Instructions to use Maxixa/lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Maxixa/lora with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Maxixa/lora",
	filename="gguf/speechless-sparsetral-mistral-16x7b-moe.Q5_K_M.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 Maxixa/lora with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Maxixa/lora:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf Maxixa/lora:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Maxixa/lora:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf Maxixa/lora:Q5_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 Maxixa/lora:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf Maxixa/lora:Q5_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 Maxixa/lora:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Maxixa/lora:Q5_K_M

Use Docker

docker model run hf.co/Maxixa/lora:Q5_K_M

LM Studio
Jan
Ollama
How to use Maxixa/lora with Ollama:
```
ollama run hf.co/Maxixa/lora:Q5_K_M
```

Unsloth Studio new

How to use Maxixa/lora 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 Maxixa/lora 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 Maxixa/lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Maxixa/lora to start chatting

Docker Model Runner
How to use Maxixa/lora with Docker Model Runner:
```
docker model run hf.co/Maxixa/lora:Q5_K_M
```

Lemonade

How to use Maxixa/lora with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Maxixa/lora:Q5_K_M

Run and chat with the model

lemonade run user.lora-Q5_K_M

List all available models

lemonade list

Maxixa commited on Feb 21, 2023

Commit

6e6ab57

1 Parent(s): 40dd31d

Upload dwrtsg-65-768 with huggingface_hub

Browse files

Files changed (4) hide show

dwrtsg-65-768/dwrtsg-65-768-1.ckpt +3 -0
dwrtsg-65-768/dwrtsg-65-768-2.ckpt +3 -0
dwrtsg-65-768/dwrtsg-65-768-3.ckpt +3 -0
dwrtsg-65-768/dwrtsg-65-768-4.ckpt +3 -0

dwrtsg-65-768/dwrtsg-65-768-1.ckpt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d6f2848c9b0c321ad39b0f054a63a4b82eead2f7d75a270479fe6083ce62c0
+size 151349795

dwrtsg-65-768/dwrtsg-65-768-2.ckpt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7327e08f8fb262d9f4b6f5e2feab99c3670df46b6788dd7550634c7b26272981
+size 151349795

dwrtsg-65-768/dwrtsg-65-768-3.ckpt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:15128b9f5b2d72648046921fbfbee682e6d514f8b2303cd7f1e32fd7ad930580
+size 151349795

dwrtsg-65-768/dwrtsg-65-768-4.ckpt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6e81e32dd9cfa8c5716bd7375edd119a0dc0f483a7abcb4223f9b77e355f74f0
+size 151344237