Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

keyfan
/

grok-1-hf

Text Generation

Transformers

PyTorch

Grok

custom_code

Model card Files Files and versions

xet

Community

Instructions to use keyfan/grok-1-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use keyfan/grok-1-hf with Transformers:

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

pipe = pipeline("text-generation", model="keyfan/grok-1-hf", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("keyfan/grok-1-hf", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keyfan/grok-1-hf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/keyfan/grok-1-hf

SGLang

How to use keyfan/grok-1-hf 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 "keyfan/grok-1-hf" \
    --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": "keyfan/grok-1-hf",
		"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 "keyfan/grok-1-hf" \
        --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": "keyfan/grok-1-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use keyfan/grok-1-hf with Docker Model Runner:
```
docker model run hf.co/keyfan/grok-1-hf
```

[WIP] Fix float32 precision (multi-commit 6f4f3fee98ff848b483b84b692a4b03251126f470852d10f1205f6af709627e7)

by keyfan - opened Mar 21, 2024

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

-8

keyfan

Owner Mar 21, 2024

Fix float32 precision

Multi commit ID: 6f4f3fee98ff848b483b84b692a4b03251126f470852d10f1205f6af709627e7

Scheduled commits:

Upload 1 file(s) totalling 24.7G (86cab0a8dc9beabfc2590460e637cafbdde2797f98a93ba4322312101460a2db)
Upload 1 file(s) totalling 36.0G (d4ac5d8543bedbc5445a6c493044cd61cad18d1c451aceb8b449b9acfad0b1e8)
Upload 1 file(s) totalling 32.9G (e0a4aa6132c93847db4bc7e6002b5e6d96db3445d979d217990eb121f3c4cbf3)
Upload 1 file(s) totalling 36.0G (561f027a0f6f9cb29148cbfb1dd0b3ce44bc0bc24e8a851af371ee2b047ec380)
Upload 1 file(s) totalling 32.9G (ddbc6dda632fda5b2cdde9b9ca312d836f10a667212ea21b5aa56e5183c37c01)
Upload 1 file(s) totalling 36.0G (b49f5d759e26551d43a0b79b418e92b4cc6e8583b163ef0f2237165e65a98985)
Upload 1 file(s) totalling 32.9G (a4fa448c9aeb063bb8670105dbf23ae960b0ab8762ef4ef840ad28d7aff27ba9)
Upload 1 file(s) totalling 36.0G (9d248a30a85ea0edd3772a7a9a717a00b1b9f75e340c6436943968f147cf3c0f)
Upload 1 file(s) totalling 32.9G (556ff779a4abc6c952c62aa1db101b0332327927423642a708454b8776773fbf)
Upload 1 file(s) totalling 36.0G (ab7647cfc18216f9de5214534d068ab3f5390314173e6db165f0faaef3d985fc)
Upload 1 file(s) totalling 32.9G (44fa6b5fe2f64b32aacad72ff834c69b9881d7024af6162d36b72fe4d891a031)
Upload 1 file(s) totalling 36.0G (ee2f3c1bfd6904056f083b28b52e9604eac74eeeb6c15d36c9bb2cd9b805fe56)
Upload 1 file(s) totalling 32.9G (aa363dc369e6f20a0cd72da0a325cec9734ab2086d55ce41131f8d4cdda5b266)
Upload 1 file(s) totalling 36.0G (3ce57e796a94924a8f0444fb0e21170a8dabecd56576ed3d72c0907d5fca95a7)
Upload 1 file(s) totalling 32.9G (8508c1066f4ac614d743f559d9be854f6780e183bd2a31b98c7968204cbc7d35)
Upload 1 file(s) totalling 36.0G (fc41da00f4b758190bda3d67c8667ffefe73cbbcb44cb3c391d7247338d99781)
Upload 1 file(s) totalling 32.9G (63b370d5aee642b1f4f79c6531a5990df24142e16745d925e395af349681a3dc)
Upload 1 file(s) totalling 36.0G (050691e71b83ee89a907f28f6d3665d1b55f425db608bae55785b47fea5d2997)
Upload 1 file(s) totalling 19.7G (2b21be2c7236ccb78b9af4e66bade81430c7e2f7313acb25f2eaa0a06d29fcf9)
Upload 7 file(s) totalling 2.5M (4c09a04f32ca15464e5e15ea4d49a9325d4e4f7f65f9368fb26e13ce383b1108)

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.

keyfan changed pull request status to closed Mar 21, 2024

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

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs