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

Libraries

How to use cdomingoenrich/Llama-3.2-1B-random-weights with Transformers:

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

pipe = pipeline("text-generation", model="cdomingoenrich/Llama-3.2-1B-random-weights")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cdomingoenrich/Llama-3.2-1B-random-weights")
model = AutoModelForCausalLM.from_pretrained("cdomingoenrich/Llama-3.2-1B-random-weights")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cdomingoenrich/Llama-3.2-1B-random-weights with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cdomingoenrich/Llama-3.2-1B-random-weights"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cdomingoenrich/Llama-3.2-1B-random-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cdomingoenrich/Llama-3.2-1B-random-weights

SGLang

How to use cdomingoenrich/Llama-3.2-1B-random-weights 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 "cdomingoenrich/Llama-3.2-1B-random-weights" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cdomingoenrich/Llama-3.2-1B-random-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "cdomingoenrich/Llama-3.2-1B-random-weights" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cdomingoenrich/Llama-3.2-1B-random-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cdomingoenrich/Llama-3.2-1B-random-weights with Docker Model Runner:
```
docker model run hf.co/cdomingoenrich/Llama-3.2-1B-random-weights
```

cdomingoenrich/Llama-3.2-1B-random-weights

This repository contains randomly initialized weights for meta-llama/Llama-3.2-1B using the model's standard Hugging Face initialization (AutoModelForCausalLM.from_config(...)).

Source config/tokenizer: meta-llama/Llama-3.2-1B
Weights: random (not pretrained)
Created: 2026-02-10

This model is not expected to produce meaningful generations without training/fine-tuning.

Downloads last month: 5

Safetensors

Model size

1B params

Tensor type

BF16