO: 2024-11-18 14:19:06,629: llmtf.base.darumeru/RWSD: Processing Dataset: 5.13s
|
56 |
+
INFO: 2024-11-18 14:19:06,631: llmtf.base.darumeru/RWSD: Results for darumeru/RWSD:
|
57 |
+
INFO: 2024-11-18 14:19:06,635: llmtf.base.darumeru/RWSD: {'acc': 0.5098039215686274}
|
58 |
+
INFO: 2024-11-18 14:19:06,636: llmtf.base.evaluator: Ended eval
|
59 |
+
INFO: 2024-11-18 14:19:06,641: llmtf.base.evaluator:
|
60 |
+
mean darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruWorldTree
|
61 |
+
0.489 0.240 0.433 0.510 0.772
|
62 |
+
INFO: 2024-11-18 14:19:06,885: llmtf.base.daru/treewayabstractive: Loading Dataset: 4.00s
|
63 |
+
INFO: 2024-11-18 14:19:07,496: llmtf.base.evaluator: Starting eval on ['darumeru/cp_para_ru']
|
64 |
+
INFO: 2024-11-18 14:19:07,497: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
65 |
+
INFO: 2024-11-18 14:19:07,497: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
66 |
+
INFO: 2024-11-18 14:19:10,509: llmtf.base.darumeru/cp_para_ru: Loading Dataset: 3.01s
|
67 |
+
INFO: 2024-11-18 14:19:13,909: llmtf.base.daru/treewayextractive: Loading Dataset: 12.94s
|
68 |
+
INFO: 2024-11-18 14:19:44,800: llmtf.base.darumeru/ruOpenBookQA: Processing Dataset: 46.70s
|
69 |
+
INFO: 2024-11-18 14:19:44,801: llmtf.base.darumeru/ruOpenBookQA: Results for darumeru/ruOpenBookQA:
|
70 |
+
INFO: 2024-11-18 14:19:44,814: llmtf.base.darumeru/ruOpenBookQA: {'acc': 0.615979381443299, 'f1_macro': 0.6154023944317246}
|
71 |
+
INFO: 2024-11-18 14:19:44,821: llmtf.base.evaluator: Ended eval
|
72 |
+
INFO: 2024-11-18 14:19:44,826: llmtf.base.evaluator:
|
73 |
+
mean darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree
|
74 |
+
0.514 0.240 0.433 0.510 0.616 0.772
|
75 |
+
INFO: 2024-11-18 14:21:05,969: llmtf.base.nlpcoreteam/ruMMLU: Loading Dataset: 122.77s
|
76 |
+
INFO: 2024-11-18 14:21:35,520: llmtf.base.daru/treewayextractive: Processing Dataset: 141.61s
|
77 |
+
INFO: 2024-11-18 14:21:35,523: llmtf.base.daru/treewayextractive: Results for daru/treewayextractive:
|
78 |
+
INFO: 2024-11-18 14:21:35,753: llmtf.base.daru/treewayextractive: {'r-prec': 0.3782488455988456}
|
79 |
+
INFO: 2024-11-18 14:21:35,793: llmtf.base.evaluator: Ended eval
|
80 |
+
INFO: 2024-11-18 14:21:35,799: llmtf.base.evaluator:
|
81 |
+
mean daru/treewayextractive darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree
|
82 |
+
0.491 0.378 0.240 0.433 0.510 0.616 0.772
|
83 |
+
INFO: 2024-11-18 14:24:06,030: llmtf.base.darumeru/cp_para_ru: Processing Dataset: 295.52s
|
84 |
+
INFO: 2024-11-18 14:24:06,032: llmtf.base.darumeru/cp_para_ru: Results for darumeru/cp_para_ru:
|
85 |
+
INFO: 2024-11-18 14:24:06,036: llmtf.base.darumeru/cp_para_ru: {'symbol_per_token': 3.8978256135744003, 'len': 0.8764597602663033, 'lcs': 0.05}
|
86 |
+
INFO: 2024-11-18 14:24:06,036: llmtf.base.evaluator: Ended eval
|
87 |
+
INFO: 2024-11-18 14:24:06,041: llmtf.base.evaluator:
|
88 |
+
mean daru/treewayextractive darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/cp_para_ru darumeru/ruOpenBookQA darumeru/ruWorldTree
|
89 |
+
0.428 0.378 0.240 0.433 0.510 0.050 0.616 0.772
|
90 |
+
INFO: 2024-11-18 14:24:17,174: llmtf.base.daru/treewayabstractive: Processing Dataset: 310.29s
|
91 |
+
INFO: 2024-11-18 14:24:17,190: llmtf.base.daru/treewayabstractive: Results for daru/treewayabstractive:
|
92 |
+
INFO: 2024-11-18 14:24:17,208: llmtf.base.daru/treewayabstractive: {'rouge1': 0.31023763628891676, 'rouge2': 0.09443696323171702}
|
93 |
+
INFO: 2024-11-18 14:24:17,210: llmtf.base.evaluator: Ended eval
|
94 |
+
INFO: 2024-11-18 14:24:17,215: llmtf.base.evaluator:
|
95 |
+
