Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* 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

added_tokens.json

@@ -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
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/kto1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 147077,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 147097
+}

generation_config.json

@@ -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"
+}

llmtf_eval/daru_treewayabstractive_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/daru_treewayabstractive_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "daru/treewayabstractive",
+    "results": {
+        "rouge1": 0.3486928379990829,
+        "rouge2": 0.12579847916639003
+    },
+    "leaderboard_result": 0.23724565858273647
+}

llmtf_eval/daru_treewayextractive.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a116bbafae89d0abfaeade4c758e46404407947fbe77e42f954e739121b6f25
+size 212508807

llmtf_eval/daru_treewayextractive_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/daru_treewayextractive_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "daru/treewayextractive",
+    "results": {
+        "r-prec": 0.3931765512265512
+    },
+    "leaderboard_result": 0.3931765512265512
+}

llmtf_eval/darumeru_MultiQ_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/darumeru_MultiQ_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/MultiQ",
+    "results": {
+        "f1": 0.28476692977698215,
+        "em": 0.17304015296367112
+    },
+    "leaderboard_result": 0.22890354137032665
+}

llmtf_eval/darumeru_PARus_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/darumeru_PARus_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/PARus",
+    "results": {
+        "acc": 0.8
+    },
+    "leaderboard_result": 0.8
+}

llmtf_eval/darumeru_RCB_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/darumeru_RCB_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/RCB",
+    "results": {
+        "acc": 0.5863636363636363,
+        "f1_macro": 0.520344156087331
+    },
+    "leaderboard_result": 0.5533538962254836
+}

llmtf_eval/darumeru_RWSD_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/darumeru_RWSD_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/RWSD",
+    "results": {
+        "acc": 0.5343137254901961
+    },
+    "leaderboard_result": 0.5343137254901961
+}

llmtf_eval/darumeru_cp_para_ru_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/darumeru_cp_para_ru_total.jsonl

@@ -0,0 +1,9 @@
+{
+    "task_name": "darumeru/cp_para_ru",
+    "results": {
+        "symbol_per_token": 3.9920472926206347,
+        "len": 0.9992233172309354,
+        "lcs": 1.0
+    },
+    "leaderboard_result": 1.0
+}

llmtf_eval/darumeru_ruOpenBookQA_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/darumeru_ruOpenBookQA_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/ruOpenBookQA",
+    "results": {
+        "acc": 0.8191580756013745,
+        "f1_macro": 0.8196610608491144
+    },
+    "leaderboard_result": 0.8194095682252445
+}

llmtf_eval/darumeru_ruWorldTree_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/darumeru_ruWorldTree_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/ruWorldTree",
+    "results": {
+        "acc": 0.9047619047619048,
+        "f1_macro": 0.9048601269315972
+    },
+    "leaderboard_result": 0.904811015846751
+}

llmtf_eval/evaluation_log.txt

@@ -0,0 +1,251 @@
+INFO: 2024-10-26 10:00:21,600: llmtf.base.evaluator: Starting eval on ['darumeru/multiq']
+INFO: 2024-10-26 10:00:21,601: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:21,601: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:23,554: llmtf.base.evaluator: Starting eval on ['darumeru/parus']
+INFO: 2024-10-26 10:00:23,554: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:23,554: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:25,061: llmtf.base.evaluator: Starting eval on ['darumeru/rcb']
+INFO: 2024-10-26 10:00:25,062: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:25,062: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:25,825: llmtf.base.darumeru/MultiQ: Loading Dataset: 4.22s
+INFO: 2024-10-26 10:00:25,839: llmtf.base.darumeru/PARus: Loading Dataset: 2.28s
+INFO: 2024-10-26 10:00:27,118: llmtf.base.evaluator: Starting eval on ['darumeru/ruopenbookqa']
+INFO: 2024-10-26 10:00:27,118: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:27,118: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:27,739: llmtf.base.darumeru/RCB: Loading Dataset: 2.68s
+INFO: 2024-10-26 10:00:29,086: llmtf.base.darumeru/PARus: Processing Dataset: 3.25s
+INFO: 2024-10-26 10:00:29,088: llmtf.base.darumeru/PARus: Results for darumeru/PARus:
+INFO: 2024-10-26 10:00:29,102: llmtf.base.darumeru/PARus: {'acc': 0.8}
+INFO: 2024-10-26 10:00:29,102: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:00:29,105: llmtf.base.evaluator: 
+mean	darumeru/PARus
+0.800	0.800
+INFO: 2024-10-26 10:00:30,121: llmtf.base.evaluator: Starting eval on ['darumeru/ruworldtree']
+INFO: 2024-10-26 10:00:30,122: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:30,122: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:30,879: llmtf.base.darumeru/ruOpenBookQA: Loading Dataset: 3.76s
+INFO: 2024-10-26 10:00:31,330: llmtf.base.evaluator: Starting eval on ['darumeru/rwsd']
+INFO: 2024-10-26 10:00:31,330: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:31,330: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:32,861: llmtf.base.darumeru/RCB: Processing Dataset: 5.12s
+INFO: 2024-10-26 10:00:32,862: llmtf.base.darumeru/RCB: Results for darumeru/RCB:
+INFO: 2024-10-26 10:00:32,870: llmtf.base.darumeru/RCB: {'acc': 0.5863636363636363, 'f1_macro': 0.520344156087331}
+INFO: 2024-10-26 10:00:32,871: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:00:32,874: llmtf.base.evaluator: 
+mean	darumeru/PARus	darumeru/RCB
+0.677	0.800	0.553
+INFO: 2024-10-26 10:00:33,148: llmtf.base.darumeru/ruWorldTree: Loading Dataset: 3.03s
+INFO: 2024-10-26 10:00:33,497: llmtf.base.evaluator: Starting eval on ['daru/treewayextractive']
+INFO: 2024-10-26 10:00:33,498: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:33,498: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:34,009: llmtf.base.darumeru/RWSD: Loading Dataset: 2.68s
+INFO: 2024-10-26 10:00:35,785: llmtf.base.darumeru/ruWorldTree: Processing Dataset: 2.64s
+INFO: 2024-10-26 10:00:35,787: llmtf.base.darumeru/ruWorldTree: Results for darumeru/ruWorldTree:
+INFO: 2024-10-26 10:00:35,795: llmtf.base.darumeru/ruWorldTree: {'acc': 0.9047619047619048, 'f1_macro': 0.9048601269315972}
+INFO: 2024-10-26 10:00:35,795: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:00:35,799: llmtf.base.evaluator: 
+mean	darumeru/PARus	darumeru/RCB	darumeru/ruWorldTree
+0.753	0.800	0.553	0.905
+INFO: 2024-10-26 10:00:36,096: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/rummlu']
+INFO: 2024-10-26 10:00:36,096: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:36,096: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:39,654: llmtf.base.darumeru/RWSD: Processing Dataset: 5.64s
+INFO: 2024-10-26 10:00:39,655: llmtf.base.darumeru/RWSD: Results for darumeru/RWSD:
+INFO: 2024-10-26 10:00:39,660: llmtf.base.darumeru/RWSD: {'acc': 0.5343137254901961}
+INFO: 2024-10-26 10:00:39,660: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:00:39,664: llmtf.base.evaluator: 
+mean	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/ruWorldTree
+0.698	0.800	0.553	0.534	0.905
+INFO: 2024-10-26 10:00:40,963: llmtf.base.evaluator: Starting eval on ['daru/treewayabstractive']
+INFO: 2024-10-26 10:00:40,963: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:40,963: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:43,550: llmtf.base.evaluator: Starting eval on ['darumeru/cp_para_ru']
+INFO: 2024-10-26 10:00:43,550: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:00:43,550: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:00:44,771: llmtf.base.daru/treewayabstractive: Loading Dataset: 3.81s
+INFO: 2024-10-26 10:00:46,698: llmtf.base.darumeru/cp_para_ru: Loading Dataset: 3.15s
+INFO: 2024-10-26 10:00:46,725: llmtf.base.daru/treewayextractive: Loading Dataset: 13.23s
+INFO: 2024-10-26 10:01:01,719: llmtf.base.darumeru/ruOpenBookQA: Processing Dataset: 30.84s
+INFO: 2024-10-26 10:01:01,720: llmtf.base.darumeru/ruOpenBookQA: Results for darumeru/ruOpenBookQA:
+INFO: 2024-10-26 10:01:01,734: llmtf.base.darumeru/ruOpenBookQA: {'acc': 0.8191580756013745, 'f1_macro': 0.8196610608491144}
+INFO: 2024-10-26 10:01:01,743: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:01:01,747: llmtf.base.evaluator: 
+mean	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/ruOpenBookQA	darumeru/ruWorldTree
+0.722	0.800	0.553	0.534	0.819	0.905
+INFO: 2024-10-26 10:02:41,817: llmtf.base.darumeru/cp_para_ru: Processing Dataset: 115.10s
+INFO: 2024-10-26 10:02:41,820: llmtf.base.darumeru/cp_para_ru: Results for darumeru/cp_para_ru:
+INFO: 2024-10-26 10:02:41,823: llmtf.base.darumeru/cp_para_ru: {'symbol_per_token': 3.9920472926206347, 'len': 0.9992233172309354, 'lcs': 1.0}
+INFO: 2024-10-26 10:02:41,824: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:02:41,830: llmtf.base.nlpcoreteam/ruMMLU: Loading Dataset: 125.73s
+INFO: 2024-10-26 10:02:41,835: llmtf.base.evaluator: 
+mean	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/cp_para_ru	darumeru/ruOpenBookQA	darumeru/ruWorldTree
+0.769	0.800	0.553	0.534	1.000	0.819	0.905
+INFO: 2024-10-26 10:03:13,156: llmtf.base.daru/treewayabstractive: Processing Dataset: 148.37s
+INFO: 2024-10-26 10:03:13,158: llmtf.base.daru/treewayabstractive: Results for daru/treewayabstractive:
+INFO: 2024-10-26 10:03:13,162: llmtf.base.daru/treewayabstractive: {'rouge1': 0.3486928379990829, 'rouge2': 0.12579847916639003}
+INFO: 2024-10-26 10:03:13,164: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:03:13,169: llmtf.base.evaluator: 
+mean	daru/treewayabstractive	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/cp_para_ru	darumeru/ruOpenBookQA	darumeru/ruWorldTree
+0.693	0.237	0.800	0.553	0.534	1.000	0.819	0.905
+INFO: 2024-10-26 10:04:19,979: llmtf.base.darumeru/MultiQ: Processing Dataset: 234.15s
+INFO: 2024-10-26 10:04:19,982: llmtf.base.darumeru/MultiQ: Results for darumeru/MultiQ:
+INFO: 2024-10-26 10:04:19,986: llmtf.base.darumeru/MultiQ: {'f1': 0.28476692977698215, 'em': 0.17304015296367112}
+INFO: 2024-10-26 10:04:19,991: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:04:19,997: llmtf.base.evaluator: 
+mean	daru/treewayabstractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/cp_para_ru	darumeru/ruOpenBookQA	darumeru/ruWorldTree
+0.635	0.237	0.229	0.800	0.553	0.534	1.000	0.819	0.905
+INFO: 2024-10-26 10:04:32,092: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/enmmlu']
+INFO: 2024-10-26 10:04:32,092: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
+INFO: 2024-10-26 10:04:32,092: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-10-26 10:05:58,778: llmtf.base.daru/treewayextractive: Processing Dataset: 312.04s
+INFO: 2024-10-26 10:05:58,782: llmtf.base.daru/treewayextractive: Results for daru/treewayextractive:
+INFO: 2024-10-26 10:05:59,016: llmtf.base.daru/treewayextractive: {'r-prec': 0.3931765512265512}
+INFO: 2024-10-26 10:05:59,058: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:05:59,066: llmtf.base.evaluator: 
+mean	daru/treewayabstractive	daru/treewayextractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/cp_para_ru	darumeru/ruOpenBookQA	darumeru/ruWorldTree
+0.608	0.237	0.393	0.229	0.800	0.553	0.534	1.000	0.819	0.905
+INFO: 2024-10-26 10:06:34,248: llmtf.base.nlpcoreteam/enMMLU: Loading Dataset: 122.16s
+INFO: 2024-10-26 10:07:49,582: llmtf.base.nlpcoreteam/ruMMLU: Processing Dataset: 307.75s
+INFO: 2024-10-26 10:07:49,584: llmtf.base.nlpcoreteam/ruMMLU: Results for nlpcoreteam/ruMMLU:
+INFO: 2024-10-26 10:07:49,630: llmtf.base.nlpcoreteam/ruMMLU:                                        metric
+subject                                      
+abstract_algebra                     0.430000
+anatomy                              0.577778
+astronomy                            0.743421
+business_ethics                      0.670000
+clinical_knowledge                   0.701887
+college_biology                      0.687500
+college_chemistry                    0.470000
+college_computer_science             0.640000
+college_mathematics                  0.470000
+college_medicine                     0.589595
+college_physics                      0.490196
+computer_security                    0.710000
+conceptual_physics                   0.668085
+econometrics                         0.464912
+electrical_engineering               0.579310
+elementary_mathematics               0.624339
+formal_logic                         0.420635
+global_facts                         0.400000
+high_school_biology                  0.806452
+high_school_chemistry                0.536946
+high_school_computer_science         0.790000
+high_school_european_history         0.763636
+high_school_geography                0.777778
+high_school_government_and_politics  0.715026
+high_school_macroeconomics           0.653846
+high_school_mathematics              0.462963
+high_school_microeconomics           0.714286
+high_school_physics                  0.490066
+high_school_psychology               0.796330
+high_school_statistics               0.625000
+high_school_us_history               0.754902
+high_school_world_history            0.776371
+human_aging                          0.618834
+human_sexuality                      0.717557
+international_law                    0.702479
+jurisprudence                        0.685185
+logical_fallacies                    0.613497
+machine_learning                     0.446429
