Cartik/BastiAI-2-Instruct
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Cartik/BastiAI-2-Instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-22 11:03:18 +08:00
commit 62589b2b88
48 changed files with 369567 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
.gitattributes vendored Normal file
View File

@@ -0,0 +1,39 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
llmtf_eval/daru_treewayextractive.jsonl filter=lfs diff=lfs merge=lfs -text
llmtf_eval/nlpcoreteam_enMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
llmtf_eval/nlpcoreteam_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

11
README.md Normal file
View File

@@ -0,0 +1,11 @@
---
datasets:
- Cartik/learn-bastiai-dataset
language:
- ru
pipeline_tag: text-generation
base_model:
- Qwen/Qwen2.5-3B-Instruct
---
BastiAI 2

24
added_tokens.json Normal file
View File

@@ -0,0 +1,24 @@
{
"</tool_call>": 147090,
"<tool_call>": 147089,
"<|box_end|>": 147081,
"<|box_start|>": 147080,
"<|endoftext|>": 147075,
"<|file_sep|>": 147096,
"<|fim_middle|>": 147092,
"<|fim_pad|>": 147094,
"<|fim_prefix|>": 147091,
"<|fim_suffix|>": 147093,
"<|im_end|>": 147077,
"<|im_start|>": 147076,
"<|image_pad|>": 147087,
"<|object_ref_end|>": 147079,
"<|object_ref_start|>": 147078,
"<|quad_end|>": 147083,
"<|quad_start|>": 147082,
"<|repo_name|>": 147095,
"<|video_pad|>": 147088,
"<|vision_end|>": 147085,
"<|vision_pad|>": 147086,
"<|vision_start|>": 147084
}

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75/kto2",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"eos_token_id": 147077,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 147097
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"do_sample": true,
"eos_token_id": 147077,
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.45.2"
}

9321
llmtf_eval/daru_treewayabstractive.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

54
llmtf_eval/daru_treewayabstractive_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 512,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 200,
"method": "generate"
}
}

8
llmtf_eval/daru_treewayabstractive_total.jsonl Normal file
View File

@@ -0,0 +1,8 @@
{
"task_name": "daru/treewayabstractive",
"results": {
"rouge1": 0.33109987599556284,
"rouge2": 0.11202889150257295
},
"leaderboard_result": 0.2215643837490679
}

3
llmtf_eval/daru_treewayextractive.jsonl Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d1020fb7dc9f204618ab609bffe6d81a88ff7a7c1355f6f8be4b50fe0de8409
size 212492287

54
llmtf_eval/daru_treewayextractive_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 1,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 1000,
"method": "calculate_logsoftmax"
}
}

7
llmtf_eval/daru_treewayextractive_total.jsonl Normal file
View File

@@ -0,0 +1,7 @@
{
"task_name": "daru/treewayextractive",
"results": {
"r-prec": 0.3917218614718615
},
"leaderboard_result": 0.3917218614718615
}

57066
llmtf_eval/darumeru_MultiQ.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

54
llmtf_eval/darumeru_MultiQ_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 64,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "generate"
}
}

8
llmtf_eval/darumeru_MultiQ_total.jsonl Normal file
View File

@@ -0,0 +1,8 @@
{
"task_name": "darumeru/MultiQ",
"results": {
"f1": 0.3346248767848689,
"em": 0.22275334608030592
},
"leaderboard_result": 0.2786891114325874
}

8200
llmtf_eval/darumeru_PARus.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

54
llmtf_eval/darumeru_PARus_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 64,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "calculate_tokens_proba"
}
}

7
llmtf_eval/darumeru_PARus_total.jsonl Normal file
View File

@@ -0,0 +1,7 @@
{
"task_name": "darumeru/PARus",
"results": {
"acc": 0.7
},
"leaderboard_result": 0.7
}

9680
llmtf_eval/darumeru_RCB.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

54
llmtf_eval/darumeru_RCB_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 64,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "calculate_tokens_proba"
}
}