mean daru/treewayabstractive daru/treewayextractive darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/cp_para_ru darumeru/ruOpenBookQA darumeru/ruWorldTree
|
96 |
+
0.400 0.202 0.378 0.240 0.433 0.510 0.050 0.616 0.772
|
97 |
+
INFO: 2024-11-18 14:26:06,991: llmtf.base.nlpcoreteam/ruMMLU: Processing Dataset: 301.02s
|
98 |
+
INFO: 2024-11-18 14:26:06,993: llmtf.base.nlpcoreteam/ruMMLU: Results for nlpcoreteam/ruMMLU:
|
99 |
+
INFO: 2024-11-18 14:26:07,037: llmtf.base.nlpcoreteam/ruMMLU: metric
|
100 |
+
subject
|
101 |
+
abstract_algebra 0.280000
|
102 |
+
anatomy 0.400000
|
103 |
+
astronomy 0.572368
|
104 |
+
business_ethics 0.460000
|
105 |
+
clinical_knowledge 0.494340
|
106 |
+
college_biology 0.375000
|
107 |
+
college_chemistry 0.290000
|
108 |
+
college_computer_science 0.400000
|
109 |
+
college_mathematics 0.400000
|
110 |
+
college_medicine 0.491329
|
111 |
+
college_physics 0.362745
|
112 |
+
computer_security 0.500000
|
113 |
+
conceptual_physics 0.421277
|
114 |
+
econometrics 0.280702
|
115 |
+
electrical_engineering 0.427586
|
116 |
+
elementary_mathematics 0.391534
|
117 |
+
formal_logic 0.373016
|
118 |
+
global_facts 0.230000
|
119 |
+
high_school_biology 0.496774
|
120 |
+
high_school_chemistry 0.458128
|
121 |
+
high_school_computer_science 0.500000
|
122 |
+
high_school_european_history 0.600000
|
123 |
+
high_school_geography 0.535354
|
124 |
+
high_school_government_and_politics 0.518135
|
125 |
+
high_school_macroeconomics 0.471795
|
126 |
+
high_school_mathematics 0.400000
|
127 |
+
high_school_microeconomics 0.462185
|
128 |
+
high_school_physics 0.291391
|
129 |
+
high_school_psychology 0.614679
|
130 |
+
high_school_statistics 0.490741
|
131 |
+
high_school_us_history 0.534314
|
132 |
+
high_school_world_history 0.624473
|
133 |
+
human_aging 0.520179
|
134 |
+
human_sexuality 0.519084
|
135 |
+
international_law 0.694215
|
136 |
+
jurisprudence 0.537037
|
137 |
+
logical_fallacies 0.472393
|
138 |
+
machine_learning 0.258929
|
139 |
+
management 0.640777
|
140 |
+
marketing 0.700855
|
141 |
+
medical_genetics 0.480000
|
142 |
+
miscellaneous 0.533844
|
143 |
+
moral_disputes 0.488439
|
144 |
+
moral_scenarios 0.268156
|
145 |
+
nutrition 0.526144
|
146 |
+
philosophy 0.543408
|
147 |
+
prehistory 0.475309
|
148 |
+
professional_accounting 0.347518
|
149 |
+
professional_law 0.345502
|
150 |
+
professional_medicine 0.426471
|
151 |
+
professional_psychology 0.411765
|
152 |
+
public_relations 0.427273
|
153 |
+
security_studies 0.542857
|
154 |
+
sociology 0.686567
|
155 |
+
us_foreign_policy 0.700000
|
156 |
+
virology 0.379518
|
157 |
+
world_religions 0.538012
|
158 |
+
INFO: 2024-11-18 14:26:07,045: llmtf.base.nlpcoreteam/ruMMLU: metric
|
159 |
+
subject
|
160 |
+
STEM 0.406471
|
161 |
+
humanities 0.499559
|
162 |
+
other (business, health, misc.) 0.473641
|
163 |
+
social sciences 0.514200
|
164 |
+
INFO: 2024-11-18 14:26:07,053: llmtf.base.nlpcoreteam/ruMMLU: {'acc': 0.47346768524963356}
|
165 |
+
INFO: 2024-11-18 14:26:07,087: llmtf.base.evaluator: Ended eval
|
166 |
+
INFO: 2024-11-18 14:26:07,096: llmtf.base.evaluator:
|
167 |
+
mean daru/treewayabstractive daru/treewayextractive darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/cp_para_ru darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/ruMMLU
|
168 |
+
0.408 0.202 0.378 0.240 0.433 0.510 0.050 0.616 0.772 0.473
|
169 |
+
INFO: 2024-11-18 14:29:49,600: llmtf.base.darumeru/MultiQ: Processing Dataset: 656.90s
|
170 |
+
INFO: 2024-11-18 14:29:49,603: llmtf.base.darumeru/MultiQ: Results for darumeru/MultiQ:
|
171 |
+
INFO: 2024-11-18 14:29:49,608: llmtf.base.darumeru/MultiQ: {'f1': 0.20613243758223346, 'em': 0.11281070745697896}
