commit 201024fde5a5ddb376682ae2a9d8213127e54b57 Author: ModelHub XC Date: Wed May 6 09:48:44 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MTSAIR/Cotype-Nano-4bit Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..50e4376 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +vocab.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Apache License MTS AI.docx b/Apache License MTS AI.docx new file mode 100644 index 0000000..e57046a Binary files /dev/null and b/Apache License MTS AI.docx differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..a6399c2 --- /dev/null +++ b/README.md @@ -0,0 +1,113 @@ +--- +library_name: transformers +language: +- ru +- en +pipeline_tag: text-generation +license: other +license_name: apache-2.0 +license_link: https://huggingface.co/MTSAIR/Cotype-Nano-4bit/blob/main/Apache%20License%20MTS%20AI.docx +--- + +# Cotype-Nano-4bit🤖 + +Cotype-Nano-4bit – это LLM, которая весит меньше и работает быстрее чем Cotype-Nano, при этом сохраняя свои языковые способности + +Cotype-Nano-4bit is an LLM that is lighter and runs faster than Cotype-Nano, while maintaining its language capabilities. + +### Inference with vLLM +``` +python3 -m vllm.entrypoints.openai.api_server --model MTSAIR/Cotype-Nano-4bit --port 8000 +``` + +### Recommended generation parameters and system prompt +```python +import openai +import pandas as pd +from tqdm import tqdm + +openai.api_key = 'xxx' + +endpoint = 'http://localhost:8000/v1' +model = 'MTSAIR/Cotype-Nano-4bit' +openai.api_base = endpoint + +response = openai.ChatCompletion.create( + model=model, + temperature=0.0, # также допускается 0.2 + frequency_penalty=0.0, + max_tokens=2048, + top_p=0.1, # также допускается 0.9 + messages=[ + {"role": "system", "content": "Ты — ИИ-помощник. Тебе дано задание: необходимо сгенерировать подробный и развернутый ответ."}, + {"role": "user", "content": "Расскажи мне про ИИ, коротко"} + ] + ) + +answer = response["choices"][0]["message"]["content"] +print(answer) +``` + +### Inference with Huggingface +```python +from transformers import pipeline + +pipe = pipeline("text-generation", model="MTSAIR/Cotype-Nano-4bit", device="cuda") + +messages = [ + {"role": "system", "content": "Ты — ИИ-помощник. Тебе дано задание: необходимо сгенерировать подробный и развернутый ответ."}, + {"role": "user", "content": "Расскажи мне про ИИ"}, +] + +res = pipe(messages, max_length=1024) +print(res[0]['generated_text'][1]) +``` + + +## Example request + +**Request:** + + +#### Cotype-Nano-4bit response: + +> **Рекламный текст для магазина экологичной одежды:** +> +> --- +> +> **Заботьтесь о Земле, одевайтесь с умом!** +> +> Приглашаем вас в мир экологичной моды! Мы предлагаем вам не только стильные и качественные вещи, но и возможность сделать свой выбор в пользу устойчивого развития и сохранения природы. +> +> **Экологичная одежда – ваш выбор!** +> +> 1. **Создание гармонии с природой.** Мы используем только экологически чистые материалы, которые не наносят вреда окружающей среде. +> 2. **Минимализм в стиле.** Наша одежда – это не просто предметы гардероба, это стиль, который подчеркивает вашу индивидуальность. +> 3. **Продолжительный срок службы.** Мы создаем вещи, которые прослужат вам долго, что позволяет избежать ненужного потребления и отходов. +> 4. **Поддержка местных производителей.** Мы выбираем местных мастеров и производителей, что способствует созданию рабочих мест и поддерживает местную экономику. +> 5. **Возвращаем вещи в круговорот.** Мы предлагаем программы по возврату и переработке одежды, чтобы вы могли внести свой вклад в сохранение экологии. +> +> **Ваш выбор – ваша ответственность.** +> +> Выбирайте экологичную одежду, и помните, что ваш выбор влияет на будущее нашей планеты. Давайте вместе создадим гармонию между человеком, его потребностями и природой. +> +> **Приходите в наш магазин, чтобы стать частью экологической моды!** +> +> --- +> +>Мы уверены, что вы найдете в нашем ассортименте не только стильные вещи, но и уверенность в том, что ваш выбор в пользу устойчивости и экологии не будет лишним. Приходите и посмотрите, как можно сочетать моду с ответственностью! + +### Results on ru-llm-arena: 22.5 (local measurement) + +| Model | Score | 95% CI | Avg. #Tokens | +|---------------------------------------------|-------|-------------------------|---------------| +| **Cotype-Nano-4bit** | **22.5** | **+2.1 / -1.4** | **582** | +| storm-7b | 20.62 | +1.4 / -1.6 | 419.32 | +| neural-chat-7b-v3-3 | 19.04 | +1.8 / -1.5 | 927.21 | +| Vikhrmodels-Vikhr-Llama-3.2-1B-instruct | 19.04 | +1.2 / -1.5 | 958.63 | +| gigachat_lite | 17.2 | +1.5 / -1.5 | 276.81 | +| Vikhrmodels-Vikhr-Qwen-2.5-0.5b-Instruct | 16.5 | +1.5 / -1.7 | 583.5 | +| Qwen-Qwen2.5-1.5B-Instruct | 16.46 | +1.3 / -1.3 | 483.67 | +| Vikhrmodels-vikhr-qwen-1.5b-it | 13.19 | +1.3 / -1.1 | 2495.38 | +| meta-llama-Llama-3.2-1B-Instruct | 4.04 | +0.6 / -0.8 | 1240.53 | +| Qwen-Qwen2.5-0.5B-Instruct | 4.02 | +0.7 / -0.8 | 829.87 | \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..b3c76da --- /dev/null +++ b/config.json @@ -0,0 +1,42 @@ +{ + "_name_or_path": "", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "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, + "quantization_config": { + "backend": "autoawq", + "bits": 4, + "do_fuse": false, + "exllama_config": null, + "fuse_max_seq_len": null, + "group_size": 256, + "modules_to_fuse": null, + "modules_to_not_convert": null, + "quant_method": "awq", + "version": "gemm", + "zero_point": true + }, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "float16", + "transformers_version": "4.46.2", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c65b983 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.1, + "temperature": 0.2, + "top_k": 20, + "top_p": 0.9, + "transformers_version": "4.46.2" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..65674f3 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d914618341373065ed76012adea9d28cc6c43143874a7c93763c2ea5fb6d92d +size 1135011144 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "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|>" + ], + "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 + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..abdf789 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,207 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "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": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- '' }}\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 XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\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\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\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\\n' }}\n {{- message.content }}\n {{- '\\n' }}\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 +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833