Instructions to use heegyu/llama-small-randomweights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use heegyu/llama-small-randomweights with Transformers:

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

pipe = pipeline("text-generation", model="heegyu/llama-small-randomweights")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("heegyu/llama-small-randomweights")
model = AutoModelForCausalLM.from_pretrained("heegyu/llama-small-randomweights")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use heegyu/llama-small-randomweights with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/heegyu/llama-small-randomweights

SGLang

How to use heegyu/llama-small-randomweights 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 "heegyu/llama-small-randomweights" \
    --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": "heegyu/llama-small-randomweights",
		"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 "heegyu/llama-small-randomweights" \
        --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": "heegyu/llama-small-randomweights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use heegyu/llama-small-randomweights with Docker Model Runner:
```
docker model run hf.co/heegyu/llama-small-randomweights
```

This is 82M parameters llama model of random weights. This model can be use for proof of concept.
Tokenizer is copy of meta-llama/Llama-2-7b

# Use a pipeline as a high-level helper
from transformers import LlamaConfig, LlamaForCausalLM, LlamaTokenizer
import numpy as np

config = LlamaConfig(vocab_size=32000, hidden_size=768, intermediate_size=768*4, num_hidden_layers=4, num_attention_heads=8)
tokenizer = LlamaTokenizer.from_pretrained("meta-llama/Llama-2-7b")
model = LlamaForCausalLM(config).half()
model_parameters = filter(lambda p: p.requires_grad, model.parameters())
params = sum([np.prod(p.size()) for p in model_parameters])
print(params / 1024 / 1024) # 82.881591796875

hub_id = "heegyu/llama-small-randomweights"
tokenizer.push_to_hub(hub_id)
model.push_to_hub(hub_id)

Downloads last month: 4