Instructions to use jsbaicenter/Llama-3.2-1B-Instruct-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsbaicenter/Llama-3.2-1B-Instruct-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="jsbaicenter/Llama-3.2-1B-Instruct-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jsbaicenter/Llama-3.2-1B-Instruct-FP8")
model = AutoModelForCausalLM.from_pretrained("jsbaicenter/Llama-3.2-1B-Instruct-FP8")
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 jsbaicenter/Llama-3.2-1B-Instruct-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jsbaicenter/Llama-3.2-1B-Instruct-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jsbaicenter/Llama-3.2-1B-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jsbaicenter/Llama-3.2-1B-Instruct-FP8

SGLang

How to use jsbaicenter/Llama-3.2-1B-Instruct-FP8 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 "jsbaicenter/Llama-3.2-1B-Instruct-FP8" \
    --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": "jsbaicenter/Llama-3.2-1B-Instruct-FP8",
		"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 "jsbaicenter/Llama-3.2-1B-Instruct-FP8" \
        --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": "jsbaicenter/Llama-3.2-1B-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jsbaicenter/Llama-3.2-1B-Instruct-FP8 with Docker Model Runner:
```
docker model run hf.co/jsbaicenter/Llama-3.2-1B-Instruct-FP8
```

Llama-3.2-1B-Instruct-FP8-Dynamic

FP8 dynamic quantization pipeline for Llama-3.2-1B-Instruct using llm_compressor.

Overview

This repository demonstrates how to apply FP8 dynamic quantization to the Llama-3.2-1B-Instruct model.
The goal is to reduce memory usage and improve inference efficiency while maintaining strong performance for text generation and instruction-following tasks.

⚠️ This is a quantization pipeline, not a pre-quantized checkpoint.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from llmcompressor.transformers import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier

# Define the model ID for the model you want to quantize
MODEL_ID = "meta-llama/Llama-3.2-1B-Instruct"

# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, device_map="auto", torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)

# Configure the quantization recipe
recipe = QuantizationModifier(targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"])

# Apply the quantization algorithm
oneshot(model=model, recipe=recipe)

# Define the directory to save the quantized model
SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"

# Save the quantized model and tokenizer
model.save_pretrained(SAVE_DIR)
tokenizer.save_pretrained(SAVE_DIR)

print(f"Quantized model saved to (SAVE_DIR)")

Downloads last month: 5

Safetensors

Model size

1B params

Tensor type

BF16

F8_E4M3

Model tree for jsbaicenter/Llama-3.2-1B-Instruct-FP8

Base model

meta-llama/Llama-3.2-1B-Instruct

Quantized

(373)

this model

Collection including jsbaicenter/Llama-3.2-1B-Instruct-FP8

Quantized LLama-based Models

Collection

llama based models quantized to various precisions • 6 items • Updated Mar 18