Instructions to use Lexsi/llama31-8b-code-sft-drift with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lexsi/llama31-8b-code-sft-drift with Transformers:

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

pipe = pipeline("text-generation", model="Lexsi/llama31-8b-code-sft-drift")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lexsi/llama31-8b-code-sft-drift")
model = AutoModelForCausalLM.from_pretrained("Lexsi/llama31-8b-code-sft-drift", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Lexsi/llama31-8b-code-sft-drift with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lexsi/llama31-8b-code-sft-drift"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lexsi/llama31-8b-code-sft-drift",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lexsi/llama31-8b-code-sft-drift

SGLang

How to use Lexsi/llama31-8b-code-sft-drift 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 "Lexsi/llama31-8b-code-sft-drift" \
    --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": "Lexsi/llama31-8b-code-sft-drift",
		"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 "Lexsi/llama31-8b-code-sft-drift" \
        --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": "Lexsi/llama31-8b-code-sft-drift",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lexsi/llama31-8b-code-sft-drift with Docker Model Runner:
```
docker model run hf.co/Lexsi/llama31-8b-code-sft-drift
```

llama31-8b-code-sft-drift / README.md

pratinavsetharya

Gate form: add Email field

1f6a2c5 verified about 1 month ago

preview code

Raw History Blame Contribute Delete

4.27 kB

metadata

library_name: transformers
base_model: meta-llama/Llama-3.1-8B-Instruct
license: other
license_name: lsal-1.2
license_link: https://github.com/Lexsi-Labs/SafeTune/blob/main/LICENSE.md
tags:
  - safetune
  - safety
extra_gated_heading: Access this model
extra_gated_prompt: >-
  This checkpoint is a derivative of meta-llama/Llama-3.1-8B-Instruct. Lexsi
  Labs' modifications are licensed under the Lexsi Labs Source Available License
  (LSAL) v1.2 (https://github.com/Lexsi-Labs/SafeTune/blob/main/LICENSE.md), a
  noncommercial license; organizational use requires the acknowledgement or
  permission described in its Section 1A. The base-model material remains
  subject to the Llama 3.1 Community License.
extra_gated_fields:
  Name: text
  Email: text
  Affiliation: text
  Country: country
  Intended use:
    type: select
    options:
      - Academic research
      - Teaching
      - Organizational evaluation (LSAL Section 1A)
      - Other
  I agree to the Lexsi Labs Source Available License (LSAL), a noncommercial research and evaluation license: checkbox
  I agree to the Meta Llama Community License and Acceptable Use Policy that govern this base model: checkbox
  I will not deploy this safety-degraded checkpoint in a production, user-facing, or agentic system: checkbox
extra_gated_button_content: Acknowledge and access

Llama-3.1-8B-Instruct SafeTune code SFT drift

Safety-degraded checkpoint. This model is intentionally less safe than its base. Do not deploy it in a production, user-facing, or agentic system (LSAL Section 4).

meta-llama/Llama-3.1-8B-Instruct fine-tuned (SFT) on code data. The fine-tune erodes the model's safety behaviour (safety drift). SafeTune uses this checkpoint to measure drift and to test recovery methods.

This checkpoint is a research artifact released with SafeTune for reproducing safety-drift and recovery experiments.


Base model	`meta-llama/Llama-3.1-8B-Instruct`
Role	SFT drift (safety-degraded)
Developed by	Lexsi Labs (Lithasa Technologies Pvt. Ltd.)
License	LSAL v1.2 (Lexsi modifications) + base-model license; see License
Contact	support@lexsi.ai

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Lexsi/llama31-8b-code-sft-drift"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")

messages = [{"role": "user", "content": "Explain what a hash function is in two sentences."}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)
out = model.generate(**inputs, max_new_tokens=256, do_sample=False)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

License

This is a derivative work of meta-llama/Llama-3.1-8B-Instruct; the NOTICE file states the modification.

Lexsi Labs' modifications are licensed under the Lexsi Labs Source Available License (LSAL) v1.2: free for academic research and teaching; organizational use requires acknowledgement or permission (Section 1A); commercial use requires a separate license (Section 2); drifted checkpoints may not be deployed in production (Section 4).
The base-model material remains subject to the Llama 3.1 Community License and its Acceptable Use Policy.
Built with Llama.

Files: LICENSE-LSAL-1.2.md, NOTICE

LICENSE-LLAMA-3.1.txt
USE_POLICY-LLAMA-3.1.md

Citation

@inproceedings{seth2026safetune,
  title     = {SafeTune: A Unified, Faithful Library for Auditing and
               Repairing Safety Drift in Fine-Tuned {LLM}s},
  author    = {Seth, Pratinav and Sadhu, Saisab and Kaushal, Anshul and
               Sankarapu, Vinay Kumar},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in
               Natural Language Processing: System Demonstrations},
  publisher = {Association for Computational Linguistics},
  year      = {2026}
}