Instructions to use RochatAI/llama3-8B-cn-rochat-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RochatAI/llama3-8B-cn-rochat-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RochatAI/llama3-8B-cn-rochat-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RochatAI/llama3-8B-cn-rochat-v1")
model = AutoModelForCausalLM.from_pretrained("RochatAI/llama3-8B-cn-rochat-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RochatAI/llama3-8B-cn-rochat-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RochatAI/llama3-8B-cn-rochat-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RochatAI/llama3-8B-cn-rochat-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RochatAI/llama3-8B-cn-rochat-v1

SGLang

How to use RochatAI/llama3-8B-cn-rochat-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RochatAI/llama3-8B-cn-rochat-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RochatAI/llama3-8B-cn-rochat-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RochatAI/llama3-8B-cn-rochat-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RochatAI/llama3-8B-cn-rochat-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RochatAI/llama3-8B-cn-rochat-v1 with Docker Model Runner:
```
docker model run hf.co/RochatAI/llama3-8B-cn-rochat-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

RochatAI/llama3-8B-cn-rochat-v1 is an instruction-tuned language model from hfl/llama-3-chinese-8b-instruct-v3, focused on tunning for Chinese role-playing.

We perform supervised fine-tuning with our in-house high-quality instruction-following chat datasets. Afterwards, we do two rounds DPO training for some special cases.

Contact Us

Twitter/X: Rochat_AI
Discord: Rochat

Usage

Recommend Samplers

temperature=0.98
top_p=0.37
top_k=100.0
repetition_penalty=1.18

Prompt Template

Llama-3-Instruct:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Basic Roleplay System Prompt

Enter RP mode. You shall reply to {{user}} while staying in character. Write at least 1 paragraph, up to 3, no more than 300 words. Your responses must be detailed, creative, immersive, and drive the scenario forward. You will follow {{character}}'s persona and personality.

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for RochatAI/llama3-8B-cn-rochat-v1

Quantizations

2 models