8
llmtf_eval/darumeru_RCB_total.jsonl Normal file
View File

@@ -0,0 +1,8 @@
{
"task_name": "darumeru/RCB",
"results": {
"acc": 0.5454545454545454,
"f1_macro": 0.49090309951702227
},
"leaderboard_result": 0.5181788224857838
}

7956
llmtf_eval/darumeru_RWSD.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

54
llmtf_eval/darumeru_RWSD_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 64,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "calculate_tokens_proba"
}
}

7
llmtf_eval/darumeru_RWSD_total.jsonl Normal file
View File

@@ -0,0 +1,7 @@
{
"task_name": "darumeru/RWSD",
"results": {
"acc": 0.6029411764705882
},
"leaderboard_result": 0.6029411764705882
}

18976
llmtf_eval/darumeru_cp_para_ru.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

54
llmtf_eval/darumeru_cp_para_ru_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 1024,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "generate"
}
}

9
llmtf_eval/darumeru_cp_para_ru_total.jsonl Normal file
View File

@@ -0,0 +1,9 @@
{
"task_name": "darumeru/cp_para_ru",
"results": {
"symbol_per_token": 3.993754090002875,
"len": 0.9986883734384026,
"lcs": 0.98
},
"leaderboard_result": 0.98
}

104760
llmtf_eval/darumeru_ruOpenBookQA.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

54
llmtf_eval/darumeru_ruOpenBookQA_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 64,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "calculate_tokens_proba"
}
}

8
llmtf_eval/darumeru_ruOpenBookQA_total.jsonl Normal file
View File

@@ -0,0 +1,8 @@
{
"task_name": "darumeru/ruOpenBookQA",
"results": {
"acc": 0.7302405498281787,
"f1_macro": 0.7304546157096631
},
"leaderboard_result": 0.7303475827689209
}

5040
llmtf_eval/darumeru_ruWorldTree.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

54
llmtf_eval/darumeru_ruWorldTree_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 64,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "calculate_tokens_proba"
}
}

8
llmtf_eval/darumeru_ruWorldTree_total.jsonl Normal file
View File

@@ -0,0 +1,8 @@
{
"task_name": "darumeru/ruWorldTree",
"results": {
"acc": 0.9047619047619048,
"f1_macro": 0.9043404138496471
},
"leaderboard_result": 0.904551159305776
}

