Instructions to use DataSoul/ALMA-7B-R-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DataSoul/ALMA-7B-R-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DataSoul/ALMA-7B-R-gguf",
	filename="ALMA-7B-R-Q3_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 DataSoul/ALMA-7B-R-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DataSoul/ALMA-7B-R-gguf:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf DataSoul/ALMA-7B-R-gguf:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DataSoul/ALMA-7B-R-gguf:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf DataSoul/ALMA-7B-R-gguf:Q3_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 DataSoul/ALMA-7B-R-gguf:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf DataSoul/ALMA-7B-R-gguf:Q3_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 DataSoul/ALMA-7B-R-gguf:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DataSoul/ALMA-7B-R-gguf:Q3_K_M

Use Docker

docker model run hf.co/DataSoul/ALMA-7B-R-gguf:Q3_K_M

LM Studio
Jan
Ollama
How to use DataSoul/ALMA-7B-R-gguf with Ollama:
```
ollama run hf.co/DataSoul/ALMA-7B-R-gguf:Q3_K_M
```

Unsloth Studio new

How to use DataSoul/ALMA-7B-R-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 DataSoul/ALMA-7B-R-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 DataSoul/ALMA-7B-R-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DataSoul/ALMA-7B-R-gguf to start chatting

Docker Model Runner
How to use DataSoul/ALMA-7B-R-gguf with Docker Model Runner:
```
docker model run hf.co/DataSoul/ALMA-7B-R-gguf:Q3_K_M
```

Lemonade

How to use DataSoul/ALMA-7B-R-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DataSoul/ALMA-7B-R-gguf:Q3_K_M

Run and chat with the model

lemonade run user.ALMA-7B-R-gguf-Q3_K_M

List all available models

lemonade list

DataSoul commited on Jan 29, 2024

Commit

e18188f

verified ·

1 Parent(s): b3f96cc

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -1

README.md CHANGED Viewed

@@ -4,8 +4,14 @@ I just made a gguf file for my own use, and then share it, please support the or
 ---
 This repo contains GGUF format model files for  **[haoranxu/ALMA-7B-R](https://huggingface.co/haoranxu/ALMA-7B-R)**
 ---
-license: mit
 ---
 **[ALMA-R](https://arxiv.org/abs/2401.08417)** builds upon [ALMA models](https://arxiv.org/abs/2309.11674), with further LoRA fine-tuning with our proposed **Contrastive Preference Optimization (CPO)** as opposed to the Supervised Fine-tuning used in ALMA. CPO fine-tuning requires our [triplet preference data](https://huggingface.co/datasets/haoranxu/ALMA-R-Preference) for preference learning. ALMA-R now can matches or even exceeds GPT-4 or WMT winners!
 ```
 @misc{xu2024contrastive,

 ---
 This repo contains GGUF format model files for  **[haoranxu/ALMA-7B-R](https://huggingface.co/haoranxu/ALMA-7B-R)**
 ---
 ---
+---
+---
+---
+the original model card:
+---
+license: mit
 **[ALMA-R](https://arxiv.org/abs/2401.08417)** builds upon [ALMA models](https://arxiv.org/abs/2309.11674), with further LoRA fine-tuning with our proposed **Contrastive Preference Optimization (CPO)** as opposed to the Supervised Fine-tuning used in ALMA. CPO fine-tuning requires our [triplet preference data](https://huggingface.co/datasets/haoranxu/ALMA-R-Preference) for preference learning. ALMA-R now can matches or even exceeds GPT-4 or WMT winners!
 ```
 @misc{xu2024contrastive,