Instructions to use KaifengGGG/Llama3-8b-Hanscripter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KaifengGGG/Llama3-8b-Hanscripter with Transformers:

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

pipe = pipeline("text-generation", model="KaifengGGG/Llama3-8b-Hanscripter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KaifengGGG/Llama3-8b-Hanscripter")
model = AutoModelForCausalLM.from_pretrained("KaifengGGG/Llama3-8b-Hanscripter")
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 Settings

vLLM

How to use KaifengGGG/Llama3-8b-Hanscripter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KaifengGGG/Llama3-8b-Hanscripter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KaifengGGG/Llama3-8b-Hanscripter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KaifengGGG/Llama3-8b-Hanscripter

SGLang

How to use KaifengGGG/Llama3-8b-Hanscripter 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 "KaifengGGG/Llama3-8b-Hanscripter" \
    --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": "KaifengGGG/Llama3-8b-Hanscripter",
		"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 "KaifengGGG/Llama3-8b-Hanscripter" \
        --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": "KaifengGGG/Llama3-8b-Hanscripter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use KaifengGGG/Llama3-8b-Hanscripter with Docker Model Runner:
```
docker model run hf.co/KaifengGGG/Llama3-8b-Hanscripter
```

Model Summary

Hanscripter is an instruction-tuned language model focused on translation classical Chinese (i.e WenYanwen 文言文) to English. Our Github repo.

Base Model: Meta-Llama-3-8B-Instruct
SFT Dataset: KaifengGGG/WenYanWen_English_Parallel
Fine-tune Method: QLoRA

Version

Usage

Fine-tuning Details

Below are detailed descriptions of the various parameters and technologies used.

LoRA Parameters

lora_r: 64
lora_alpha: 16
lora_dropout: 0.1

Quantization

The model uses Bitsandbytes for state-of-the-art model quantization, enhancing computational efficiency:

use_4bit: True - Enables the use of 4-bit quantization.
bnb_4bit_compute_dtype: "float16" - The datatype used for computation in quantized state.
bnb_4bit_quant_type: "nf4" - Specifies the quantization type.
use_nested_quant: False - Nested quantization is not used.

Training Arguments

Settings for training the model are as follows:

num_train_epochs: 10
fp16: False
bf16: True - Optimized for use with A100 GPUs, employing Brain Floating Point (bf16).
per_device_train_batch_size: 2
per_device_eval_batch_size: 2
gradient_accumulation_steps: 4
gradient_checkpointing: True
max_grad_norm: 0.3
learning_rate: 0.0002
weight_decay: 0.001
optim: "paged_adamw_32bit"
lr_scheduler_type: "cosine"
max_steps: -1
warmup_ratio: 0.03
group_by_length: True

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

F32

KaifengGGG
/

Llama3-8b-Hanscripter