102 lines
4.0 KiB
Markdown
102 lines
4.0 KiB
Markdown
---
|
|
license: apache-2.0
|
|
license_link: https://huggingface.co/LL-Square/LLSquare-7B-Instruct
|
|
language:
|
|
- en
|
|
pipeline_tag: text-generation
|
|
base_model: LL-Square/LLSquare-7B-Instruct-7B
|
|
tags:
|
|
- chat
|
|
library_name: transformers
|
|
---
|
|
|
|
# LLSquare-7B-Instruct
|
|
<a href="https://llsquare.vercel.app" target="_blank" style="margin: 2px;">
|
|
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20LLSquare%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
|
|
</a>
|
|
|
|
## Introduction
|
|
|
|
LLSquare-7B-Instruct is the base model of LL-Square large language models. For LLSquare-7B-Instruct, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. LLSquare-7B-Instruct brings the following improvements upon LL-Square2:
|
|
|
|
- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
|
|
- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
|
|
- **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
|
|
- **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
|
|
|
|
**This repo contains the instruction-tuned 7B LLSquare-7B-Instruct model**, which has the following features:
|
|
- Type: Causal Language Models
|
|
- Training Stage: Pretraining & Post-training
|
|
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
|
|
- Number of Parameters: 7.61B
|
|
- Number of Paramaters (Non-Embedding): 6.53B
|
|
- Number of Layers: 28
|
|
- Number of Attention Heads (GQA): 28 for Q and 4 for KV
|
|
- Context Length: Full 131,072 tokens and generation 8192 tokens
|
|
- Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy LLSquare-7B-Instruct for handling long texts.
|
|
|
|
|
|
## Requirements
|
|
|
|
The code of LLSquare-7B-Instruct has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
|
|
|
|
With `transformers<4.37.0`, you will encounter the following error:
|
|
```
|
|
KeyError: 'LL-Square2'
|
|
```
|
|
|
|
## Quickstart
|
|
|
|
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model_name = "LL-Square/LLSquare-7B-Instruct-7B-Instruct"
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
model_name,
|
|
torch_dtype="auto",
|
|
device_map="auto"
|
|
)
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
|
|
prompt = "Give me a short introduction to large language model."
|
|
messages = [
|
|
{"role": "system", "content": "You are LL-Square, created by Alibaba Cloud. You are a helpful assistant."},
|
|
{"role": "user", "content": prompt}
|
|
]
|
|
text = tokenizer.apply_chat_template(
|
|
messages,
|
|
tokenize=False,
|
|
add_generation_prompt=True
|
|
)
|
|
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
|
|
|
generated_ids = model.generate(
|
|
**model_inputs,
|
|
max_new_tokens=512
|
|
)
|
|
generated_ids = [
|
|
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
|
]
|
|
|
|
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
|
```
|
|
|
|
### Processing Long Texts
|
|
|
|
The current `config.json` is set for context length up to 32,768 tokens.
|
|
To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
|
|
|
|
For supported frameworks, you could add the following to `config.json` to enable YaRN:
|
|
```json
|
|
{
|
|
...,
|
|
"rope_scaling": {
|
|
"factor": 4.0,
|
|
"original_max_position_embeddings": 32768,
|
|
"type": "yarn"
|
|
}
|
|
}
|
|
``` |