251
llmtf_eval/evaluation_log.txt Normal file
View File

@@ -0,0 +1,251 @@
INFO: 2024-10-17 21:30:14,019: llmtf.base.evaluator: Starting eval on ['darumeru/multiq']
INFO: 2024-10-17 21:30:14,019: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:30:14,019: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:30:20,481: llmtf.base.darumeru/MultiQ: Loading Dataset: 6.46s
INFO: 2024-10-17 21:35:59,593: llmtf.base.darumeru/MultiQ: Processing Dataset: 339.11s
INFO: 2024-10-17 21:35:59,593: llmtf.base.darumeru/MultiQ: Results for darumeru/MultiQ:
INFO: 2024-10-17 21:35:59,594: llmtf.base.darumeru/MultiQ: {'f1': 0.3346248767848689, 'em': 0.22275334608030592}
INFO: 2024-10-17 21:35:59,599: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:35:59,599: llmtf.base.evaluator:
mean darumeru/MultiQ
0.279 0.279
INFO: 2024-10-17 21:36:08,809: llmtf.base.evaluator: Starting eval on ['darumeru/parus']
INFO: 2024-10-17 21:36:08,810: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:36:08,810: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:36:12,969: llmtf.base.darumeru/PARus: Loading Dataset: 4.16s
INFO: 2024-10-17 21:36:18,316: llmtf.base.darumeru/PARus: Processing Dataset: 5.35s
INFO: 2024-10-17 21:36:18,317: llmtf.base.darumeru/PARus: Results for darumeru/PARus:
INFO: 2024-10-17 21:36:18,327: llmtf.base.darumeru/PARus: {'acc': 0.7}
INFO: 2024-10-17 21:36:18,327: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:36:18,328: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus
0.489 0.279 0.700
INFO: 2024-10-17 21:36:27,550: llmtf.base.evaluator: Starting eval on ['darumeru/rcb']
INFO: 2024-10-17 21:36:27,550: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:36:27,551: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:36:31,450: llmtf.base.darumeru/RCB: Loading Dataset: 3.90s
INFO: 2024-10-17 21:36:38,683: llmtf.base.darumeru/RCB: Processing Dataset: 7.23s
INFO: 2024-10-17 21:36:38,683: llmtf.base.darumeru/RCB: Results for darumeru/RCB:
INFO: 2024-10-17 21:36:38,686: llmtf.base.darumeru/RCB: {'acc': 0.5454545454545454, 'f1_macro': 0.49090309951702227}
INFO: 2024-10-17 21:36:38,687: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:36:38,688: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB
0.499 0.279 0.700 0.518
INFO: 2024-10-17 21:36:48,734: llmtf.base.evaluator: Starting eval on ['darumeru/ruopenbookqa']
INFO: 2024-10-17 21:36:48,735: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:36:48,735: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:36:54,900: llmtf.base.darumeru/ruOpenBookQA: Loading Dataset: 6.17s
INFO: 2024-10-17 21:38:00,519: llmtf.base.darumeru/ruOpenBookQA: Processing Dataset: 65.62s
INFO: 2024-10-17 21:38:00,520: llmtf.base.darumeru/ruOpenBookQA: Results for darumeru/ruOpenBookQA:
INFO: 2024-10-17 21:38:00,532: llmtf.base.darumeru/ruOpenBookQA: {'acc': 0.7302405498281787, 'f1_macro': 0.7304546157096631}
INFO: 2024-10-17 21:38:00,541: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:38:00,542: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/ruOpenBookQA
0.557 0.279 0.700 0.518 0.730
INFO: 2024-10-17 21:38:09,745: llmtf.base.evaluator: Starting eval on ['darumeru/ruworldtree']
INFO: 2024-10-17 21:38:09,745: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:38:09,745: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:38:14,102: llmtf.base.darumeru/ruWorldTree: Loading Dataset: 4.36s
INFO: 2024-10-17 21:38:16,932: llmtf.base.darumeru/ruWorldTree: Processing Dataset: 2.83s
INFO: 2024-10-17 21:38:16,933: llmtf.base.darumeru/ruWorldTree: Results for darumeru/ruWorldTree:
INFO: 2024-10-17 21:38:16,936: llmtf.base.darumeru/ruWorldTree: {'acc': 0.9047619047619048, 'f1_macro': 0.9043404138496471}
INFO: 2024-10-17 21:38:16,936: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:38:16,937: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/ruOpenBookQA darumeru/ruWorldTree
0.626 0.279 0.700 0.518 0.730 0.905
INFO: 2024-10-17 21:38:26,077: llmtf.base.evaluator: Starting eval on ['darumeru/rwsd']
INFO: 2024-10-17 21:38:26,077: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:38:26,077: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:38:30,781: llmtf.base.darumeru/RWSD: Loading Dataset: 4.70s
INFO: 2024-10-17 21:38:36,497: llmtf.base.darumeru/RWSD: Processing Dataset: 5.72s
INFO: 2024-10-17 21:38:36,497: llmtf.base.darumeru/RWSD: Results for darumeru/RWSD:
INFO: 2024-10-17 21:38:36,498: llmtf.base.darumeru/RWSD: {'acc': 0.6029411764705882}
INFO: 2024-10-17 21:38:36,499: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:38:36,500: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree
0.622 0.279 0.700 0.518 0.603 0.730 0.905
INFO: 2024-10-17 21:38:45,688: llmtf.base.evaluator: Starting eval on ['daru/treewayextractive']
INFO: 2024-10-17 21:38:45,688: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:38:45,688: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:39:02,002: llmtf.base.daru/treewayextractive: Loading Dataset: 16.31s
INFO: 2024-10-17 21:42:05,777: llmtf.base.daru/treewayextractive: Processing Dataset: 183.77s
INFO: 2024-10-17 21:42:05,777: llmtf.base.daru/treewayextractive: Results for daru/treewayextractive:
INFO: 2024-10-17 21:42:06,010: llmtf.base.daru/treewayextractive: {'r-prec': 0.3917218614718615}
INFO: 2024-10-17 21:42:06,052: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:42:06,054: llmtf.base.evaluator:
mean daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree
0.589 0.392 0.279 0.700 0.518 0.603 0.730 0.905
INFO: 2024-10-17 21:42:15,170: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/rummlu']
INFO: 2024-10-17 21:42:15,170: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:42:15,170: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:46:47,282: llmtf.base.nlpcoreteam/ruMMLU: Loading Dataset: 272.11s
INFO: 2024-10-17 21:56:29,398: llmtf.base.nlpcoreteam/ruMMLU: Processing Dataset: 582.12s
INFO: 2024-10-17 21:56:29,399: llmtf.base.nlpcoreteam/ruMMLU: Results for nlpcoreteam/ruMMLU:
INFO: 2024-10-17 21:56:29,464: llmtf.base.nlpcoreteam/ruMMLU: metric
subject
abstract_algebra 0.340000
anatomy 0.414815
astronomy 0.611842
business_ethics 0.610000
clinical_knowledge 0.554717
college_biology 0.548611
college_chemistry 0.380000
college_computer_science 0.450000
college_mathematics 0.400000
college_medicine 0.526012
college_physics 0.470588
computer_security 0.620000
conceptual_physics 0.565957
econometrics 0.377193
electrical_engineering 0.537931
elementary_mathematics 0.529101
formal_logic 0.365079
global_facts 0.360000
high_school_biology 0.664516
high_school_chemistry 0.487685
high_school_computer_science 0.700000
high_school_european_history 0.751515
high_school_geography 0.722222
high_school_government_and_politics 0.564767
high_school_macroeconomics 0.528205
high_school_mathematics 0.433333
high_school_microeconomics 0.533613
high_school_physics 0.403974
high_school_psychology 0.713761
high_school_statistics 0.523148
high_school_us_history 0.661765
high_school_world_history 0.717300
human_aging 0.587444
human_sexuality 0.618321
international_law 0.735537
jurisprudence 0.666667
logical_fallacies 0.564417
machine_learning 0.392857
management 0.650485
marketing 0.752137
medical_genetics 0.580000
miscellaneous 0.632184
moral_disputes 0.583815
moral_scenarios 0.299441
nutrition 0.637255
philosophy 0.617363
prehistory 0.561728
professional_accounting 0.386525
professional_law 0.377445
professional_medicine 0.481618
professional_psychology 0.516340
public_relations 0.500000
security_studies 0.648980
sociology 0.756219
us_foreign_policy 0.720000
virology 0.439759
world_religions 0.719298
INFO: 2024-10-17 21:56:29,473: llmtf.base.nlpcoreteam/ruMMLU: metric
subject
STEM 0.503308
humanities 0.586259
other (business, health, misc.) 0.543782
social sciences 0.599968
INFO: 2024-10-17 21:56:29,478: llmtf.base.nlpcoreteam/ruMMLU: {'acc': 0.5583294528508019}
INFO: 2024-10-17 21:56:29,516: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:56:29,518: llmtf.base.evaluator:
mean daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/ruMMLU
0.586 0.392 0.279 0.700 0.518 0.603 0.730 0.905 0.558
INFO: 2024-10-17 21:56:39,535: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/enmmlu']
INFO: 2024-10-17 21:56:39,536: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:56:39,536: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:58:54,966: llmtf.base.nlpcoreteam/enMMLU: Loading Dataset: 135.43s
