Instructions to use mgonzs13/TextBase-7B-v0.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mgonzs13/TextBase-7B-v0.1-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mgonzs13/TextBase-7B-v0.1-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 mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mgonzs13/TextBase-7B-v0.1-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 mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use mgonzs13/TextBase-7B-v0.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mgonzs13/TextBase-7B-v0.1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mgonzs13/TextBase-7B-v0.1-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M

Ollama
How to use mgonzs13/TextBase-7B-v0.1-GGUF with Ollama:
```
ollama run hf.co/mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M
```

Unsloth Studio

How to use mgonzs13/TextBase-7B-v0.1-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 mgonzs13/TextBase-7B-v0.1-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 mgonzs13/TextBase-7B-v0.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mgonzs13/TextBase-7B-v0.1-GGUF to start chatting

Docker Model Runner
How to use mgonzs13/TextBase-7B-v0.1-GGUF with Docker Model Runner:
```
docker model run hf.co/mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M
```

Lemonade

How to use mgonzs13/TextBase-7B-v0.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mgonzs13/TextBase-7B-v0.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TextBase-7B-v0.1-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Prompt Template

by Marjovl - opened Jun 11, 2024

Discussion

Marjovl

Jun 11, 2024

Hi There. Do you know what the prompt template is? I want to put it on Ollama, but sometimes I get a lot of INST on my local.

mgonzs13

Owner Jun 12, 2024

Hey @Marjovl , I am also waiting for @SF-Foundation to know the prompt template. I have tried ChatML and Alapaca-Instruct and it works fine.

I don't know how to fix the INST loop issue. I have faced it with other models like Mistroll but this issue seems to be something recurrent from some months ago (https://www.linkedin.com/posts/michal-pogoda_jaskier-56-case-study-activity-7165652768337158144-RsfM/, https://huggingface.co/bardsai/jaskier-7b-dpo-v6.1/discussions/2).

Marjovl

Jun 12, 2024

Thank you for replying @mgonzs13

There's something about this model. I tried a few successful templates. The first input message generates a great response; then, when I ask a follow-up question, I get the repeated INST.

I've also seen it respond in my native language, Afrikaans. It looked pretty good! Afrikaans is a relatively small language that's based on old simplified Dutch. So, somehow it understands it, and that's impressive.

Marjovl

Jun 18, 2024

@mgonzs13 Seems they removed the model now...

Marjovl changed discussion status to closed Jun 18, 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