Instructions to use RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-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 RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-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 RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Alphacode-AI_-_Alphacode-MALI-11B-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Alphacode-MALI-11B - GGUF

Model creator: https://huggingface.co/Alphacode-AI/
Original model: https://huggingface.co/Alphacode-AI/Alphacode-MALI-11B/

Name	Quant method	Size
Alphacode-MALI-11B.Q2_K.gguf	Q2_K	3.8GB
Alphacode-MALI-11B.IQ3_XS.gguf	IQ3_XS	4.23GB
Alphacode-MALI-11B.IQ3_S.gguf	IQ3_S	4.46GB
Alphacode-MALI-11B.Q3_K_S.gguf	Q3_K_S	4.43GB
Alphacode-MALI-11B.IQ3_M.gguf	IQ3_M	4.6GB
Alphacode-MALI-11B.Q3_K.gguf	Q3_K	4.94GB
Alphacode-MALI-11B.Q3_K_M.gguf	Q3_K_M	4.94GB
Alphacode-MALI-11B.Q3_K_L.gguf	Q3_K_L	5.37GB
Alphacode-MALI-11B.IQ4_XS.gguf	IQ4_XS	5.54GB
Alphacode-MALI-11B.Q4_0.gguf	Q4_0	5.77GB
Alphacode-MALI-11B.IQ4_NL.gguf	IQ4_NL	5.83GB
Alphacode-MALI-11B.Q4_K_S.gguf	Q4_K_S	5.81GB
Alphacode-MALI-11B.Q4_K.gguf	Q4_K	6.15GB
Alphacode-MALI-11B.Q4_K_M.gguf	Q4_K_M	6.15GB
Alphacode-MALI-11B.Q4_1.gguf	Q4_1	6.4GB
Alphacode-MALI-11B.Q5_0.gguf	Q5_0	7.03GB
Alphacode-MALI-11B.Q5_K_S.gguf	Q5_K_S	7.03GB
Alphacode-MALI-11B.Q5_K.gguf	Q5_K	7.22GB
Alphacode-MALI-11B.Q5_K_M.gguf	Q5_K_M	7.22GB
Alphacode-MALI-11B.Q5_1.gguf	Q5_1	7.66GB
Alphacode-MALI-11B.Q6_K.gguf	Q6_K	8.37GB
Alphacode-MALI-11B.Q8_0.gguf	Q8_0	10.84GB

Original model description:

license: cc-by-4.0 language: - ko pipeline_tag: text-generation tags: - merge

MALI-11B (Model with Auto Learning Ideation) is a merge version of Alphacode's Models that has been fine-tuned with Our In House CustomData.

Train Spec : We utilized an A100x8 for training our model with DeepSpeed / HuggingFace TRL Trainer / HuggingFace Accelerate

Contact : Alphacode Co. [https://alphacode.ai/]

Downloads last month: 210

GGUF

Model size

11B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support