Instructions to use Barkavi/LLAMA_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Barkavi/LLAMA_7B with Transformers:

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

pipe = pipeline("text-generation", model="Barkavi/LLAMA_7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Barkavi/LLAMA_7B")
model = AutoModelForCausalLM.from_pretrained("Barkavi/LLAMA_7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Barkavi/LLAMA_7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Barkavi/LLAMA_7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Barkavi/LLAMA_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Barkavi/LLAMA_7B

SGLang

How to use Barkavi/LLAMA_7B 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 "Barkavi/LLAMA_7B" \
    --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": "Barkavi/LLAMA_7B",
		"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 "Barkavi/LLAMA_7B" \
        --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": "Barkavi/LLAMA_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Barkavi/LLAMA_7B with Docker Model Runner:
```
docker model run hf.co/Barkavi/LLAMA_7B
```

[WIP] Upload folder using huggingface_hub (multi-commit 8a56b98d8ebcc4ccd340c86dd707bcdfe5e585a1dbeae68039b2bb36278baad8)

by Barkavi - opened Jul 11, 2023

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+225

-0

This PR is in draft mode

Barkavi

Owner Jul 11, 2023

•

edited Jul 11, 2023

Upload folder using huggingface_hub

Multi commit ID: 8a56b98d8ebcc4ccd340c86dd707bcdfe5e585a1dbeae68039b2bb36278baad8

Scheduled commits:

Upload 8 file(s) totalling 2.0G (45dabbef3bb35a60d9805d64c9cddea57424f02f542df29363019e6b34ae00ac)
Upload 5 file(s) totalling 2.1G (4e0b541d3b41923f26a973b9c5c2ac61a5ad3b57aba7495bce6c43f04670f58e)
Upload 5 file(s) totalling 2.0G (8a74c4cbccc44f0056ada6a000b3da44b8d44409bd999d1244bd34ceed178d77)
Upload 5 file(s) totalling 2.1G (4e62fbe231648b9f02f1eea299df5bf1851793f0b76544f2e96f92079fce5a45)
Upload 5 file(s) totalling 2.0G (41e60c3fd5fd7d2d239c1366406b63e561901f509e066024a4aa7bfb04359aa6)
Upload 5 file(s) totalling 2.1G (aa309ed869128e324640b22887d832e483963c3b021f276a5e7c847da37c523c)
Upload 5 file(s) totalling 2.0G (3f56d28a766f9b74ed4f19cf1067dc772d7baf3d1b4e9d4b174f70266bcd6092)
Upload 5 file(s) totalling 2.1G (3d5b4b63c0c44625b0e0fbbd31a085e8a6e24cb60cf5d3bc8190164f2bf2dca6)
Upload 5 file(s) totalling 2.0G (03a27ef155b6f64aabce938e289d4c86f855f299bd464f8d57bdab50163871be)
Upload 5 file(s) totalling 2.1G (da0b956e5ffe938104baa7c76bc68f2c97c5d3d9d1be1c0b8f334d7b77c930cb)
Upload 5 file(s) totalling 2.0G (3bb808d46227918a53cf0b351bdda6718095c0fc2fb8896a0af44953b62ae95a)
Upload 5 file(s) totalling 2.1G (f34b5c80497ac2e5c6dd38fe230cf5f7c0bb6c1ced919ed2f377cbba587164ca)
Upload 5 file(s) totalling 2.0G (2ce2ed3ed937317e80af0891e3d6cea48ff34aa277ac2befdc80d40d6ed7c890)
Upload 1 file(s) totalling 27.0G (16ba851d327d092a65dae56594cfeec36da9e8b6cd69bcc7f0771efba6ed1624)
Upload 7 file(s) totalling 707.1M (128ba394fdd8595ea12c450a9aa750700f4975804903755e1d9d980eb2bbe0d2)

This is a PR opened using the huggingface_hub library in the context of a multi-commit. PR can be commented as a usual PR. However, please be aware that manually updating the PR description, changing the PR status, or pushing new commits, is not recommended as it might corrupt the commit process. Learn more about multi-commits in this guide.