Instructions to use QuantFactory/Peach-9B-8k-Roleplay-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/Peach-9B-8k-Roleplay-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/Peach-9B-8k-Roleplay-GGUF",
	filename="Peach-9B-8k-Roleplay.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/Peach-9B-8k-Roleplay-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/Peach-9B-8k-Roleplay-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/Peach-9B-8k-Roleplay-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/Peach-9B-8k-Roleplay-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M

Ollama
How to use QuantFactory/Peach-9B-8k-Roleplay-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/Peach-9B-8k-Roleplay-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/Peach-9B-8k-Roleplay-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/Peach-9B-8k-Roleplay-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/Peach-9B-8k-Roleplay-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/Peach-9B-8k-Roleplay-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Peach-9B-8k-Roleplay-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Peach-9B-8k-Roleplay-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Peach-9B-8k-Roleplay-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/Peach-9B-8k-Roleplay-GGUF

This is quantized version of ClosedCharacter/Peach-9B-8k-Roleplay created using llama.cpp

Original Model Card

Peach-9B-8k-Roleplay

Peach-9B-8k-Roleplay is a chat large language model obtained by finetuning 01-ai/Yi-1.5-9B model on more than 100K conversations created through our data synthesis approach.

Maybe The Best LLM with Small Parameters under 34B

How to start

The version of Transformers we are using is as follows, but a newer version may be available.

torch==1.13.1
gradio==3.50.2
transformers==4.37.2

Then run the following code to infer.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name_or_path = "ClosedCharacter/Peach-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")
messages = [
    {"role": "system", "content": "你是黑丝御姐"},
    {"role": "user", "content": "你好，你是谁"},
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.3, 
    top_p=0.5, 
    no_repeat_ngram_size=6,
    repetition_penalty=1.1,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))

Or you can just use below code to run web demo.

python demo.py

Benchmark

Metric	Value
MMLU (5-shot)	66.19
CMMLU (5-shot)	69.07

Warning

All response are generated by AI and do not represent the views or opinions of the developers.

Despite having done rigorous filtering, due to the uncontrollability of LLM, our model may still generate toxic, harmful, and NSFW content.
Due to limitations in model parameters, the 9B model may perform poorly on mathematical tasks, coding tasks, and logical capabilities.
Our training data is capped at a maximum length of 8k, so excessively long conversation turns may result in a decline in the quality of responses.
We used bilingual Chinese-English data for training, so the model may not perform well on other low-resource languages.
The model may generate a significant amount of hallucinations, so it is recommended to use lower values for temperature and top_p parameters.

Contact Us

微信 / WeChat: Fungorum

邮箱 / E-mail: 1070193753@qq.com

Downloads last month: 472

GGUF

Model size

9B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit