Instructions to use afrideva/smol_llama-101M-GQA-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 afrideva/smol_llama-101M-GQA-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 afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf afrideva/smol_llama-101M-GQA-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 afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf afrideva/smol_llama-101M-GQA-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 afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/smol_llama-101M-GQA-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 afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/smol_llama-101M-GQA-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/smol_llama-101M-GQA-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/smol_llama-101M-GQA-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M

Ollama
How to use afrideva/smol_llama-101M-GQA-GGUF with Ollama:
```
ollama run hf.co/afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use afrideva/smol_llama-101M-GQA-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/smol_llama-101M-GQA-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/smol_llama-101M-GQA-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.smol_llama-101M-GQA-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

BEE-spoke-data/smol_llama-101M-GQA-GGUF

Quantized GGUF model files for smol_llama-101M-GQA from BEE-spoke-data

Name	Quant method	Size
smol_llama-101m-gqa.fp16.gguf	fp16	203.28 MB
smol_llama-101m-gqa.q2_k.gguf	q2_k	50.93 MB
smol_llama-101m-gqa.q3_k_m.gguf	q3_k_m	57.06 MB
smol_llama-101m-gqa.q4_k_m.gguf	q4_k_m	65.40 MB
smol_llama-101m-gqa.q5_k_m.gguf	q5_k_m	74.34 MB
smol_llama-101m-gqa.q6_k.gguf	q6_k	83.83 MB
smol_llama-101m-gqa.q8_0.gguf	q8_0	108.35 MB

Original Model Card:

smol_llama-101M-GQA

A small 101M param (total) decoder model. This is the first version of the model.

768 hidden size, 6 layers
GQA (24 heads, 8 key-value), context length 1024
train-from-scratch

Notes

This checkpoint is the 'raw' pre-trained model and has not been tuned to a more specific task. It should be fine-tuned before use in most cases.

Checkpoints & Links

smol-er 81M parameter checkpoint with in/out embeddings tied: here
Fine-tuned on pypi to generate Python code - link
For the chat version of this model, please see here

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.32
ARC (25-shot)	23.55
HellaSwag (10-shot)	28.77
MMLU (5-shot)	24.24
TruthfulQA (0-shot)	45.76
Winogrande (5-shot)	50.67
GSM8K (5-shot)	0.83
DROP (3-shot)	3.39

Downloads last month: 185

GGUF

Model size

0.1B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for afrideva/smol_llama-101M-GQA-GGUF

Base model

BEE-spoke-data/smol_llama-101M-GQA

Quantized

(1)

this model

afrideva
/

smol_llama-101M-GQA-GGUF