Instructions to use parmanu-lcs2/Llama-3.1-6B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use parmanu-lcs2/Llama-3.1-6B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="parmanu-lcs2/Llama-3.1-6B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("parmanu-lcs2/Llama-3.1-6B-Instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("parmanu-lcs2/Llama-3.1-6B-Instruct", trust_remote_code=True, 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use parmanu-lcs2/Llama-3.1-6B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "parmanu-lcs2/Llama-3.1-6B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "parmanu-lcs2/Llama-3.1-6B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/parmanu-lcs2/Llama-3.1-6B-Instruct

SGLang

How to use parmanu-lcs2/Llama-3.1-6B-Instruct 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 "parmanu-lcs2/Llama-3.1-6B-Instruct" \
    --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": "parmanu-lcs2/Llama-3.1-6B-Instruct",
		"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 "parmanu-lcs2/Llama-3.1-6B-Instruct" \
        --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": "parmanu-lcs2/Llama-3.1-6B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use parmanu-lcs2/Llama-3.1-6B-Instruct with Docker Model Runner:
```
docker model run hf.co/parmanu-lcs2/Llama-3.1-6B-Instruct
```

parmanu-lcs2/Llama-3.1-6B-Instruct

This model is a pruned version of Meta-Llama-3.1-8B-Instruct, compressed using SNIPER (paper).

Pruning details

Setting	Value
Pruning method	SNIPER (paper)
Target compression ratio	25%
Parameters after pruning	6,030,118,912
Calibration data	slim_orca (50 samples × 512 tokens)

Recovery fine-tuning

LoRA fine-tuned on 2000 samples of SlimOrca after pruning. The LoRA adapters have been merged into the base weights.

Setting	Value
Epochs	1
Context length	1024
Learning rate	0.0002
LoRA rank / alpha	64 / 16
LoRA target modules	up_proj, gate_proj, down_proj, q_proj, o_proj, k_proj, v_proj

Hardware

All pruning and fine-tuning was performed on an NVIDIA A100 GPU.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("parmanu-lcs2/Llama-3.1-6B-Instruct", trust_remote_code=True, dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("parmanu-lcs2/Llama-3.1-6B-Instruct")

trust_remote_code=True is required because pruning leaves layers with different shapes (and some attention/MLP blocks removed). This architecture is defined in the bundled modeling_pruned.py.

References

Original model: Meta-Llama-3.1-8B-Instruct
SNIPER paper: https://arxiv.org/abs/2608.12953

Downloads last month: -

Safetensors

Model size

6B params

Tensor type

BF16

Dataset used to train parmanu-lcs2/Llama-3.1-6B-Instruct

Paper for parmanu-lcs2/Llama-3.1-6B-Instruct

Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization

Paper • 2608.12953 • Published Aug 13