Instructions to use devAnurag/TinyLlama-Finetuned-Mixed-10k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use devAnurag/TinyLlama-Finetuned-Mixed-10k with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="devAnurag/TinyLlama-Finetuned-Mixed-10k",
	filename="GGUF/tinyllama-f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use devAnurag/TinyLlama-Finetuned-Mixed-10k 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 devAnurag/TinyLlama-Finetuned-Mixed-10k:F16
# Run inference directly in the terminal:
llama cli -hf devAnurag/TinyLlama-Finetuned-Mixed-10k:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf devAnurag/TinyLlama-Finetuned-Mixed-10k:F16
# Run inference directly in the terminal:
llama cli -hf devAnurag/TinyLlama-Finetuned-Mixed-10k:F16

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 devAnurag/TinyLlama-Finetuned-Mixed-10k:F16
# Run inference directly in the terminal:
./llama-cli -hf devAnurag/TinyLlama-Finetuned-Mixed-10k:F16

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 devAnurag/TinyLlama-Finetuned-Mixed-10k:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf devAnurag/TinyLlama-Finetuned-Mixed-10k:F16

Use Docker

docker model run hf.co/devAnurag/TinyLlama-Finetuned-Mixed-10k:F16

LM Studio
Jan
Ollama
How to use devAnurag/TinyLlama-Finetuned-Mixed-10k with Ollama:
```
ollama run hf.co/devAnurag/TinyLlama-Finetuned-Mixed-10k:F16
```

Unsloth Studio

How to use devAnurag/TinyLlama-Finetuned-Mixed-10k 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 devAnurag/TinyLlama-Finetuned-Mixed-10k 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 devAnurag/TinyLlama-Finetuned-Mixed-10k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for devAnurag/TinyLlama-Finetuned-Mixed-10k to start chatting

Atomic Chat new
Docker Model Runner
How to use devAnurag/TinyLlama-Finetuned-Mixed-10k with Docker Model Runner:
```
docker model run hf.co/devAnurag/TinyLlama-Finetuned-Mixed-10k:F16
```

Lemonade

How to use devAnurag/TinyLlama-Finetuned-Mixed-10k with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull devAnurag/TinyLlama-Finetuned-Mixed-10k:F16

Run and chat with the model

lemonade run user.TinyLlama-Finetuned-Mixed-10k-F16

List all available models

lemonade list

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

Check out the documentation for more information.

TinyLlama Finetuned - Mixed Dataset 10k

This repository contains:

Merged full HuggingFace model
LoRA adapter
GGUF formats (F16 & Q4_K_M)
Dataset used: Mixed multilingual dataset 10K
Architecture: TinyLlama 1.1B Chat v1.0
Finetuned with LoRA (r=16, alpha=32)

Files

Type	Path
Full HF model	/HF_full_model
LoRA Adapter	/LoRA_adapter
GGUF F16	/GGUF/tinyllama_f16.gguf
GGUF Q4_K_M	/GGUF/tinyllama_q4_k_m.gguf

Downloads last month: 1

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

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