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

Libraries

How to use afrideva/tinyllama-python-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="afrideva/tinyllama-python-GGUF",
	filename="tinyllama-python.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/tinyllama-python-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/tinyllama-python-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/tinyllama-python-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/tinyllama-python-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/tinyllama-python-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/tinyllama-python-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/tinyllama-python-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/tinyllama-python-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/tinyllama-python-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/tinyllama-python-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/tinyllama-python-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/afrideva/tinyllama-python-GGUF:Q4_K_M

Ollama
How to use afrideva/tinyllama-python-GGUF with Ollama:
```
ollama run hf.co/afrideva/tinyllama-python-GGUF:Q4_K_M
```

Unsloth Studio new

How to use afrideva/tinyllama-python-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/tinyllama-python-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/tinyllama-python-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/tinyllama-python-GGUF to start chatting

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

Lemonade

How to use afrideva/tinyllama-python-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/tinyllama-python-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.tinyllama-python-GGUF-Q4_K_M

List all available models

lemonade list

afrideva commited on Jan 20, 2024

Commit

9b785a0

verified ·

1 Parent(s): 393765c

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +85 -0

README.md ADDED Viewed

	@@ -0,0 +1,85 @@

+---
+base_model: rahuldshetty/tinyllama-python
+datasets:
+- iamtarun/python_code_instructions_18k_alpaca
+inference: false
+language:
+- en
+license: apache-2.0
+model_creator: rahuldshetty
+model_name: tinyllama-python
+pipeline_tag: text-generation
+quantized_by: afrideva
+tags:
+- code
+- gguf
+- ggml
+- quantized
+- q2_k
+- q3_k_m
+- q4_k_m
+- q5_k_m
+- q6_k
+- q8_0
+widget:
+- text: '### Instruction:
+    Write a function to find square of a number.
+    ### Response:'
+- text: '### Instruction:
+    Write a function to calculate factorial.
+    ### Response:'
+- text: '### Instruction:
+    Write a function to check whether a number is prime.
+    ### Response:'
+---
+# rahuldshetty/tinyllama-python-GGUF
+Quantized GGUF model files for [tinyllama-python](https://huggingface.co/rahuldshetty/tinyllama-python) from [rahuldshetty](https://huggingface.co/rahuldshetty)
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [tinyllama-python.fp16.gguf](https://huggingface.co/afrideva/tinyllama-python-GGUF/resolve/main/tinyllama-python.fp16.gguf) | fp16 | 2.20 GB  |
+| [tinyllama-python.q2_k.gguf](https://huggingface.co/afrideva/tinyllama-python-GGUF/resolve/main/tinyllama-python.q2_k.gguf) | q2_k | 432.13 MB  |
+| [tinyllama-python.q3_k_m.gguf](https://huggingface.co/afrideva/tinyllama-python-GGUF/resolve/main/tinyllama-python.q3_k_m.gguf) | q3_k_m | 548.40 MB  |
+| [tinyllama-python.q4_k_m.gguf](https://huggingface.co/afrideva/tinyllama-python-GGUF/resolve/main/tinyllama-python.q4_k_m.gguf) | q4_k_m | 667.81 MB  |
+| [tinyllama-python.q5_k_m.gguf](https://huggingface.co/afrideva/tinyllama-python-GGUF/resolve/main/tinyllama-python.q5_k_m.gguf) | q5_k_m | 782.04 MB  |
+| [tinyllama-python.q6_k.gguf](https://huggingface.co/afrideva/tinyllama-python-GGUF/resolve/main/tinyllama-python.q6_k.gguf) | q6_k | 903.41 MB  |
+| [tinyllama-python.q8_0.gguf](https://huggingface.co/afrideva/tinyllama-python-GGUF/resolve/main/tinyllama-python.q8_0.gguf) | q8_0 | 1.17 GB  |
+## Original Model Card:
+# rahuldshetty/tinyllama-python-gguf
+- Base model: [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit)
+- Dataset: [iamtarun/python_code_instructions_18k_alpaca](https://huggingface.co/datasets/iamtarun/python_code_instructions_18k_alpaca)
+- Training Script: [unslothai: Alpaca + TinyLlama + RoPE Scaling full example.ipynb](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing)
+## Prompt Format
+```
+### Instruction:
+{instruction}
+### Response:
+```
+## Example
+```
+### Instruction:
+Write a function to find cube of a number.
+### Response:
+```