|
172 |
+
INFO: 2024-11-18 14:29:49,612: llmtf.base.evaluator: Ended eval
|
173 |
+
INFO: 2024-11-18 14:29:49,634: llmtf.base.evaluator:
|
174 |
+
mean daru/treewayabstractive daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/cp_para_ru darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/ruMMLU
|
175 |
+
0.383 0.202 0.378 0.159 0.240 0.433 0.510 0.050 0.616 0.772 0.473
|
176 |
+
INFO: 2024-11-18 14:29:55,578: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/enmmlu']
|
177 |
+
INFO: 2024-11-18 14:29:55,579: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
|
178 |
+
INFO: 2024-11-18 14:29:55,579: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
|
179 |
+
INFO: 2024-11-18 14:31:56,928: llmtf.base.nlpcoreteam/enMMLU: Loading Dataset: 121.35s
|
180 |
+
INFO: 2024-11-18 14:36:48,348: llmtf.base.nlpcoreteam/enMMLU: Processing Dataset: 291.42s
|
181 |
+
INFO: 2024-11-18 14:36:48,352: llmtf.base.nlpcoreteam/enMMLU: Results for nlpcoreteam/enMMLU:
|
182 |
+
INFO: 2024-11-18 14:36:48,396: llmtf.base.nlpcoreteam/enMMLU: metric
|
183 |
+
subject
|
184 |
+
abstract_algebra 0.350000
|
185 |
+
anatomy 0.562963
|
186 |
+
astronomy 0.664474
|
187 |
+
business_ethics 0.640000
|
188 |
+
clinical_knowledge 0.652830
|
189 |
+
college_biology 0.652778
|
190 |
+
college_chemistry 0.450000
|
191 |
+
college_computer_science 0.490000
|
192 |
+
college_mathematics 0.310000
|
193 |
+
college_medicine 0.618497
|
194 |
+
college_physics 0.500000
|
195 |
+
computer_security 0.710000
|
196 |
+
conceptual_physics 0.587234
|
197 |
+
econometrics 0.429825
|
198 |
+
electrical_engineering 0.531034
|
199 |
+
elementary_mathematics 0.460317
|
200 |
+
formal_logic 0.373016
|
201 |
+
global_facts 0.270000
|
202 |
+
high_school_biology 0.748387
|
203 |
+
high_school_chemistry 0.522167
|
204 |
+
high_school_computer_science 0.620000
|
205 |
+
high_school_european_history 0.733333
|
206 |
+
high_school_geography 0.747475
|
207 |
+
high_school_government_and_politics 0.808290
|
208 |
+
high_school_macroeconomics 0.658974
|
209 |
+
high_school_mathematics 0.403704
|
210 |
+
high_school_microeconomics 0.684874
|
211 |
+
high_school_physics 0.390728
|
212 |
+
high_school_psychology 0.822018
|
213 |
+
high_school_statistics 0.550926
|
214 |
+
high_school_us_history 0.720588
|
215 |
+
high_school_world_history 0.742616
|
216 |
+
human_aging 0.623318
|
217 |
+
human_sexuality 0.687023
|
218 |
+
international_law 0.710744
|
219 |
+
jurisprudence 0.759259
|
220 |
+
logical_fallacies 0.742331
|
221 |
+
machine_learning 0.419643
|
222 |
+
management 0.747573
|
223 |
+
marketing 0.824786
|
224 |
+
medical_genetics 0.690000
|
225 |
+
miscellaneous 0.708812
|
226 |
+
moral_disputes 0.641618
|
227 |
+
moral_scenarios 0.252514
|
228 |
+
nutrition 0.653595
|
229 |
+
philosophy 0.668810
|
230 |
+
prehistory 0.675926
|
231 |
+
professional_accounting 0.510638
|
232 |
+
professional_law 0.397653
|
233 |
+
professional_medicine 0.602941
|
234 |
+
professional_psychology 0.589869
|
235 |
+
public_relations 0.609091
|
236 |
+
security_studies 0.673469
|
237 |
+
sociology 0.776119
|
238 |
+
us_foreign_policy 0.740000
|
239 |
+
virology 0.463855
|
240 |
+
world_religions 0.783626
|
241 |
+
INFO: 2024-11-18 14:36:48,403: llmtf.base.nlpcoreteam/enMMLU: metric
|
242 |
+
subject
|
243 |
+
STEM 0.520077
|
244 |
+
humanities 0.630926
|
245 |
+
other (business, health, misc.) 0.612129
|
246 |
+
social sciences 0.685586
|
247 |
+
INFO: 2024-11-18 14:36:48,425: llmtf.base.nlpcoreteam/enMMLU: {'acc': 0.6121795307919802}
|
248 |
+
INFO: 2024-11-18 14:36:48,459: llmtf.base.evaluator: Ended eval
|
249 |
+
INFO: 2024-11-18 14:36:48,480: llmtf.base.evaluator:
|
250 |
+
mean daru/treewayabstractive daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/cp_para_ru darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU
|
251 |
+
0.404 0.202 0.378 0.159 0.240 0.433 0.510 0.050 0.616 0.772 0.612 0.473
|
llmtf_eval/evaluation_results.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
mean daru/treewayabstractive daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/cp_para_ru darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU
|
2 |
+
0.404 0.202 0.378 0.159 0.240 0.433 0.510 0.050 0.616 0.772 0.612 0.473
|
llmtf_eval/nlpcoreteam_enMMLU.jsonl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc82cd8c8f64da35f0862509ddfd17217e9fb107f450d2e3e2807f69ff6bc80c
|
3 |
+
size 37142060
|
llmtf_eval/nlpcoreteam_enMMLU_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 64,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "calculate_tokens_proba"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/nlpcoreteam_enMMLU_total.jsonl
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "nlpcoreteam/enMMLU",
|
3 |
+
"results": {
|
4 |
+
"acc": 0.6121795307919802
|
5 |
+
},
|
6 |
+
"leaderboard_result": 0.6121795307919802
|
7 |
+
}
|
llmtf_eval/nlpcoreteam_ruMMLU.jsonl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c07ebf724c9c50407ac459026f3c3514cc89efab52531b4f6c15c9002046f0ec
|
3 |
+
size 43069976
|
llmtf_eval/nlpcoreteam_ruMMLU_params.jsonl
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"custom_generation_config": null,
|
3 |
+
"model_params": {
|
4 |
+
"model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.5_nm_pv21/simpo2",
|
5 |
+
"generation_config": {
|
6 |
+
"bos_token_id": 145109,
|
7 |
+
"do_sample": true,
|
8 |
+
"eos_token_id": [
|
9 |
+
145111
|
10 |
+
],
|
11 |
+
"max_length": 32768,
|
12 |
+
"max_new_tokens": 64,
|
13 |
+
"pad_token_id": 145109,
|
14 |
+
"stop_strings": [
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"temperature": 0.1,
|
18 |
+
"top_k": 40,
|
19 |
+
"top_p": 0.9,
|
20 |
+
"transformers_version": "4.45.2",
|
21 |
+
"trust_remote_code": false
|
22 |
+
},
|
23 |
+
"conversation_template": {
|
24 |
+
"system_prompt": "",
|
25 |
+
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
26 |
+
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
27 |
+
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
|
28 |
+
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
|
29 |
+
"user_role": "user",
|
30 |
+
"bot_role": "assistant",
|
31 |
+
"system_role": "system",
|
32 |
+
"global_prefix": "",
|
33 |
+
"suffix": "<|im_start|>assistant\n",
|
34 |
+
"add_special_tokens": false,
|
35 |
+
"eos_token": "<|im_end|>"
|
36 |
+
},
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"torch_dtype": "auto",
|
39 |
+
"use_flash_attention_2": true,
|
40 |
+
"device_map": "cuda:0",
|
41 |
+
"use_fast_tokenizer": true,
|
42 |
+
"leading_space": false,
|
43 |
+
"space_token": null,
|
44 |
+
"trust_remote_code": false,
|
45 |
+
"max_model_len": 32768
|
46 |
+
},
|
47 |
+
"task_params": {
|
48 |
+
"max_len": 4000,
|
49 |
+
"few_shot_count": 0,
|
50 |
+
"batch_size": 2,
|
51 |
+
"max_sample_per_dataset": 10000000000000,
|
52 |
+
"method": "calculate_tokens_proba"
|
53 |
+
}
|
54 |
+
}
|
llmtf_eval/nlpcoreteam_ruMMLU_total.jsonl
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"task_name": "nlpcoreteam/ruMMLU",
|
3 |
+
"results": {
|
4 |
+
"acc": 0.47346768524963356
|
5 |
+
},
|
6 |
+
"leaderboard_result": 0.47346768524963356
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfb7628b063626c5d89defab15a697d2219f88248b9660c4fe1253acab2af894
|
3 |
+
size 3066626688
|
special_tokens_map.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"eos_token": {
|
25 |
+
"content": "<|im_end|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"pad_token": {
|
32 |
+
"content": "<|endoftext|>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
}
|
38 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e03677792927c1ab6656bfc682845e327f47a996db955621143a6412b06c1908
|
3 |
+
size 12298410
|
tokenizer_config.json
ADDED
@@ -0,0 +1,375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"145109": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"145110": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"145111": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"145112": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"145113": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"145114": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"145115": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"145116": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"145117": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"145118": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"145119": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"145120": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"145121": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"145122": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"145123": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"145124": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"145125": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"145126": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"145127": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
},
|
157 |
+
"145128": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": true
|
164 |
+
},
|
165 |
+
"145129": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
"145130": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
},
|
181 |
+
"145131": {
|
182 |
+
"content": "<|free_token1|>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": true,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"145132": {
|
190 |
+
"content": "<|free_token2|>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": true,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"145133": {
|
198 |
+
"content": "<|free_token3|>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": true,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"145134": {
|
206 |
+
"content": "<|free_token4|>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": true,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
},
|
213 |
+
"145135": {
|
214 |
+
"content": "<|free_token5|>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": true,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": false
|
220 |
+
},
|
221 |
+
"145136": {
|
222 |
+
"content": "<|free_token6|>",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": true,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": false
|
228 |
+
},
|
229 |
+
"145137": {
|
230 |
+
"content": "<|free_token7|>",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": true,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": false
|
236 |
+
},
|
237 |
+
"145138": {
|
238 |
+
"content": "<|free_token8|>",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": true,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": false
|
244 |
+
},
|
245 |
+
"145139": {
|
246 |
+
"content": "<|free_token9|>",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": true,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": false
|
252 |
+
},
|
253 |
+
"145140": {
|
254 |
+
