Instructions to use john-broadway/SmolLM2-135M-RYS-18-22-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use john-broadway/SmolLM2-135M-RYS-18-22-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="john-broadway/SmolLM2-135M-RYS-18-22-GGUF",
	filename="SmolLM2-135M-RYS-18-22-Q4_K_M.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 john-broadway/SmolLM2-135M-RYS-18-22-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/SmolLM2-135M-RYS-18-22-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 john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/SmolLM2-135M-RYS-18-22-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 john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf john-broadway/SmolLM2-135M-RYS-18-22-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 john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M

Use Docker

docker model run hf.co/john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use john-broadway/SmolLM2-135M-RYS-18-22-GGUF with Ollama:
```
ollama run hf.co/john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M
```

Unsloth Studio

How to use john-broadway/SmolLM2-135M-RYS-18-22-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 john-broadway/SmolLM2-135M-RYS-18-22-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 john-broadway/SmolLM2-135M-RYS-18-22-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for john-broadway/SmolLM2-135M-RYS-18-22-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use john-broadway/SmolLM2-135M-RYS-18-22-GGUF with Docker Model Runner:
```
docker model run hf.co/john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M
```

Lemonade

How to use john-broadway/SmolLM2-135M-RYS-18-22-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull john-broadway/SmolLM2-135M-RYS-18-22-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM2-135M-RYS-18-22-GGUF-Q4_K_M

List all available models

lemonade list

john-broadway commited on May 13

Commit

5c9e14a

verified ·

1 Parent(s): e265ded

Remove broken reference to deleted -RYS-eval companion repo (consolidated into this weights repo)

Browse files

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -39,7 +39,6 @@ llama-server -m SmolLM2-135M-RYS-18-22-Q4_K_M.gguf -ngl 99
 40 configurations tested. (18,22) block-4 is the best-combined pick. Full per-config sweep + cross-architecture analysis: [v2 dataset](https://huggingface.co/datasets/john-broadway/rys-sovereign-collection-v2).
-Eval-only companion card: [`john-broadway/SmolLM2-135M-RYS-eval`](https://huggingface.co/john-broadway/SmolLM2-135M-RYS-eval).
 Part of the RYS Sovereign Collection v2.


39
40	40 configurations tested. (18,22) block-4 is the best-combined pick. Full per-config sweep + cross-architecture analysis: [v2 dataset](https://huggingface.co/datasets/john-broadway/rys-sovereign-collection-v2).
41

42
43	Part of the RYS Sovereign Collection v2.
44