INFO: 2024-10-17 22:08:04,419: llmtf.base.nlpcoreteam/enMMLU: Processing Dataset: 549.45s
INFO: 2024-10-17 22:08:04,426: llmtf.base.nlpcoreteam/enMMLU: Results for nlpcoreteam/enMMLU:
INFO: 2024-10-17 22:08:04,492: llmtf.base.nlpcoreteam/enMMLU: metric
subject
abstract_algebra 0.380000
anatomy 0.637037
astronomy 0.717105
business_ethics 0.700000
clinical_knowledge 0.705660
college_biology 0.715278
college_chemistry 0.470000
college_computer_science 0.580000
college_mathematics 0.330000
college_medicine 0.664740
college_physics 0.509804
computer_security 0.740000
conceptual_physics 0.642553
econometrics 0.508772
electrical_engineering 0.600000
elementary_mathematics 0.547619
formal_logic 0.412698
global_facts 0.360000
high_school_biology 0.783871
high_school_chemistry 0.581281
high_school_computer_science 0.710000
high_school_european_history 0.800000
high_school_geography 0.757576
high_school_government_and_politics 0.854922
high_school_macroeconomics 0.679487
high_school_mathematics 0.455556
high_school_microeconomics 0.773109
high_school_physics 0.437086
high_school_psychology 0.844037
high_school_statistics 0.652778
high_school_us_history 0.833333
high_school_world_history 0.843882
human_aging 0.677130
human_sexuality 0.786260
international_law 0.768595
jurisprudence 0.814815
logical_fallacies 0.803681
machine_learning 0.446429
management 0.786408
marketing 0.858974
medical_genetics 0.760000
miscellaneous 0.795658
moral_disputes 0.667630
moral_scenarios 0.311732
nutrition 0.732026
philosophy 0.704180
prehistory 0.712963
professional_accounting 0.503546
professional_law 0.457627
professional_medicine 0.658088
professional_psychology 0.668301
public_relations 0.709091
security_studies 0.697959
sociology 0.800995
us_foreign_policy 0.800000
virology 0.506024
world_religions 0.801170
INFO: 2024-10-17 22:08:04,506: llmtf.base.nlpcoreteam/enMMLU: metric
subject
STEM 0.572187
humanities 0.687100
other (business, health, misc.) 0.667521
social sciences 0.740042
INFO: 2024-10-17 22:08:04,511: llmtf.base.nlpcoreteam/enMMLU: {'acc': 0.6667125709237595}
INFO: 2024-10-17 22:08:04,554: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 22:08:04,556: llmtf.base.evaluator:
mean daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU
0.595 0.392 0.279 0.700 0.518 0.603 0.730 0.905 0.667 0.558
INFO: 2024-10-17 22:08:14,512: llmtf.base.evaluator: Starting eval on ['daru/treewayabstractive']
INFO: 2024-10-17 22:08:14,513: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 22:08:14,513: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 22:08:18,791: llmtf.base.daru/treewayabstractive: Loading Dataset: 4.28s
INFO: 2024-10-17 22:11:46,260: llmtf.base.daru/treewayabstractive: Processing Dataset: 207.47s
INFO: 2024-10-17 22:11:46,260: llmtf.base.daru/treewayabstractive: Results for daru/treewayabstractive:
INFO: 2024-10-17 22:11:46,261: llmtf.base.daru/treewayabstractive: {'rouge1': 0.33109987599556284, 'rouge2': 0.11202889150257295}
INFO: 2024-10-17 22:11:46,262: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 22:11:46,263: llmtf.base.evaluator:
mean daru/treewayabstractive daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU
0.557 0.222 0.392 0.279 0.700 0.518 0.603 0.730 0.905 0.667 0.558
INFO: 2024-10-17 22:11:55,717: llmtf.base.evaluator: Starting eval on ['darumeru/cp_para_ru']
INFO: 2024-10-17 22:11:55,717: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 22:11:55,717: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 22:11:59,846: llmtf.base.darumeru/cp_para_ru: Loading Dataset: 4.13s
INFO: 2024-10-17 22:14:29,975: llmtf.base.darumeru/cp_para_ru: Processing Dataset: 150.13s
INFO: 2024-10-17 22:14:29,975: llmtf.base.darumeru/cp_para_ru: Results for darumeru/cp_para_ru:
INFO: 2024-10-17 22:14:29,976: llmtf.base.darumeru/cp_para_ru: {'symbol_per_token': 3.993754090002875, 'len': 0.9986883734384026, 'lcs': 0.98}
INFO: 2024-10-17 22:14:29,977: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 22:14:29,977: llmtf.base.evaluator:
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
0.596 0.222 0.392 0.279 0.700 0.518 0.603 0.980 0.730 0.905 0.667 0.558