+management                           0.737864
+marketing                            0.799145
+medical_genetics                     0.650000
+miscellaneous                        0.717752
+moral_disputes                       0.604046
+moral_scenarios                      0.242458
+nutrition                            0.705882
+philosophy                           0.639871
+prehistory                           0.626543
+professional_accounting              0.446809
+professional_law                     0.399609
+professional_medicine                0.595588
+professional_psychology              0.601307
+public_relations                     0.600000
+security_studies                     0.673469
+sociology                            0.711443
+us_foreign_policy                    0.800000
+virology                             0.500000
+world_religions                      0.730994
+INFO: 2024-10-26 10:07:49,638: llmtf.base.nlpcoreteam/ruMMLU:                                    metric
+subject                                  
+STEM                             0.592817
+humanities                       0.612325
+other (business, health, misc.)  0.622224
+social sciences                  0.685496
+INFO: 2024-10-26 10:07:49,666: llmtf.base.nlpcoreteam/ruMMLU: {'acc': 0.6282155966274303}
+INFO: 2024-10-26 10:07:49,702: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:07:49,714: 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/ruMMLU
+0.610	0.237	0.393	0.229	0.800	0.553	0.534	1.000	0.819	0.905	0.628
+INFO: 2024-10-26 10:11:09,714: llmtf.base.nlpcoreteam/enMMLU: Processing Dataset: 275.46s
+INFO: 2024-10-26 10:11:09,718: llmtf.base.nlpcoreteam/enMMLU: Results for nlpcoreteam/enMMLU:
+INFO: 2024-10-26 10:11:09,763: llmtf.base.nlpcoreteam/enMMLU:                                        metric
+subject                                      
+abstract_algebra                     0.510000
+anatomy                              0.703704
+astronomy                            0.848684
+business_ethics                      0.770000
+clinical_knowledge                   0.777358
+college_biology                      0.847222
+college_chemistry                    0.550000
+college_computer_science             0.710000
+college_mathematics                  0.470000
+college_medicine                     0.693642
+college_physics                      0.519608
+computer_security                    0.780000
+conceptual_physics                   0.706383
+econometrics                         0.596491
+electrical_engineering               0.668966
+elementary_mathematics               0.666667
+formal_logic                         0.484127
+global_facts                         0.450000
+high_school_biology                  0.867742
+high_school_chemistry                0.630542
+high_school_computer_science         0.860000
+high_school_european_history         0.800000
+high_school_geography                0.878788
+high_school_government_and_politics  0.943005
+high_school_macroeconomics           0.761538
+high_school_mathematics              0.551852
+high_school_microeconomics           0.865546
+high_school_physics                  0.582781
+high_school_psychology               0.882569
+high_school_statistics               0.717593
+high_school_us_history               0.848039
+high_school_world_history            0.848101
+human_aging                          0.784753
+human_sexuality                      0.748092
+international_law                    0.785124
+jurisprudence                        0.787037
+logical_fallacies                    0.834356
+machine_learning                     0.535714
+management                           0.864078
+marketing                            0.901709
+medical_genetics                     0.790000
+miscellaneous                        0.846743
+moral_disputes                       0.731214
+moral_scenarios                      0.401117
+nutrition                            0.790850
+philosophy                           0.729904
+prehistory                           0.793210
+professional_accounting              0.570922
+professional_law                     0.507171
+professional_medicine                0.764706
+professional_psychology              0.745098
+public_relations                     0.700000
+security_studies                     0.759184
+sociology                            0.845771
+us_foreign_policy                    0.880000
+virology                             0.518072
+world_religions                      0.847953
+INFO: 2024-10-26 10:11:09,771: llmtf.base.nlpcoreteam/enMMLU:                                    metric
+subject                                  
+STEM                             0.667986
+humanities                       0.722873
+other (business, health, misc.)  0.730467
+social sciences                  0.800507
+INFO: 2024-10-26 10:11:09,779: llmtf.base.nlpcoreteam/enMMLU: {'acc': 0.7304583527816666}
+INFO: 2024-10-26 10:11:09,811: llmtf.base.evaluator: Ended eval
+INFO: 2024-10-26 10:11:09,819: 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
+0.621	0.237	0.393	0.229	0.800	0.553	0.534	1.000	0.819	0.905	0.730	0.628

