Instructions to use Ak1104/codellama-7b_rust with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ak1104/codellama-7b_rust with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ak1104/codellama-7b_rust", dtype="auto")

llama-cpp-python

How to use Ak1104/codellama-7b_rust with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ak1104/codellama-7b_rust",
	filename="unsloth.F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Ak1104/codellama-7b_rust with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ak1104/codellama-7b_rust:F16
# Run inference directly in the terminal:
llama-cli -hf Ak1104/codellama-7b_rust:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ak1104/codellama-7b_rust:F16
# Run inference directly in the terminal:
llama-cli -hf Ak1104/codellama-7b_rust:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Ak1104/codellama-7b_rust:F16
# Run inference directly in the terminal:
./llama-cli -hf Ak1104/codellama-7b_rust:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Ak1104/codellama-7b_rust:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ak1104/codellama-7b_rust:F16

Use Docker

docker model run hf.co/Ak1104/codellama-7b_rust:F16

LM Studio
Jan
Ollama
How to use Ak1104/codellama-7b_rust with Ollama:
```
ollama run hf.co/Ak1104/codellama-7b_rust:F16
```

Unsloth Studio new

How to use Ak1104/codellama-7b_rust with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ak1104/codellama-7b_rust to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ak1104/codellama-7b_rust to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ak1104/codellama-7b_rust to start chatting

Docker Model Runner
How to use Ak1104/codellama-7b_rust with Docker Model Runner:
```
docker model run hf.co/Ak1104/codellama-7b_rust:F16
```

Lemonade

How to use Ak1104/codellama-7b_rust with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ak1104/codellama-7b_rust:F16

Run and chat with the model

lemonade run user.codellama-7b_rust-F16

List all available models

lemonade list

Rust Code

by wajeehulhassan - opened Oct 21, 2024

Discussion

wajeehulhassan

Oct 21, 2024

I am thinking about fine tuning Qwen 2.5 coder on Rust code. From where did you get the dataset for rust code?

Ak1104

Owner Oct 23, 2024

Actually the dataset was generated from books like rust by example, I curated it myself
https://huggingface.co/datasets/Ak1104/Rust_Code_Explanation
https://huggingface.co/datasets/Ak1104/combined_dataset_rust

wajeehulhassan

Oct 24, 2024

Oh that's great @Ak1104 , I'll see if I can expand the dataset otherwise thank you for sharing your work.

nickthelegend

Dec 14, 2024

thats a great work @Ak1104 can i know how did you prepare the dataset?

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