Edit model card


πŸ“‘ arXiv | πŸ‘» GitHub | πŸ€— HuggingFace-MiniMA | πŸ€— HuggingFace-MiniChat | πŸ€— HuggingFace-MiniChat-1.5 | πŸ€– ModelScope-MiniMA | πŸ€– ModelScope-MiniChat

πŸ†• Updates from MiniChat-3B:

  • better data mixture;
  • use of NEFTune;
  • use of DPO.

❗ Must comply with LICENSE of LLaMA2 since it is derived from LLaMA2.

A language model distilled and finetuned from an adapted version of LLaMA2-7B following "Towards the Law of Capacity Gap in Distilling Language Models".

Outperforming a wide range of 3B competitors in GPT4 evaluation and even competing with several 7B chat models.


The following is an example code snippet to use MiniChat-3B:

import torch

from transformers import AutoModelForCausalLM, AutoTokenizer

from conversation import get_default_conv_template

# MiniChat
tokenizer = AutoTokenizer.from_pretrained("GeneZC/MiniChat-3B", use_fast=False)
# GPU.
model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniChat-3B", use_cache=True, device_map="auto", torch_dtype=torch.float16).eval()
# CPU.
# model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniChat-3B", use_cache=True, device_map="cpu", torch_dtype=torch.float16).eval()

conv = get_default_conv_template("minichat")

question = "Implement a program to find the common elements in two arrays without using any extra data structures."
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer([prompt]).input_ids
output_ids = model.generate(
output_ids = output_ids[0][len(input_ids[0]):]
output = tokenizer.decode(output_ids, skip_special_tokens=True).strip()
# output: "def common_elements(arr1, arr2):\n    if len(arr1) == 0:\n        return []\n    if len(arr2) == 0:\n        return arr1\n\n    common_elements = []\n    for element in arr1:\n        if element in arr2:\n            common_elements.append(element)\n\n    return common_elements"
# Multiturn conversation could be realized by continuously appending questions to `conv`.


    title={Towards the Law of Capacity Gap in Distilling Language Models},
    author={Zhang, Chen and Song, Dawei and Ye, Zheyu and Gao, Yan},

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 50.23
AI2 Reasoning Challenge (25-Shot) 46.50
HellaSwag (10-Shot) 68.28
MMLU (5-Shot) 46.67
TruthfulQA (0-shot) 50.71
Winogrande (5-shot) 65.04
GSM8k (5-shot) 24.18
Downloads last month
Model size
3.02B params
Tensor type

Spaces using GeneZC/MiniChat-1.5-3B 2

Evaluation results