Instructions to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="notSnix/Step-3.7-Flash-MTP-Draft-GGUF",
	filename="Step-3.7-Flash-MTP-BF16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf notSnix/Step-3.7-Flash-MTP-Draft-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 notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf notSnix/Step-3.7-Flash-MTP-Draft-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 notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf notSnix/Step-3.7-Flash-MTP-Draft-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 notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

Use Docker

docker model run hf.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with Ollama:
```
ollama run hf.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
```

Unsloth Studio

How to use notSnix/Step-3.7-Flash-MTP-Draft-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 notSnix/Step-3.7-Flash-MTP-Draft-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 notSnix/Step-3.7-Flash-MTP-Draft-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for notSnix/Step-3.7-Flash-MTP-Draft-GGUF to start chatting

Docker Model Runner
How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with Docker Model Runner:
```
docker model run hf.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
```

Lemonade

How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Step-3.7-Flash-MTP-Draft-GGUF-Q4_K_M

List all available models

lemonade list

Step-3.7-Flash quant support with the MTP GGUF models

by scottgl - opened 4 days ago

Discussion

scottgl

4 days ago

•

edited 4 days ago

I was wondering, have you tried other quants for the Step-3.7-Flash model, other than Step-3.7-Flash-Q4_K_M.gguf? The reason I ask, I would like to run Step-3.7-Flash + MTP, but it will not fit into memory. I'm wondering if anyone has tried other quants with the MTP, such as IQ4_XS or Q4_K_S with one of the MTP GGUF files?

slavap5

4 days ago

•

edited 4 days ago

Yes. MTP works with IQ4_XS and Q4_K_S. But on my StrixHalo it is only realistic to use it with IQ4_XS with context > 128k, till -ctkd and -ctvd get fixed (MTP takes too much vram currently because of F16), so I can set q8_0 for draft model cache. See https://github.com/ggml-org/llama.cpp/issues/24040
By the way, I like Bartowski quants, official Stepfun ones are good as well.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment