---
language:
- zh
- en
pipeline_tag: text-generation
license: other
license_name: llama3
license_link: LICENSE
tags:
- llama3
- chinese
- meta
---


# llama-3-8b-instruct-262k-chinese-lora


llama-3-8b-instruct-262k-chinese基于[Llama-3-8B-Instruct-262k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k)，使用ORPO方法，在中英文偏好数据集[shibing624/DPO-En-Zh-20k-Preference](https://huggingface.co/datasets/shibing624/DPO-En-Zh-20k-Preference)
上微调得到的对话模型。

模型的部署、训练等方法详见MedicalGPT的GitHub仓库：[https://github.com/shibing624/MedicalGPT](https://github.com/shibing624/MedicalGPT)
## Relate models
- 完整模型权重：https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese
- lora权重：https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese-lora
## 如何使用

```python
import transformers
import torch

model_id = "shibing624/llama-3-8b-instruct-262k-chinese"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.float16},
    device="cuda",
)

messages = [{"role": "system", "content": ""}]
messages.append({"role": "user", "content": "介绍一下机器学习"})
prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
    )
terminators = [
        pipeline.tokenizer.eos_token_id,
        pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
    ]
outputs = pipeline(
    prompt,
    max_new_tokens=512,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9
)
content = outputs[0]["generated_text"][len(prompt):]
print(content)
```


## About Llama-3-8B-Instruct-262k
Gradient incorporates your data to deploy autonomous assistants that power critical operations across your business. To learn more or collaborate on a custom model.

This model extends LLama-3 8B's context length from 8k to -> 160K, developed by Gradient, sponsored by compute from [Crusoe Energy](https://huggingface.co/crusoeai). It demonstrates that SOTA LLMs can learn to operate on long context with minimal training (< 200M tokens) by appropriately adjusting RoPE theta. 

<img src="https://cdn-uploads.huggingface.co/production/uploads/6585dc9be92bc5f258156bd6/hiHWva3CbsrnPvZTp5-lu.png" width="600">

**Approach:**

- [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as the base
- NTK-aware interpolation [1] to initialize an optimal schedule for RoPE theta, followed by a new data-driven RoPE theta optimization technique
- Progressive training on increasing context lengths similar to the [Large World Model](https://huggingface.co/LargeWorldModel) [2] (See details below)

**Infra:**

We build on top of the EasyContext Blockwise RingAttention library [3] to scalably and efficiently train on contexts up to 262144 tokens on [Crusoe Energy](https://huggingface.co/crusoeai) high performance L40S cluster. 

**Data:**

For training data, we generate long contexts by augmenting [SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B).

**Progressive Training Details:**

| Parameter                   | 65K            | 262K       |
|-----------------------------|----------------|------------|
| Initialize From             | LLaMA-3-8B-Inst| 65K        |
| Sequence Length             | 2^16           | 2^18       |
| RoPE theta                  | 15.3 M         | 207.1 M    |
| Batch Size (Tokens / Step)  | 2.097 M        | 4.192 M    |
| Steps                       | 30             | 24         |
| Total Tokens                | 63 M           | 101 M      |
| Learning Rate               | 2.00E-05       | 2.00E-05   |
| # GPUs                      | 32             | 32         |
| GPU Type                    | NVIDIA L40S    | NVIDIA L40S|