Instructions to use mradermacher/CodeLlama-13b-Python-hf-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/CodeLlama-13b-Python-hf-GGUF with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/CodeLlama-13b-Python-hf-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/CodeLlama-13b-Python-hf-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 mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/CodeLlama-13b-Python-hf-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 mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/CodeLlama-13b-Python-hf-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 mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/CodeLlama-13b-Python-hf-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 mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/CodeLlama-13b-Python-hf-GGUF with Ollama:
```
ollama run hf.co/mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use mradermacher/CodeLlama-13b-Python-hf-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/CodeLlama-13b-Python-hf-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/CodeLlama-13b-Python-hf-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CodeLlama-13b-Python-hf-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

mradermacher commited on Sep 16, 2024

Commit

2ff96ff

verified ·

1 Parent(s): 7024b97

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -32,6 +32,7 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q2_K.gguf) | Q2_K | 5.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.IQ3_S.gguf) | IQ3_S | 5.8 | beats Q3_K* |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q3_K_S.gguf) | Q3_K_S | 5.8 |  |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.IQ3_M.gguf) | IQ3_M | 6.1 |  |
@@ -40,6 +41,7 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q5_K_S.gguf) | Q5_K_S | 9.1 |  |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |

 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q2_K.gguf) | Q2_K | 5.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.IQ3_XS.gguf) | IQ3_XS | 5.5 |  |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.IQ3_S.gguf) | IQ3_S | 5.8 | beats Q3_K* |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q3_K_S.gguf) | Q3_K_S | 5.8 |  |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.IQ3_M.gguf) | IQ3_M | 6.1 |  |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q5_K_S.gguf) | Q5_K_S | 9.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q5_K_M.gguf) | Q5_K_M | 9.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/CodeLlama-13b-Python-hf-GGUF/resolve/main/CodeLlama-13b-Python-hf.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |