Instructions to use afrideva/TinyMistral-248M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afrideva/TinyMistral-248M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="afrideva/TinyMistral-248M-GGUF",
	filename="tinymistral-248m.fp16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use afrideva/TinyMistral-248M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf afrideva/TinyMistral-248M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/TinyMistral-248M-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 afrideva/TinyMistral-248M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/TinyMistral-248M-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/TinyMistral-248M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/TinyMistral-248M-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/TinyMistral-248M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/TinyMistral-248M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/TinyMistral-248M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/TinyMistral-248M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/TinyMistral-248M-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/TinyMistral-248M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afrideva/TinyMistral-248M-GGUF:Q4_K_M

Ollama
How to use afrideva/TinyMistral-248M-GGUF with Ollama:
```
ollama run hf.co/afrideva/TinyMistral-248M-GGUF:Q4_K_M
```

Unsloth Studio

How to use afrideva/TinyMistral-248M-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 afrideva/TinyMistral-248M-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 afrideva/TinyMistral-248M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for afrideva/TinyMistral-248M-GGUF to start chatting

Docker Model Runner
How to use afrideva/TinyMistral-248M-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/TinyMistral-248M-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/TinyMistral-248M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/TinyMistral-248M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TinyMistral-248M-GGUF-Q4_K_M

List all available models

lemonade list

Locutusque/TinyMistral-248M-GGUF

Quantized GGUF model files for TinyMistral-248M from Locutusque

Name	Quant method	Size
tinymistral-248m.fp16.gguf	fp16	497.76 MB
tinymistral-248m.q2_k.gguf	q2_k	116.20 MB
tinymistral-248m.q3_k_m.gguf	q3_k_m	131.01 MB
tinymistral-248m.q4_k_m.gguf	q4_k_m	156.61 MB
tinymistral-248m.q5_k_m.gguf	q5_k_m	180.17 MB
tinymistral-248m.q6_k.gguf	q6_k	205.20 MB
tinymistral-248m.q8_0.gguf	q8_0	265.26 MB

Original Model Card:

A pre-trained language model, based on the Mistral 7B model, has been scaled down to approximately 248 million parameters. This model has been trained on 7,488,000 examples. This model isn't intended for direct use but for fine-tuning on a downstream task. This model should have a context length of around 32,768 tokens. Safe serialization has been removed due to issues saving model weights.

During evaluation on InstructMix, this model achieved an average perplexity score of 6.3. More epochs are planned for this model on different datasets.

Open LLM Leaderboard Evaluation Results (outdated)

Detailed results can be found here

Metric	Value
Avg.	24.18
ARC (25-shot)	20.82
HellaSwag (10-shot)	26.98
MMLU (5-shot)	23.11
TruthfulQA (0-shot)	46.89
Winogrande (5-shot)	50.75
GSM8K (5-shot)	0.0
DROP (3-shot)	0.74

The purpose of this model is to prove that trillion-scale datasets are not needed to pretrain a language model. As a result of needing small datasets, this model was pretrained on a single GPU (Titan V).

Downloads last month: 347

GGUF

Model size

0.2B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for afrideva/TinyMistral-248M-GGUF

Base model

Locutusque/TinyMistral-248M

Quantized

(5)

this model

afrideva
/

TinyMistral-248M-GGUF

Locutusque/TinyMistral-248M-GGUF

Original Model Card:

Open LLM Leaderboard Evaluation Results (outdated)

Model tree for afrideva/TinyMistral-248M-GGUF

Datasets used to train afrideva/TinyMistral-248M-GGUF