Instructions to use sandmanbuzz/llama-3.1-8b-fix-json-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sandmanbuzz/llama-3.1-8b-fix-json-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sandmanbuzz/llama-3.1-8b-fix-json-gguf",
	filename="fix-json-full.Q3_K_L.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sandmanbuzz/llama-3.1-8b-fix-json-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M

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 sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M

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 sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M

Use Docker

docker model run hf.co/sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use sandmanbuzz/llama-3.1-8b-fix-json-gguf with Ollama:
```
ollama run hf.co/sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M
```

Unsloth Studio

How to use sandmanbuzz/llama-3.1-8b-fix-json-gguf 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 sandmanbuzz/llama-3.1-8b-fix-json-gguf 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 sandmanbuzz/llama-3.1-8b-fix-json-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sandmanbuzz/llama-3.1-8b-fix-json-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use sandmanbuzz/llama-3.1-8b-fix-json-gguf with Docker Model Runner:
```
docker model run hf.co/sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M
```

Lemonade

How to use sandmanbuzz/llama-3.1-8b-fix-json-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sandmanbuzz/llama-3.1-8b-fix-json-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llama-3.1-8b-fix-json-gguf-Q4_K_M

List all available models

lemonade list

These are basic-ass llama.cpp quants of the syntheticlab/fix-json lora on the actual base model.

Y'know, since you actually have to fuckin apply for access to the base model.

Have fun, y'all.

Downloads last month: 14

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for sandmanbuzz/llama-3.1-8b-fix-json-gguf

Base model

meta-llama/Llama-3.1-8B

Quantized

(325)

this model