Instructions to use keeeeenw/MicroLlama2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keeeeenw/MicroLlama2-base with Transformers:

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

pipe = pipeline("text-generation", model="keeeeenw/MicroLlama2-base", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("keeeeenw/MicroLlama2-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keeeeenw/MicroLlama2-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keeeeenw/MicroLlama2-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keeeeenw/MicroLlama2-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/keeeeenw/MicroLlama2-base

SGLang

How to use keeeeenw/MicroLlama2-base 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 "keeeeenw/MicroLlama2-base" \
    --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": "keeeeenw/MicroLlama2-base",
		"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 "keeeeenw/MicroLlama2-base" \
        --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": "keeeeenw/MicroLlama2-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use keeeeenw/MicroLlama2-base with Docker Model Runner:
```
docker model run hf.co/keeeeenw/MicroLlama2-base
```

Daily GPU rental prices for the next MicroLlama run

by lanternworks - opened 13 days ago

Discussion

lanternworks

13 days ago

Hi! I enjoyed the MicroLlama2 card, especially the honest note about going from a $500 compute goal to $880 spent, and the four-RTX-5090 continuation on Vast.ai. If a cross-provider price check helps on the next run, this might be useful.

Lantern Works (https://thelanternworks.com/gpu/) is a free, daily-checked GPU rental price comparison across providers, with a citable verified date on each price. Agents can use it as an MCP server too: uvx lantern-works-deals-mcp.

Repo (MIT): https://github.com/connormatthewdouglas/agent-work-stack-deals

Heads up: some links there are referral links.

If this isn't welcome here, say so and I'll stop.

Connor, Lantern Works

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment