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 +1,45 @@
+{
+  "</tool_call>": 145124,
+  "<tool_call>": 145123,
+  "<|box_end|>": 145115,
+  "<|box_start|>": 145114,
+  "<|endoftext|>": 145109,
+  "<|file_sep|>": 145130,
+  "<|fim_middle|>": 145126,
+  "<|fim_pad|>": 145128,
+  "<|fim_prefix|>": 145125,
+  "<|fim_suffix|>": 145127,
+  "<|free_token10|>": 145140,
+  "<|free_token11|>": 145141,
+  "<|free_token12|>": 145142,
+  "<|free_token13|>": 145143,
+  "<|free_token14|>": 145144,
+  "<|free_token15|>": 145145,
+  "<|free_token16|>": 145146,
+  "<|free_token17|>": 145147,
+  "<|free_token18|>": 145148,
+  "<|free_token19|>": 145149,
+  "<|free_token1|>": 145131,
+  "<|free_token20|>": 145150,
+  "<|free_token21|>": 145151,
+  "<|free_token2|>": 145132,
+  "<|free_token3|>": 145133,
+  "<|free_token4|>": 145134,
+  "<|free_token5|>": 145135,
+  "<|free_token6|>": 145136,
+  "<|free_token7|>": 145137,
+  "<|free_token8|>": 145138,
+  "<|free_token9|>": 145139,
+  "<|im_end|>": 145111,
+  "<|im_start|>": 145110,
+  "<|image_pad|>": 145121,
+  "<|object_ref_end|>": 145113,
+  "<|object_ref_start|>": 145112,
+  "<|quad_end|>": 145117,
+  "<|quad_start|>": 145116,
+  "<|repo_name|>": 145129,
+  "<|video_pad|>": 145122,
+  "<|vision_end|>": 145119,
+  "<|vision_pad|>": 145120,
+  "<|vision_start|>": 145118
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_coder_1.5B_ext_u48_part1-2_lr5e4_bs128_peft_mlp_32_32_lm_head_lora_3e4_r_as1.35_pv21/ft0",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 145111,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "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": 145152
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "do_sample": true,
+  "eos_token_id": 145111,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "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": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 512,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.30478241492489133,
+        "rouge2": 0.09260347651798656
+    },
+    "leaderboard_result": 0.19869294572143895
+}

llmtf_eval/daru_treewayextractive.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624538fa3c1cb0ec9d2b358224e5bdf354ae76a751c230c6dedb8a385eb10991
+size 212306798

llmtf_eval/daru_treewayextractive_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 1,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.3703670274170274
+    },
+    "leaderboard_result": 0.3703670274170274
+}

llmtf_eval/darumeru_MultiQ_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.2166827508040571,
+        "em": 0.11567877629063097
+    },
+    "leaderboard_result": 0.16618076354734404
+}

llmtf_eval/darumeru_PARus_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.21
+    },
+    "leaderboard_result": 0.21
+}

llmtf_eval/darumeru_RCB_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.4681818181818182,
+        "f1_macro": 0.3981025874347421
+    },
+    "leaderboard_result": 0.43314220280828014
+}

llmtf_eval/darumeru_RWSD_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.45098039215686275
+    },
+    "leaderboard_result": 0.45098039215686275
+}

llmtf_eval/darumeru_cp_para_ru_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 1024,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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 +1,10 @@
+{
+    "task_name": "darumeru/cp_para_ru",
+    "results": {
+        "tokens_per_word": 1.8729616000663136,
+        "symbol_per_token": 4.043905520913176,
+        "len": 0.927490542336371,
+        "lcs": 0.05
+    },
+    "leaderboard_result": 0.05
+}

llmtf_eval/darumeru_ruOpenBookQA_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.46134020618556704,
+        "f1_macro": 0.4607981854644543
+    },
+    "leaderboard_result": 0.46106919582501066
+}

llmtf_eval/darumeru_ruWorldTree_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.5619047619047619,
+        "f1_macro": 0.5621556341232892
+    },
+    "leaderboard_result": 0.5620301980140255
+}

llmtf_eval/evaluation_log.txt

@@ -0,0 +1,251 @@
+INFO: 2024-11-15 16:53:45,193: llmtf.base.evaluator: Starting eval on ['darumeru/multiq']
+INFO: 2024-11-15 16:53:45,193: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 16:53:45,193: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 16:53:45,368: llmtf.base.evaluator: Starting eval on ['darumeru/parus']
+INFO: 2024-11-15 16:53:45,368: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 16:53:45,368: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 16:53:47,651: llmtf.base.darumeru/PARus: Loading Dataset: 2.28s
+INFO: 2024-11-15 16:53:48,903: llmtf.base.darumeru/MultiQ: Loading Dataset: 3.71s
+INFO: 2024-11-15 16:53:49,849: llmtf.base.darumeru/PARus: Processing Dataset: 2.20s
+INFO: 2024-11-15 16:53:49,849: llmtf.base.darumeru/PARus: Results for darumeru/PARus:
+INFO: 2024-11-15 16:53:49,859: llmtf.base.darumeru/PARus: {'acc': 0.21}
+INFO: 2024-11-15 16:53:49,859: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 16:53:49,859: llmtf.base.evaluator: 
+mean	darumeru/PARus
+0.210	0.210
+INFO: 2024-11-15 16:53:58,225: llmtf.base.evaluator: Starting eval on ['darumeru/ruopenbookqa']
+INFO: 2024-11-15 16:53:58,225: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 16:53:58,225: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 16:54:01,621: llmtf.base.darumeru/ruOpenBookQA: Loading Dataset: 3.40s
+INFO: 2024-11-15 16:54:27,891: llmtf.base.darumeru/ruOpenBookQA: Processing Dataset: 26.27s
+INFO: 2024-11-15 16:54:27,892: llmtf.base.darumeru/ruOpenBookQA: Results for darumeru/ruOpenBookQA:
+INFO: 2024-11-15 16:54:27,903: llmtf.base.darumeru/ruOpenBookQA: {'acc': 0.46134020618556704, 'f1_macro': 0.4607981854644543}
+INFO: 2024-11-15 16:54:27,909: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 16:54:27,910: llmtf.base.evaluator: 
+mean	darumeru/PARus	darumeru/ruOpenBookQA
+0.336	0.210	0.461
+INFO: 2024-11-15 16:54:36,808: llmtf.base.evaluator: Starting eval on ['darumeru/rwsd']
+INFO: 2024-11-15 16:54:36,809: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 16:54:36,809: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 16:54:41,755: llmtf.base.darumeru/RWSD: Loading Dataset: 4.95s
+INFO: 2024-11-15 16:54:44,248: llmtf.base.darumeru/RWSD: Processing Dataset: 2.49s
+INFO: 2024-11-15 16:54:44,248: llmtf.base.darumeru/RWSD: Results for darumeru/RWSD:
+INFO: 2024-11-15 16:54:44,248: llmtf.base.darumeru/RWSD: {'acc': 0.45098039215686275}
+INFO: 2024-11-15 16:54:44,249: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 16:54:44,250: llmtf.base.evaluator: 
+mean	darumeru/PARus	darumeru/RWSD	darumeru/ruOpenBookQA
+0.374	0.210	0.451	0.461
+INFO: 2024-11-15 16:54:52,912: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/rummlu']
+INFO: 2024-11-15 16:54:52,912: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 16:54:52,912: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 16:56:43,744: llmtf.base.nlpcoreteam/ruMMLU: Loading Dataset: 110.83s
+INFO: 2024-11-15 16:59:38,517: llmtf.base.nlpcoreteam/ruMMLU: Processing Dataset: 174.77s
+INFO: 2024-11-15 16:59:38,517: llmtf.base.nlpcoreteam/ruMMLU: Results for nlpcoreteam/ruMMLU:
+INFO: 2024-11-15 16:59:38,578: llmtf.base.nlpcoreteam/ruMMLU:                                        metric
+subject                                      
+abstract_algebra                     0.240000
+anatomy                              0.370370
+astronomy                            0.453947
+business_ethics                      0.350000
+clinical_knowledge                   0.475472
+college_biology                      0.340278
+college_chemistry                    0.250000
+college_computer_science             0.350000
+college_mathematics                  0.310000
+college_medicine                     0.427746
+college_physics                      0.274510
+computer_security                    0.540000
+conceptual_physics                   0.331915
+econometrics                         0.350877
+electrical_engineering               0.496552
+elementary_mathematics               0.357143
+formal_logic                         0.317460
+global_facts                         0.350000
+high_school_biology                  0.416129
+high_school_chemistry                0.438424
+high_school_computer_science         0.550000
+high_school_european_history         0.472727
+high_school_geography                0.484848
+high_school_government_and_politics  0.398964
+high_school_macroeconomics           0.325641
+high_school_mathematics              0.318519
+high_school_microeconomics           0.407563
+high_school_physics                  0.337748
+high_school_psychology               0.453211
+high_school_statistics               0.342593
+high_school_us_history               0.387255
+high_school_world_history            0.468354
+human_aging                          0.448430
+human_sexuality                      0.396947
+international_law                    0.661157
+jurisprudence                        0.490741
+logical_fallacies                    0.312883
+machine_learning                     0.339286
+management                           0.446602
+marketing                            0.615385
+medical_genetics                     0.390000
+miscellaneous                        0.441890
+moral_disputes                       0.419075
+moral_scenarios                      0.242458
+nutrition                            0.411765
+philosophy                           0.456592
+prehistory                           0.373457
+professional_accounting              0.336879
+professional_law                     0.314211
+professional_medicine                0.330882
+professional_psychology              0.364379
+public_relations                     0.463636
+security_studies                     0.395918
+sociology                            0.452736
+us_foreign_policy                    0.640000
+virology                             0.361446
+world_religions                      0.403509
+INFO: 2024-11-15 16:59:38,586: llmtf.base.nlpcoreteam/ruMMLU:                                    metric
+subject                                  
+STEM                             0.371502
+humanities                       0.409222
+other (business, health, misc.)  0.411205
+social sciences                  0.427893
+INFO: 2024-11-15 16:59:38,591: llmtf.base.nlpcoreteam/ruMMLU: {'acc': 0.4049555256540374}
+INFO: 2024-11-15 16:59:38,625: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 16:59:38,627: llmtf.base.evaluator: 
+mean	darumeru/PARus	darumeru/RWSD	darumeru/ruOpenBookQA	nlpcoreteam/ruMMLU
+0.382	0.210	0.451	0.461	0.405
+INFO: 2024-11-15 16:59:47,415: llmtf.base.evaluator: Starting eval on ['daru/treewayabstractive']
+INFO: 2024-11-15 16:59:47,416: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 16:59:47,416: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 16:59:50,756: llmtf.base.daru/treewayabstractive: Loading Dataset: 3.34s
+INFO: 2024-11-15 17:00:04,037: llmtf.base.darumeru/MultiQ: Processing Dataset: 375.13s
+INFO: 2024-11-15 17:00:04,037: llmtf.base.darumeru/MultiQ: Results for darumeru/MultiQ:
+INFO: 2024-11-15 17:00:04,038: llmtf.base.darumeru/MultiQ: {'f1': 0.2166827508040571, 'em': 0.11567877629063097}
+INFO: 2024-11-15 17:00:04,043: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 17:00:04,044: llmtf.base.evaluator: 
+mean	darumeru/MultiQ	darumeru/PARus	darumeru/RWSD	darumeru/ruOpenBookQA	nlpcoreteam/ruMMLU
+0.339	0.166	0.210	0.451	0.461	0.405
+INFO: 2024-11-15 17:00:12,617: llmtf.base.evaluator: Starting eval on ['darumeru/rcb']
+INFO: 2024-11-15 17:00:12,617: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 17:00:12,617: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 17:00:15,035: llmtf.base.darumeru/RCB: Loading Dataset: 2.42s
+INFO: 2024-11-15 17:00:17,696: llmtf.base.darumeru/RCB: Processing Dataset: 2.66s
+INFO: 2024-11-15 17:00:17,696: llmtf.base.darumeru/RCB: Results for darumeru/RCB:
+INFO: 2024-11-15 17:00:17,699: llmtf.base.darumeru/RCB: {'acc': 0.4681818181818182, 'f1_macro': 0.3981025874347421}
+INFO: 2024-11-15 17:00:17,700: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 17:00:17,701: llmtf.base.evaluator: 
+mean	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/ruOpenBookQA	nlpcoreteam/ruMMLU
+0.354	0.166	0.210	0.433	0.451	0.461	0.405
+INFO: 2024-11-15 17:00:26,448: llmtf.base.evaluator: Starting eval on ['darumeru/ruworldtree']
+INFO: 2024-11-15 17:00:26,448: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 17:00:26,448: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 17:00:28,717: llmtf.base.darumeru/ruWorldTree: Loading Dataset: 2.27s
+INFO: 2024-11-15 17:00:30,112: llmtf.base.darumeru/ruWorldTree: Processing Dataset: 1.39s
+INFO: 2024-11-15 17:00:30,112: llmtf.base.darumeru/ruWorldTree: Results for darumeru/ruWorldTree:
+INFO: 2024-11-15 17:00:30,116: llmtf.base.darumeru/ruWorldTree: {'acc': 0.5619047619047619, 'f1_macro': 0.5621556341232892}
+INFO: 2024-11-15 17:00:30,116: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 17:00:30,116: llmtf.base.evaluator: 
+mean	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/ruOpenBookQA	darumeru/ruWorldTree	nlpcoreteam/ruMMLU
+0.384	0.166	0.210	0.433	0.451	0.461	0.562	0.405
+INFO: 2024-11-15 17:00:38,826: llmtf.base.evaluator: Starting eval on ['daru/treewayextractive']
+INFO: 2024-11-15 17:00:38,826: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 17:00:38,826: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 17:00:51,532: llmtf.base.daru/treewayextractive: Loading Dataset: 12.71s
+INFO: 2024-11-15 17:02:39,091: llmtf.base.daru/treewayextractive: Processing Dataset: 107.56s
+INFO: 2024-11-15 17:02:39,091: llmtf.base.daru/treewayextractive: Results for daru/treewayextractive:
+INFO: 2024-11-15 17:02:39,318: llmtf.base.daru/treewayextractive: {'r-prec': 0.3703670274170274}
+INFO: 2024-11-15 17:02:39,357: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 17:02:39,359: llmtf.base.evaluator: 
+mean	daru/treewayextractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/ruOpenBookQA	darumeru/ruWorldTree	nlpcoreteam/ruMMLU
+0.382	0.370	0.166	0.210	0.433	0.451	0.461	0.562	0.405
+INFO: 2024-11-15 17:02:47,961: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/enmmlu']
+INFO: 2024-11-15 17:02:47,961: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 17:02:47,961: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 17:03:40,869: llmtf.base.daru/treewayabstractive: Processing Dataset: 230.11s
+INFO: 2024-11-15 17:03:40,869: llmtf.base.daru/treewayabstractive: Results for daru/treewayabstractive:
+INFO: 2024-11-15 17:03:40,870: llmtf.base.daru/treewayabstractive: {'rouge1': 0.30478241492489133, 'rouge2': 0.09260347651798656}
+INFO: 2024-11-15 17:03:40,872: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 17:03:40,872: llmtf.base.evaluator: 
+mean	daru/treewayabstractive	daru/treewayextractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/ruOpenBookQA	darumeru/ruWorldTree	nlpcoreteam/ruMMLU
+0.362	0.199	0.370	0.166	0.210	0.433	0.451	0.461	0.562	0.405
+INFO: 2024-11-15 17:04:33,322: llmtf.base.nlpcoreteam/enMMLU: Loading Dataset: 105.36s
+INFO: 2024-11-15 17:07:11,362: llmtf.base.nlpcoreteam/enMMLU: Processing Dataset: 158.04s
+INFO: 2024-11-15 17:07:11,362: llmtf.base.nlpcoreteam/enMMLU: Results for nlpcoreteam/enMMLU:
+INFO: 2024-11-15 17:07:11,425: llmtf.base.nlpcoreteam/enMMLU:                                        metric
+subject                                      
+abstract_algebra                     0.320000
+anatomy                              0.481481
+astronomy                            0.480263
+business_ethics                      0.470000
+clinical_knowledge                   0.573585
+college_biology                      0.506944
+college_chemistry                    0.310000
+college_computer_science             0.380000
+college_mathematics                  0.290000
+college_medicine                     0.485549
+college_physics                      0.303922
+computer_security                    0.640000
+conceptual_physics                   0.489362
+econometrics                         0.412281
+electrical_engineering               0.551724
+elementary_mathematics               0.402116
+formal_logic                         0.285714
+global_facts                         0.350000
+high_school_biology                  0.541935
+high_school_chemistry                0.453202
+high_school_computer_science         0.670000
+high_school_european_history         0.587879
+high_school_geography                0.621212
+high_school_government_and_politics  0.616580
+high_school_macroeconomics           0.443590
+high_school_mathematics              0.348148
+high_school_microeconomics           0.529412
+high_school_physics                  0.344371
+high_school_psychology               0.642202
+high_school_statistics               0.430556
+high_school_us_history               0.573529
+high_school_world_history            0.594937
+human_aging                          0.542601
+human_sexuality                      0.534351
+international_law                    0.619835
+jurisprudence                        0.555556
+logical_fallacies                    0.558282
+machine_learning                     0.366071
+management                           0.582524
+marketing                            0.782051
+medical_genetics                     0.430000
+miscellaneous                        0.579821
+moral_disputes                       0.546243
+moral_scenarios                      0.241341
+nutrition                            0.562092
+philosophy                           0.517685
+prehistory                           0.518519
+professional_accounting              0.414894
+professional_law                     0.365711
+professional_medicine                0.367647
+professional_psychology              0.446078
+public_relations                     0.536364
+security_studies                     0.538776
+sociology                            0.592040
+us_foreign_policy                    0.700000
+virology                             0.433735
+world_religions                      0.631579
+INFO: 2024-11-15 17:07:11,433: llmtf.base.nlpcoreteam/enMMLU:                                    metric
+subject                                  
+STEM                             0.434923
+humanities                       0.507447
+other (business, health, misc.)  0.503999
+social sciences                  0.551074
+INFO: 2024-11-15 17:07:11,438: llmtf.base.nlpcoreteam/enMMLU: {'acc': 0.4993605425093448}
+INFO: 2024-11-15 17:07:11,470: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 17:07:11,472: llmtf.base.evaluator: 
+mean	daru/treewayabstractive	daru/treewayextractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/ruOpenBookQA	darumeru/ruWorldTree	nlpcoreteam/enMMLU	nlpcoreteam/ruMMLU
+0.376	0.199	0.370	0.166	0.210	0.433	0.451	0.461	0.562	0.499	0.405
+INFO: 2024-11-15 17:07:20,297: llmtf.base.evaluator: Starting eval on ['darumeru/cp_para_ru']
+INFO: 2024-11-15 17:07:20,298: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
+INFO: 2024-11-15 17:07:20,298: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
+INFO: 2024-11-15 17:07:22,739: llmtf.base.darumeru/cp_para_ru: Loading Dataset: 2.44s
+INFO: 2024-11-15 17:10:45,613: llmtf.base.darumeru/cp_para_ru: Processing Dataset: 202.87s
+INFO: 2024-11-15 17:10:45,613: llmtf.base.darumeru/cp_para_ru: Results for darumeru/cp_para_ru:
+INFO: 2024-11-15 17:10:45,614: llmtf.base.darumeru/cp_para_ru: {'tokens_per_word': 1.8729616000663136, 'symbol_per_token': 4.043905520913176, 'len': 0.927490542336371, 'lcs': 0.05}
+INFO: 2024-11-15 17:10:45,615: llmtf.base.evaluator: Ended eval
+INFO: 2024-11-15 17:10:45,615: 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
+0.346	0.199	0.370	0.166	0.210	0.433	0.451	0.050	0.461	0.562	0.499	0.405

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
+0.346	0.199	0.370	0.166	0.210	0.433	0.451	0.050	0.461	0.562	0.499	0.405

llmtf_eval/nlpcoreteam_enMMLU.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52298c720ae44404dcba7cb6143416159debb8e355dc7172c1e63311828dbf94
+size 37102846

llmtf_eval/nlpcoreteam_enMMLU_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.4993605425093448
+    },
+    "leaderboard_result": 0.4993605425093448
+}

llmtf_eval/nlpcoreteam_ruMMLU.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b5734796e46be007a5a586c087505fd4666dde90cbf6b77ad7fd415e31ad43
+size 43042432

llmtf_eval/nlpcoreteam_ruMMLU_params.jsonl

@@ -0,0 +1,54 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/workdir/data/models/qwen/RuadaptQwen2.5-Coder-1.5B-instruct",
+        "generation_config": {
+            "bos_token_id": 145109,
+            "do_sample": true,
+            "eos_token_id": [
+                145111
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 145109,
+            "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",
+        "attn_implementation": "flash_attention_2",
+        "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": 0.4049555256540374
+    },
+    "leaderboard_result": 0.4049555256540374
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4065b3b145f19db165d8671457d8718273b84baa58f44e015d121baa65af422c
+size 3066626688

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:e03677792927c1ab6656bfc682845e327f47a996db955621143a6412b06c1908
+size 12298410

tokenizer_config.json

@@ -0,0 +1,375 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "145109": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145110": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145111": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145112": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145113": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145114": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145115": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145116": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145117": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145118": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145119": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145120": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145121": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145122": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145123": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145124": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145125": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145126": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145127": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145128": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145129": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145130": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145131": {
+      "content": "<|free_token1|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145132": {
+      "content": "<|free_token2|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145133": {
+      "content": "<|free_token3|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145134": {
+      "content": "<|free_token4|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145135": {
+      "content": "<|free_token5|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145136": {
+      "content": "<|free_token6|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145137": {
+      "content": "<|free_token7|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145138": {
+      "content": "<|free_token8|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145139": {
+      "content": "<|free_token9|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145140": {
+      "content": "<|free_token10|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145141": {
+      "content": "<|free_token11|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145142": {
+      "content": "<|free_token12|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145143": {
+      "content": "<|free_token13|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145144": {
+      "content": "<|free_token14|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145145": {
+      "content": "<|free_token15|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145146": {
+      "content": "<|free_token16|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145147": {
+      "content": "<|free_token17|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145148": {
+      "content": "<|free_token18|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145149": {
+      "content": "<|free_token19|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145150": {
+      "content": "<|free_token20|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145151": {
+      "content": "<|free_token21|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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
+}