Instructions to use AssistantsLab/SmolLM2-1.7B-humanized_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AssistantsLab/SmolLM2-1.7B-humanized_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AssistantsLab/SmolLM2-1.7B-humanized_GGUF",
	filename="smollm2-1.7b-humanized-q2_k.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 AssistantsLab/SmolLM2-1.7B-humanized_GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AssistantsLab/SmolLM2-1.7B-humanized_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 AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AssistantsLab/SmolLM2-1.7B-humanized_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 AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AssistantsLab/SmolLM2-1.7B-humanized_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 AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M

Use Docker

docker model run hf.co/AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use AssistantsLab/SmolLM2-1.7B-humanized_GGUF with Ollama:
```
ollama run hf.co/AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M
```

Unsloth Studio

How to use AssistantsLab/SmolLM2-1.7B-humanized_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 AssistantsLab/SmolLM2-1.7B-humanized_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 AssistantsLab/SmolLM2-1.7B-humanized_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AssistantsLab/SmolLM2-1.7B-humanized_GGUF to start chatting

Docker Model Runner
How to use AssistantsLab/SmolLM2-1.7B-humanized_GGUF with Docker Model Runner:
```
docker model run hf.co/AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M
```

Lemonade

How to use AssistantsLab/SmolLM2-1.7B-humanized_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AssistantsLab/SmolLM2-1.7B-humanized_GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM2-1.7B-humanized_GGUF-Q4_K_M

List all available models

lemonade list

Michielo commited on Mar 12, 2025

Commit

77cfecf

verified ·

1 Parent(s): d6eaec2

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -7,6 +7,9 @@ license: apache-2.0
 **This repo contains the humanized 360M SmolLM2 model in the GGUF Format**
 - Quantization: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_0, q4_K_S, q4_K_M, q5_0, q5_K_S, q5_K_M, q6_K, q8_0
 ## Quickstart
 We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and install it following the official guide. We follow the latest version of llama.cpp.

 **This repo contains the humanized 360M SmolLM2 model in the GGUF Format**
 - Quantization: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_0, q4_K_S, q4_K_M, q5_0, q5_K_S, q5_K_M, q6_K, q8_0
+**More about this model**
+- We released a 135M, 360M and 1.7B parameter version of this model. For more information, view our [report](https://www.assistantslab.com/research/smollm2-report).
 ## Quickstart
 We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and install it following the official guide. We follow the latest version of llama.cpp.