Instructions to use afrideva/smol_llama-220M-open_instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afrideva/smol_llama-220M-open_instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="afrideva/smol_llama-220M-open_instruct-GGUF",
	filename="smol_llama-220m-open_instruct.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/smol_llama-220M-open_instruct-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/smol_llama-220M-open_instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/smol_llama-220M-open_instruct-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/smol_llama-220M-open_instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/smol_llama-220M-open_instruct-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-220M-open_instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/smol_llama-220M-open_instruct-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-220M-open_instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/smol_llama-220M-open_instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/smol_llama-220M-open_instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/smol_llama-220M-open_instruct-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-220M-open_instruct-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-220M-open_instruct-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afrideva/smol_llama-220M-open_instruct-GGUF:Q4_K_M

Ollama
How to use afrideva/smol_llama-220M-open_instruct-GGUF with Ollama:
```
ollama run hf.co/afrideva/smol_llama-220M-open_instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use afrideva/smol_llama-220M-open_instruct-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/smol_llama-220M-open_instruct-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/smol_llama-220M-open_instruct-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/smol_llama-220M-open_instruct-GGUF to start chatting

Docker Model Runner
How to use afrideva/smol_llama-220M-open_instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/smol_llama-220M-open_instruct-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/smol_llama-220M-open_instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/smol_llama-220M-open_instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.smol_llama-220M-open_instruct-GGUF-Q4_K_M

List all available models

lemonade list

BEE-spoke-data/smol_llama-220M-open_instruct-GGUF

Quantized GGUF model files for smol_llama-220M-open_instruct from BEE-spoke-data

Name	Quant method	Size
smol_llama-220m-open_instruct.fp16.gguf	fp16	436.50 MB
smol_llama-220m-open_instruct.q2_k.gguf	q2_k	94.43 MB
smol_llama-220m-open_instruct.q3_k_m.gguf	q3_k_m	114.65 MB
smol_llama-220m-open_instruct.q4_k_m.gguf	q4_k_m	137.58 MB
smol_llama-220m-open_instruct.q5_k_m.gguf	q5_k_m	157.91 MB
smol_llama-220m-open_instruct.q6_k.gguf	q6_k	179.52 MB
smol_llama-220m-open_instruct.q8_0.gguf	q8_0	232.28 MB

Original Model Card:

BEE-spoke-data/smol_llama-220M-open_instruct

Please note that this is an experiment, and the model has limitations because it is smol.

prompt format is alpaca.

Below is an instruction that describes a task, paired with an input that
provides further context. Write a response that appropriately completes
the request.  

### Instruction:  

How can I increase my meme production/output? Currently, I only create them in ancient babylonian which is time consuming.  

### Response:

This was not trained using a separate 'inputs' field (as VMware/open-instruct doesn't use one).

Example

Output on the text above ^. The inference API is set to sample with low temp so you should see (at least slightly) different generations each time.

Note that the inference API parameters used here are an initial educated guess, and may be updated over time:

inference:
  parameters:
    do_sample: true
    renormalize_logits: true
    temperature: 0.25
    top_p: 0.95
    top_k: 50
    min_new_tokens: 2
    max_new_tokens: 96
    repetition_penalty: 1.04
    no_repeat_ngram_size: 6
    epsilon_cutoff: 0.0006

Feel free to experiment with the parameters using the model in Python and let us know if you have improved results with other params!

Data

This was trained on VMware/open-instruct so do whatever you want, provided it falls under the base apache-2.0 license :)

Downloads last month: 59

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/smol_llama-220M-open_instruct-GGUF

Base model

BEE-spoke-data/smol_llama-220M-GQA

Finetuned

BEE-spoke-data/smol_llama-220M-open_instruct

Quantized

(1)

this model

afrideva
/

smol_llama-220M-open_instruct-GGUF

BEE-spoke-data/smol_llama-220M-open_instruct-GGUF

Original Model Card:

BEE-spoke-data/smol_llama-220M-open_instruct

Example

Data

Model tree for afrideva/smol_llama-220M-open_instruct-GGUF

Dataset used to train afrideva/smol_llama-220M-open_instruct-GGUF