Instructions to use resistz/sft_Llama-3.1-8B_ultra200k_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use resistz/sft_Llama-3.1-8B_ultra200k_lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("cache_dir/Llama-3.1-8B")
model = PeftModel.from_pretrained(base_model, "resistz/sft_Llama-3.1-8B_ultra200k_lora")

Transformers

How to use resistz/sft_Llama-3.1-8B_ultra200k_lora with Transformers:

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

pipe = pipeline("text-generation", model="resistz/sft_Llama-3.1-8B_ultra200k_lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("resistz/sft_Llama-3.1-8B_ultra200k_lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use resistz/sft_Llama-3.1-8B_ultra200k_lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "resistz/sft_Llama-3.1-8B_ultra200k_lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "resistz/sft_Llama-3.1-8B_ultra200k_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/resistz/sft_Llama-3.1-8B_ultra200k_lora

SGLang

How to use resistz/sft_Llama-3.1-8B_ultra200k_lora 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 "resistz/sft_Llama-3.1-8B_ultra200k_lora" \
    --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": "resistz/sft_Llama-3.1-8B_ultra200k_lora",
		"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 "resistz/sft_Llama-3.1-8B_ultra200k_lora" \
        --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": "resistz/sft_Llama-3.1-8B_ultra200k_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use resistz/sft_Llama-3.1-8B_ultra200k_lora with Docker Model Runner:
```
docker model run hf.co/resistz/sft_Llama-3.1-8B_ultra200k_lora
```

Model Card for sft_Llama-3.1-8B_ultra200k

This model is a fine-tuned version of None. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

PEFT 0.16.0
TRL: 0.19.1
Transformers: 4.54.0.dev0
Pytorch: 2.7.1+cu128
Datasets: 3.6.0
Tokenizers: 0.21.2

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 6

Collection including resistz/sft_Llama-3.1-8B_ultra200k_lora

SFT on UltraChat200K

Collection

Train one epoch SFT on UltraChat200K • 9 items • Updated Sep 30, 2025