2
llmtf_eval/evaluation_results.txt Normal file
View File

@@ -0,0 +1,2 @@
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
0.596 0.222 0.392 0.279 0.700 0.518 0.603 0.980 0.730 0.905 0.667 0.558

3
llmtf_eval/nlpcoreteam_enMMLU.jsonl Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7333ae2dd9a5974ba2d5a03e75a6f52f4f469f8d181f2b230b4c72c30d43220e
size 37141480

54
llmtf_eval/nlpcoreteam_enMMLU_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 64,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "calculate_tokens_proba"
}
}

7
llmtf_eval/nlpcoreteam_enMMLU_total.jsonl Normal file
View File

@@ -0,0 +1,7 @@
{
"task_name": "nlpcoreteam/enMMLU",
"results": {
"acc": 0.6667125709237595
},
"leaderboard_result": 0.6667125709237595
}

3
llmtf_eval/nlpcoreteam_ruMMLU.jsonl Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14ad0be3cf344bf030c934b0049c4691c1ab4d94c6b54d5b28ffa9cf84b88867
size 43064153

54
llmtf_eval/nlpcoreteam_ruMMLU_params.jsonl Normal file
View File

@@ -0,0 +1,54 @@
{
"custom_generation_config": null,
"model_params": {
"model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256_as1.75_kto_simpo/simpo0",
"generation_config": {
"bos_token_id": 147075,
"do_sample": true,
"eos_token_id": [
147077
],
"max_length": 32768,
"max_new_tokens": 64,
"pad_token_id": 147075,
"stop_strings": [
"<|im_end|>"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9,
"transformers_version": "4.45.2",
"trust_remote_code": false
},
"conversation_template": {
"system_prompt": "",
"system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
"bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
"user_role": "user",
"bot_role": "assistant",
"system_role": "system",
"global_prefix": "",
"suffix": "<|im_start|>assistant\n",
"add_special_tokens": false,
"eos_token": "<|im_end|>"
},
"load_in_8bit": false,
"torch_dtype": "auto",
"use_flash_attention_2": true,
"device_map": "cuda:0",
"use_fast_tokenizer": true,
"leading_space": false,
"space_token": null,
"trust_remote_code": false,
"max_model_len": 32768
},
"task_params": {
"max_len": 4000,
"few_shot_count": 0,
"batch_size": 8,
"max_sample_per_dataset": 10000000000000,
"method": "calculate_tokens_proba"
}
}

7
llmtf_eval/nlpcoreteam_ruMMLU_total.jsonl Normal file
View File

@@ -0,0 +1,7 @@
{
"task_name": "nlpcoreteam/ruMMLU",
"results": {
"acc": 0.5583294528508019
},
"leaderboard_result": 0.5583294528508019
}

146820
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78d625497b470a4e2ca4b4e41223b9694859b8f6d48dd5b3f537dd7a8b2486bf
size 4982828640

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1ce29823d548fffc6e3b2679bea25e856e12a3053a8bbbb55384ab1dc2f8c5a
size 1169277800

441
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,441 @@
{
"metadata": {
"total_size": 6152056832
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00002-of-00002.safetensors"
}
}

38
special_tokens_map.json Normal file
View File

@@ -0,0 +1,38 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:84b9483a1bfb5b8bb09b0269429a5e7fd89ee2868eb31cc70d5f695b64b95852
size 12441282

207
tokenizer_config.json Normal file
View File

@@ -0,0 +1,207 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"147075": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147076": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147077": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147078": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147079": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147080": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147081": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147082": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147083": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147084": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147085": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147086": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147087": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147088": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147089": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147090": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147091": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147092": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147093": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147094": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147095": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"147096": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": "<|endoftext|>",
"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",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long