---
base_model: GeneZC/MiniChat-3B
inference: false
language:
- en
- zh
library_name: transformers
license: apache-2.0
model_creator: GeneZC
model_name: MiniChat-3B
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
---
# GeneZC/MiniChat-3B-GGUF

Quantized GGUF model files for [MiniChat-3B](https://huggingface.co/GeneZC/MiniChat-3B) from [GeneZC](https://huggingface.co/GeneZC)


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [minichat-3b.q2_k.gguf](https://huggingface.co/afrideva/MiniChat-3B-GGUF/resolve/main/minichat-3b.q2_k.gguf) | q2_k | 1.30 GB  |
| [minichat-3b.q3_k_m.gguf](https://huggingface.co/afrideva/MiniChat-3B-GGUF/resolve/main/minichat-3b.q3_k_m.gguf) | q3_k_m | 1.51 GB  |
| [minichat-3b.q4_k_m.gguf](https://huggingface.co/afrideva/MiniChat-3B-GGUF/resolve/main/minichat-3b.q4_k_m.gguf) | q4_k_m | 1.85 GB  |
| [minichat-3b.q5_k_m.gguf](https://huggingface.co/afrideva/MiniChat-3B-GGUF/resolve/main/minichat-3b.q5_k_m.gguf) | q5_k_m | 2.15 GB  |
| [minichat-3b.q6_k.gguf](https://huggingface.co/afrideva/MiniChat-3B-GGUF/resolve/main/minichat-3b.q6_k.gguf) | q6_k | 2.48 GB  |
| [minichat-3b.q8_0.gguf](https://huggingface.co/afrideva/MiniChat-3B-GGUF/resolve/main/minichat-3b.q8_0.gguf) | q8_0 | 3.21 GB  |



## Original Model Card:
## MiniChat-3B

📑 [arXiv]() | 🤗 [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)

❗ 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.

<img src="./teaser_b.jpg" alt="teaser_b" width="687" />

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

```python
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(
    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: "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`.
```

## 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={}
}
```