Instructions to use GPUburnout/GPUburnout-3B-75K-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GPUburnout/GPUburnout-3B-75K-Chat with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GPUburnout/GPUburnout-3B-75K-Chat",
	filename="GPUburnout-3B-75K-Chat-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use GPUburnout/GPUburnout-3B-75K-Chat with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf GPUburnout/GPUburnout-3B-75K-Chat: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 GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GPUburnout/GPUburnout-3B-75K-Chat: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 GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M

Use Docker

docker model run hf.co/GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M

LM Studio
Jan
Ollama
How to use GPUburnout/GPUburnout-3B-75K-Chat with Ollama:
```
ollama run hf.co/GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M
```

Unsloth Studio

How to use GPUburnout/GPUburnout-3B-75K-Chat 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 GPUburnout/GPUburnout-3B-75K-Chat 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 GPUburnout/GPUburnout-3B-75K-Chat to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GPUburnout/GPUburnout-3B-75K-Chat to start chatting

Docker Model Runner
How to use GPUburnout/GPUburnout-3B-75K-Chat with Docker Model Runner:
```
docker model run hf.co/GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M
```

Lemonade

How to use GPUburnout/GPUburnout-3B-75K-Chat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GPUburnout/GPUburnout-3B-75K-Chat:Q4_K_M

Run and chat with the model

lemonade run user.GPUburnout-3B-75K-Chat-Q4_K_M

List all available models

lemonade list

GPUburnout-3B-75K-Chat / tokenizer_config.json

GPUburnout

Upload folder using huggingface_hub

4532807 verified about 1 month ago

raw

history blame contribute delete

378 Bytes

	{
	"backend": "tokenizers",
	"bos_token": "<\|im_start\|>",
	"eos_token": "<\|im_end\|>",
	"additional_special_tokens": [
	"<\|endoftext\|>",
	"<\|system\|>",
	"<\|user\|>",
	"<\|assistant\|>"
	],
	"is_local": true,
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<\|pad\|>",
	"tokenizer_class": "PreTrainedTokenizerFast",
	"unk_token": "<\|unk\|>"
	}

	{
	"backend": "tokenizers",
	"bos_token": "<\|im_start\|>",
	"eos_token": "<\|im_end\|>",
	"additional_special_tokens": [
	"<\|endoftext\|>",
	"<\|system\|>",
	"<\|user\|>",
	"<\|assistant\|>"
	],
	"is_local": true,
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<\|pad\|>",
	"tokenizer_class": "PreTrainedTokenizerFast",
	"unk_token": "<\|unk\|>"
	}