commit e610186846f19ccfc6c69d52ca70f1114702cc59 Author: ModelHub XC Date: Mon May 11 17:35:40 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: GeneZC/MiniMA-2-3B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b4c4585 --- /dev/null +++ b/README.md @@ -0,0 +1,202 @@ +--- +language: +- en +- zh +license: apache-2.0 +library_name: transformers +datasets: +- EleutherAI/pile +- togethercomputer/RedPajama-Data-1T +- p208p2002/wudao +widget: +- text: 4 + 3 = +model-index: +- name: MiniMA-2-3B + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: AI2 Reasoning Challenge (25-Shot) + type: ai2_arc + config: ARC-Challenge + split: test + args: + num_few_shot: 25 + metrics: + - type: acc_norm + value: 44.71 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniMA-2-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: HellaSwag (10-Shot) + type: hellaswag + split: validation + args: + num_few_shot: 10 + metrics: + - type: acc_norm + value: 69.33 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniMA-2-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU (5-Shot) + type: cais/mmlu + config: all + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 41.22 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniMA-2-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: TruthfulQA (0-shot) + type: truthful_qa + config: multiple_choice + split: validation + args: + num_few_shot: 0 + metrics: + - type: mc2 + value: 38.44 + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniMA-2-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: Winogrande (5-shot) + type: winogrande + config: winogrande_xl + split: validation + args: + num_few_shot: 5 + metrics: + - type: acc + value: 66.69 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniMA-2-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GSM8k (5-shot) + type: gsm8k + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 8.11 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniMA-2-3B + name: Open LLM Leaderboard +--- + +## MiniMA-2-3B + +📑 [arXiv](https://arxiv.org/abs/2311.07052) | 👻 [GitHub](https://github.com/GeneZC/MiniMA) | 🤗 [HuggingFace-MiniMA](https://huggingface.co/GeneZC/MiniMA-3B) | 🤗 [HuggingFace-MiniChat](https://huggingface.co/GeneZC/MiniChat-3B) | 🤖 [ModelScope-MiniMA](https://modelscope.cn/models/GeneZC/MiniMA-3B) | 🤖 [ModelScope-MiniChat](https://modelscope.cn/models/GeneZC/MiniChat-3B) | 🤗 [HuggingFace-MiniChat-1.5](https://huggingface.co/GeneZC/MiniChat-1.5-3B) | 🤗 [HuggingFace-MiniMA-2](https://huggingface.co/GeneZC/MiniMA-2-3B) | 🤗 [HuggingFace-MiniChat-2](https://huggingface.co/GeneZC/MiniChat-2-3B) + +🆕 **Updates from MiniMA-3B**: +- continued from MiniMA-3B without distillation; +- better data mixture; +- more trained tokens. + +❗ Must comply with LICENSE of LLaMA-2 since it is derived from LLaMA-2. + +A language model continued from MiniMA-3B. + +Completing the compute-performance pareto frontier together with MiniMA-3B and other arts. + +teaser_a + +**Standard Benchmarks** + +|Method|TFLOPs|MMLU (5-shot)|CEval (5-shot)|DROP (3-shot)|HumanEval (0-shot)|BBH (3-shot)|GSM8K (8-shot)| +|--|--|--|--|--|--|--|--| +|Mamba-2.8B|4.6E9|25.58|24.74|15.72|7.32|29.37|3.49| +|ShearedLLaMA-2.7B|0.8E9|26.97|22.88|19.98|4.88|30.48|3.56| +|BTLM-3B|11.3E9|27.20|26.00|17.84|10.98|30.87|4.55| +|StableLM-3B|72.0E9|44.75|31.05|22.35|15.85|32.59|10.99| +|Qwen-1.8B|23.8E9|44.05|54.75|12.97|14.02|30.80|22.97| +|Phi-2-2.8B|159.9E9|56.74|34.03|30.74|46.95|44.13|55.42| +|LLaMA-2-7B|84.0E9|46.00|34.40|31.57|12.80|32.02|14.10| +|| +|MiniMA-3B|4.0E9|28.51|28.23|22.50|10.98|31.61|8.11| +|MiniChat-3B|4.0E9|38.40|36.48|22.58|18.29|31.36|29.72| +|MiniMA-2-3B|13.4E9|40.14|44.65|23.10|14.63|31.43|8.87| +|MiniChat-2-3B|13.4E9|46.17|43.91|30.26|22.56|34.95|38.13| + +The following is an example code snippet to use MiniMA-2-3B: + +```python +import torch + +from transformers import AutoModelForCausalLM, AutoTokenizer + +# MiniMA +tokenizer = AutoTokenizer.from_pretrained("GeneZC/MiniMA-2-3B", use_fast=False) +# GPU. +model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniMA-2-3B", use_cache=True, device_map="auto", torch_dtype=torch.float16).eval() +# CPU. +# model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniMA-2-3B", use_cache=True, device_map="cpu", torch_dtype=torch.float16).eval() + +prompt = "Question: Sherrie tells the truth. Vernell says Sherrie tells the truth. Alexis says Vernell lies. Michaela says Alexis tells the truth. Elanor says Michaela tells the truth. Does Elanor tell the truth?\nAnswer: No\n\nQuestion: Kristian lies. Sherrie says Kristian lies. Delbert says Sherrie lies. Jerry says Delbert tells the truth. Shalonda says Jerry tells the truth. Does Shalonda tell the truth?\nAnswer: No\n\nQuestion: Vina tells the truth. Helene says Vina lies. Kandi says Helene tells the truth. Jamey says Kandi lies. Ka says Jamey lies. Does Ka tell the truth?\nAnswer: No\n\nQuestion: Christie tells the truth. Ka says Christie tells the truth. Delbert says Ka lies. Leda says Delbert tells the truth. Lorine says Leda tells the truth. Does Lorine tell the truth?\nAnswer:" +input_ids = tokenizer([prompt]).input_ids +output_ids = model.generate( + torch.as_tensor(input_ids).cuda(), + do_sample=True, + temperature=0.7, + max_new_tokens=1024, +) +output_ids = output_ids[0][len(input_ids[0]):] +output = tokenizer.decode(output_ids, skip_special_tokens=True).strip() +# output: "No" +``` + +## Bibtex + +```bibtex +@article{zhang2023law, + title={Towards the Law of Capacity Gap in Distilling Language Models}, + author={Zhang, Chen and Song, Dawei and Ye, Zheyu and Gao, Yan}, + year={2023}, + url={https://arxiv.org/abs/2311.07052} +} +``` + +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_GeneZC__MiniMA-2-3B) + +| Metric |Value| +|---------------------------------|----:| +|Avg. |44.75| +|AI2 Reasoning Challenge (25-Shot)|44.71| +|HellaSwag (10-Shot) |69.33| +|MMLU (5-Shot) |41.22| +|TruthfulQA (0-shot) |38.44| +|Winogrande (5-shot) |66.69| +|GSM8k (5-shot) | 8.11| + diff --git a/config.json b/config.json new file mode 100644 index 0000000..88ca155 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "MiniMA-2-3B", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 24, + "num_key_value_heads": 24, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.33.2", + "use_cache": true, + "vocab_size": 49216 +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..6b8286f --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de852e3df7f57006b9e0d434c06ee16debbb11a64d3536dabea455aff876cd2 +size 6040916472 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..25b3116 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd986ed24085ae6ac0e030992d73344640fdaec08cb5110c8cd5b100dbd61d59 +size 6040944595 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/teaser_a.jpg b/teaser_a.jpg new file mode 100644 index 0000000..d6a608a Binary files /dev/null and b/teaser_a.jpg differ diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..14cb1e6 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae87c0db2b21b0fa3fdc5e19d1f9cea94efb703cc7c6281d8718a6714b3cc2be +size 748869 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c55a3f9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,37 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "legacy": null, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "use_default_system_prompt": true, + "use_fast": true +}