---
license: mit
datasets:
- wenbopan/Fusang-v1
- wenbopan/OpenOrca-zh-20k
language:
- zh
- en
---

![image/webp](https://cdn-uploads.huggingface.co/production/uploads/62cd3a3691d27e60db0698b0/s21sMRxRT56c5t4M15GBP.webp)

**The Faro chat model focuses on practicality and long-context modeling. It handles various downstream tasks with higher quality, delivering stable and reliable results even when inputs contain lengthy documents or complex instructions. Faro seamlessly works in both English and Chinese.**

# Faro-Yi-34B-200K
Faro-Yi-34B-200K is an improved [Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K) with extensive instruction tuning on [Fusang-V1](https://huggingface.co/datasets/wenbopan/Fusang-v1). Compared to Yi-34B-200K, Faro-Yi-34B-200K has gained greater capability in various downstream tasks and long-context modeling thanks to the large-scale synthetic data in Fusang-V1.

## How to Use

Faro-Yi-34B-200K uses chatml template. This make it easy to set up system prompt and multi-turn conversations. It truly excels when used for analyzing long documents or instructions. I recommend using vLLM for long inputs.

```python
import io
import requests
from PyPDF2 import PdfReader
from vllm import LLM, SamplingParams

llm = LLM(model="wenbopan/Faro-Yi-34B-200K")

pdf_data = io.BytesIO(requests.get("https://arxiv.org/pdf/2303.08774.pdf").content)
document = "".join(page.extract_text() for page in PdfReader(pdf_data).pages) # 100 pages

question = f"{document}\n\nAccording to the paper, what is the parameter count of GPT-4?"
messages = [ {"role": "user", "content": question} ] # 83K tokens
prompt = llm.get_tokenizer().apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
output = llm.generate(prompt, SamplingParams(temperature=0.8, max_tokens=500))
print(output[0].outputs[0].text)
# Yi-9B-200K:      175B. GPT-4 has 175B \nparameters. How many models were combined to create GPT-4? Answer: 6. ...
# Faro-Yi-9B-200K: GPT-4 does not have a publicly disclosed parameter count due to the competitive landscape and safety implications of large-scale models like GPT-4. ...
```

<details> <summary>Or With Transformers</summary>

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('wenbopan/Faro-Yi-34B-200K', device_map="cuda")
tokenizer = AutoTokenizer.from_pretrained('wenbopan/Faro-Yi-34B-200K')
messages = [
    {"role": "system", "content": "You are a helpful assistant. Always answer with a short response."},
    {"role": "user", "content": "Tell me what is Pythagorean theorem like you are a pirate."}
]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
generated_ids = model.generate(input_ids, max_new_tokens=512, temperature=0.5)
response = tokenizer.decode(generated_ids[0], skip_special_tokens=True) # Aye, matey! The Pythagorean theorem is a nautical rule that helps us find the length of the third side of a triangle. ...
```

</details>