Instructions to use tinyopsec/mistral-7b-sft-alpha-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 tinyopsec/mistral-7b-sft-alpha-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 tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tinyopsec/mistral-7b-sft-alpha-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 tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tinyopsec/mistral-7b-sft-alpha-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 tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tinyopsec/mistral-7b-sft-alpha-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 tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use tinyopsec/mistral-7b-sft-alpha-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tinyopsec/mistral-7b-sft-alpha-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tinyopsec/mistral-7b-sft-alpha-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M

Ollama
How to use tinyopsec/mistral-7b-sft-alpha-GGUF with Ollama:
```
ollama run hf.co/tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use tinyopsec/mistral-7b-sft-alpha-GGUF with Docker Model Runner:
```
docker model run hf.co/tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M
```

Lemonade

How to use tinyopsec/mistral-7b-sft-alpha-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tinyopsec/mistral-7b-sft-alpha-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.mistral-7b-sft-alpha-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Mistral 7B SFT Alpha - GGUF

GGUF quantized versions of HuggingFaceH4/mistral-7b-sft-alpha, a 7 billion parameter instruction-tuned language model fine-tuned from Mistral 7B v0.1 on the UltraChat dataset.

Model Details

Base Model: mistralai/Mistral-7B-v0.1
Fine-tuned by: Hugging Face H4
Training Data: UltraChat (synthetic dialogue dataset)
Architecture: Mistral (32 layers, 32 attention heads, GQA)
Context Length: 4096 tokens
Vocabulary Size: 32000

Quantization

Filename	Bits	Size	Use Case
`model_f16.gguf`	16	~14 GB	Maximum quality, high VRAM requirement
`model_q8_0.gguf`	8	~7.5 GB	High quality, moderate VRAM
`model_q6_k.gguf`	6	~5.7 GB	Good quality, balanced VRAM
`model_q5_k_m.gguf`	5	~4.8 GB	Recommended for most use cases
`model_q5_k_s.gguf`	5	~4.2 GB	Compact, minimal quality loss
`model_q4_k_m.gguf`	4	~3.5 GB	Good balance, low VRAM
`model_q4_k_s.gguf`	4	~3.2 GB	Compact model
`model_q3_k_l.gguf`	3	~2.8 GB	Very compact
`model_q3_k_m.gguf`	3	~2.5 GB	Minimal size
`model_q3_k_s.gguf`	3	~2.3 GB	Extreme compression
`model_q2_k.gguf`	2	~1.8 GB	Maximum compression

VRAM Requirements

Quantization	VRAM	Recommended Device
F16	16 GB	High-end GPU
Q8_0	8 GB	High-end GPU
Q6_K	6 GB	Mid-range GPU
Q5_K_M	5 GB	Mid-range GPU
Q4_K_M	4 GB	Standard GPU / CPU
Q3_K_M	3 GB	Laptop GPU / CPU
Q2_K	2 GB	CPU with sufficient RAM

Usage

llama.cpp

./main -m model_q5_k_m.gguf -n 256 -p "You are a helpful assistant."

llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="model_q5_k_m.gguf",
    n_ctx=4096,
    n_threads=8
)

response = llm("What is machine learning?", max_tokens=256)
print(response["choices"][0]["text"])

LM Studio

Download the quantized GGUF file and load it in LM Studio's model picker.

Ollama

ollama pull tinyopsec/mistral-7b-sft-alpha-gguf:q5_k_m
ollama run tinyopsec/mistral-7b-sft-alpha-gguf:q5_k_m

Model Capabilities

This model excels at:

Conversational AI: Fine-tuned on dialogue data for natural interactions
Instruction Following: Responsive to detailed user instructions
English Text Generation: Optimized for English-language tasks
Chat Applications: Suitable for chatbot and virtual assistant use cases

License

This quantized version maintains the original model's MIT license. See the original model card for full details.

Disclaimer

These are community quantizations. For official support and documentation, refer to the original model repository and llama.cpp documentation.

Downloads last month: 303

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for tinyopsec/mistral-7b-sft-alpha-GGUF

Base model

mistralai/Mistral-7B-v0.1

Finetuned

HuggingFaceH4/mistral-7b-sft-alpha

Quantized

(2)

this model