Instructions to use tensorblock/smol_llama-81M-tied-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 tensorblock/smol_llama-81M-tied-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 tensorblock/smol_llama-81M-tied-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/smol_llama-81M-tied-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/smol_llama-81M-tied-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/smol_llama-81M-tied-GGUF:Q2_K

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 tensorblock/smol_llama-81M-tied-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/smol_llama-81M-tied-GGUF:Q2_K

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 tensorblock/smol_llama-81M-tied-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/smol_llama-81M-tied-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/smol_llama-81M-tied-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/smol_llama-81M-tied-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/smol_llama-81M-tied-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/smol_llama-81M-tied-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensorblock/smol_llama-81M-tied-GGUF:Q2_K

Ollama
How to use tensorblock/smol_llama-81M-tied-GGUF with Ollama:
```
ollama run hf.co/tensorblock/smol_llama-81M-tied-GGUF:Q2_K
```
Unsloth Desktop
Docker Model Runner
How to use tensorblock/smol_llama-81M-tied-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/smol_llama-81M-tied-GGUF:Q2_K
```

Lemonade

How to use tensorblock/smol_llama-81M-tied-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/smol_llama-81M-tied-GGUF:Q2_K

Run and chat with the model

lemonade run user.smol_llama-81M-tied-GGUF-Q2_K

List all available models

lemonade list

Atomic Chat

smol_llama-81M-tied-GGUF / README.md

morriszms

Update README.md

048c80f verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

8.48 kB

metadata

license: apache-2.0
thumbnail: https://i.ibb.co/TvyMrRc/rsz-smol-llama-banner.png
language:
  - en
inference:
  parameters:
    max_new_tokens: 64
    do_sample: true
    temperature: 0.8
    repetition_penalty: 1.15
    no_repeat_ngram_size: 4
    eta_cutoff: 0.0006
    renormalize_logits: true
widget:
  - text: My name is El Microondas the Wise and
    example_title: El Microondas
  - text: Kennesaw State University is a public
    example_title: Kennesaw State University
  - text: >-
      Bungie Studios is an American video game developer. They are most famous
      for developing the award winning Halo series of video games. They also
      made Destiny. The studio was founded
    example_title: Bungie
  - text: The Mona Lisa is a world-renowned painting created by
    example_title: Mona Lisa
  - text: >-
      The Harry Potter series, written by J.K. Rowling, begins with the book
      titled
    example_title: Harry Potter Series
  - text: >-
      Question: I have cities, but no houses. I have mountains, but no trees. I
      have water, but no fish. What am I?

      Answer:
    example_title: Riddle
  - text: The process of photosynthesis involves the conversion of
    example_title: Photosynthesis
  - text: >-
      Jane went to the store to buy some groceries. She picked up apples,
      oranges, and a loaf of bread. When she got home, she realized she forgot
    example_title: Story Continuation
  - text: >-
      Problem 2: If a train leaves Station A at 9:00 AM and travels at 60 mph,
      and another train leaves Station B at 10:00 AM and travels at 80 mph, when
      will they meet if the distance between the stations is 300 miles?

      To determine
    example_title: Math Problem
  - text: In the context of computer programming, an algorithm is
    example_title: Algorithm Definition
pipeline_tag: text-generation
tags:
  - smol_llama
  - llama2
  - TensorBlock
  - GGUF
datasets:
  - JeanKaddour/minipile
  - pszemraj/simple_wikipedia_LM
  - BEE-spoke-data/wikipedia-20230901.en-deduped
  - mattymchen/refinedweb-3m
base_model: BEE-spoke-data/smol_llama-81M-tied

BEE-spoke-data/smol_llama-81M-tied - GGUF

This repo contains GGUF format model files for BEE-spoke-data/smol_llama-81M-tied.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

Model file specification

Filename	Quant type	File Size	Description
smol_llama-81M-tied-Q2_K.gguf	Q2_K	0.039 GB	smallest, significant quality loss - not recommended for most purposes
smol_llama-81M-tied-Q3_K_S.gguf	Q3_K_S	0.042 GB	very small, high quality loss
smol_llama-81M-tied-Q3_K_M.gguf	Q3_K_M	0.045 GB	very small, high quality loss
smol_llama-81M-tied-Q3_K_L.gguf	Q3_K_L	0.047 GB	small, substantial quality loss
smol_llama-81M-tied-Q4_0.gguf	Q4_0	0.049 GB	legacy; small, very high quality loss - prefer using Q3_K_M
smol_llama-81M-tied-Q4_K_S.gguf	Q4_K_S	0.050 GB	small, greater quality loss
smol_llama-81M-tied-Q4_K_M.gguf	Q4_K_M	0.051 GB	medium, balanced quality - recommended
smol_llama-81M-tied-Q5_0.gguf	Q5_0	0.056 GB	legacy; medium, balanced quality - prefer using Q4_K_M
smol_llama-81M-tied-Q5_K_S.gguf	Q5_K_S	0.056 GB	large, low quality loss - recommended
smol_llama-81M-tied-Q5_K_M.gguf	Q5_K_M	0.057 GB	large, very low quality loss - recommended
smol_llama-81M-tied-Q6_K.gguf	Q6_K	0.063 GB	very large, extremely low quality loss
smol_llama-81M-tied-Q8_0.gguf	Q8_0	0.081 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/smol_llama-81M-tied-GGUF --include "smol_llama-81M-tied-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/smol_llama-81M-tied-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'