Instructions to use RichardErkhov/bigscience_-_bigscience-small-testing-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 RichardErkhov/bigscience_-_bigscience-small-testing-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 RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/bigscience_-_bigscience-small-testing-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 RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/bigscience_-_bigscience-small-testing-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 RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/bigscience_-_bigscience-small-testing-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 RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/bigscience_-_bigscience-small-testing-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use RichardErkhov/bigscience_-_bigscience-small-testing-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/bigscience_-_bigscience-small-testing-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/bigscience_-_bigscience-small-testing-gguf:Q4_K_M

Run and chat with the model

lemonade run user.bigscience_-_bigscience-small-testing-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

bigscience-small-testing - GGUF

Model creator: https://huggingface.co/bigscience/
Original model: https://huggingface.co/bigscience/bigscience-small-testing/

Name	Quant method	Size
bigscience-small-testing.Q2_K.gguf	Q2_K	0.04GB
bigscience-small-testing.Q3_K_S.gguf	Q3_K_S	0.04GB
bigscience-small-testing.Q3_K.gguf	Q3_K	0.04GB
bigscience-small-testing.Q3_K_M.gguf	Q3_K_M	0.04GB
bigscience-small-testing.Q3_K_L.gguf	Q3_K_L	0.04GB
bigscience-small-testing.IQ4_XS.gguf	IQ4_XS	0.04GB
bigscience-small-testing.Q4_0.gguf	Q4_0	0.04GB
bigscience-small-testing.IQ4_NL.gguf	IQ4_NL	0.04GB
bigscience-small-testing.Q4_K_S.gguf	Q4_K_S	0.04GB
bigscience-small-testing.Q4_K.gguf	Q4_K	0.04GB
bigscience-small-testing.Q4_K_M.gguf	Q4_K_M	0.04GB
bigscience-small-testing.Q4_1.gguf	Q4_1	0.04GB
bigscience-small-testing.Q5_0.gguf	Q5_0	0.04GB
bigscience-small-testing.Q5_K_S.gguf	Q5_K_S	0.04GB
bigscience-small-testing.Q5_K.gguf	Q5_K	0.04GB
bigscience-small-testing.Q5_K_M.gguf	Q5_K_M	0.04GB
bigscience-small-testing.Q5_1.gguf	Q5_1	0.04GB
bigscience-small-testing.Q6_K.gguf	Q6_K	0.04GB
bigscience-small-testing.Q8_0.gguf	Q8_0	0.04GB

Original model description:

language: - eng tags: - integration pipeline_tag: text-generation

BigScience - testing model

This model aims to test the conversion between Megatron-LM and transformers. It is a small GPT-2-like model that has been used to debug the script. Use it only for integration tests

Downloads last month: 418

GGUF

Model size

32.2M params

Architecture

bloom

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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