llmtf_eval/evaluation_results.txt

@@ -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
+0.621	0.237	0.393	0.229	0.800	0.553	0.534	1.000	0.819	0.905	0.730	0.628

llmtf_eval/nlpcoreteam_enMMLU.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f679f84c651ffdd921961a9544f1e3c1eb75e2ea8c3e89924a5bbd41658c50e4
+size 37139349

llmtf_eval/nlpcoreteam_enMMLU_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/nlpcoreteam_enMMLU_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "nlpcoreteam/enMMLU",
+    "results": {
+        "acc": 0.7304583527816666
+    },
+    "leaderboard_result": 0.7304583527816666
+}

llmtf_eval/nlpcoreteam_ruMMLU.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ed19a34b0064491314326cf6d4c8d1b9abd67664c9ae754aea132d31f6a0f3
+size 43073105

llmtf_eval/nlpcoreteam_ruMMLU_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_full_two_stage_lr5e4_peft_mlp_32_32_lm_head_lora_bs256_as1.5_pv14/simpo2",
+        "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"
+    }
+}

llmtf_eval/nlpcoreteam_ruMMLU_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "nlpcoreteam/ruMMLU",
+    "results": {
+        "acc": 0.6282155966274303
+    },
+    "leaderboard_result": 0.6282155966274303
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b23699748148a2e0b6f34a30cc42544a8d3a13645eae60e3a8bb1708f2058f
+size 4977848024

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b6196874fa79e9ceac10bb527f5482c9cf7c6c940e13668ad6ab2c5b47476c
+size 4991495856

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfe35a5c03981c86d876f992ca768f583b83997c2eb1dc1ed10c12fa059aad0
+size 4136329648

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d4361516b998390c98d9e8160d6a7950700fc492d9d5cefea8762f9de6947f
+size 1054391424

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15160026112
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -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
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -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
+}