"content": "<|free_token10|>",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": true,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": false
|
260 |
+
},
|
261 |
+
"145141": {
|
262 |
+
"content": "<|free_token11|>",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": true,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": false
|
268 |
+
},
|
269 |
+
"145142": {
|
270 |
+
"content": "<|free_token12|>",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": true,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false,
|
275 |
+
"special": false
|
276 |
+
},
|
277 |
+
"145143": {
|
278 |
+
"content": "<|free_token13|>",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": true,
|
281 |
+
"rstrip": false,
|
282 |
+
"single_word": false,
|
283 |
+
"special": false
|
284 |
+
},
|
285 |
+
"145144": {
|
286 |
+
"content": "<|free_token14|>",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": true,
|
289 |
+
"rstrip": false,
|
290 |
+
"single_word": false,
|
291 |
+
"special": false
|
292 |
+
},
|
293 |
+
"145145": {
|
294 |
+
"content": "<|free_token15|>",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": true,
|
297 |
+
"rstrip": false,
|
298 |
+
"single_word": false,
|
299 |
+
"special": false
|
300 |
+
},
|
301 |
+
"145146": {
|
302 |
+
"content": "<|free_token16|>",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": true,
|
305 |
+
"rstrip": false,
|
306 |
+
"single_word": false,
|
307 |
+
"special": false
|
308 |
+
},
|
309 |
+
"145147": {
|
310 |
+
"content": "<|free_token17|>",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": true,
|
313 |
+
"rstrip": false,
|
314 |
+
"single_word": false,
|
315 |
+
"special": false
|
316 |
+
},
|
317 |
+
"145148": {
|
318 |
+
"content": "<|free_token18|>",
|
319 |
+
"lstrip": false,
|
320 |
+
"normalized": true,
|
321 |
+
"rstrip": false,
|
322 |
+
"single_word": false,
|
323 |
+
"special": false
|
324 |
+
},
|
325 |
+
"145149": {
|
326 |
+
"content": "<|free_token19|>",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": true,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false,
|
331 |
+
"special": false
|
332 |
+
},
|
333 |
+
"145150": {
|
334 |
+
"content": "<|free_token20|>",
|
335 |
+
"lstrip": false,
|
336 |
+
"normalized": true,
|
337 |
+
"rstrip": false,
|
338 |
+
"single_word": false,
|
339 |
+
"special": false
|
340 |
+
},
|
341 |
+
"145151": {
|
342 |
+
"content": "<|free_token21|>",
|
343 |
+
"lstrip": false,
|
344 |
+
"normalized": true,
|
345 |
+
"rstrip": false,
|
346 |
+
"single_word": false,
|
347 |
+
"special": false
|
348 |
+
}
|
349 |
+
},
|
350 |
+
"additional_special_tokens": [
|
351 |
+
"<|im_start|>",
|
352 |
+
"<|im_end|>",
|
353 |
+
"<|object_ref_start|>",
|
354 |
+
"<|object_ref_end|>",
|
355 |
+
"<|box_start|>",
|
356 |
+
"<|box_end|>",
|
357 |
+
"<|quad_start|>",
|
358 |
+
"<|quad_end|>",
|
359 |
+
"<|vision_start|>",
|
360 |
+
"<|vision_end|>",
|
361 |
+
"<|vision_pad|>",
|
362 |
+
"<|image_pad|>",
|
363 |
+
"<|video_pad|>"
|
364 |
+
],
|
365 |
+
"bos_token": "<|endoftext|>",
|
366 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\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{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.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{%- endif %}\n",
|
367 |
+
"clean_up_tokenization_spaces": false,
|
368 |
+
"eos_token": "<|im_end|>",
|
369 |
+
"errors": "replace",
|
370 |
+
"model_max_length": 131072,
|
371 |
+
"pad_token": "<|endoftext|>",
|
372 |
+
"split_special_tokens": false,
|
373 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
374 |
+
"unk_token": null
|
375 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|