Instructions to use mradermacher/CodeLlama3-8B-Python-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/CodeLlama3-8B-Python-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/CodeLlama3-8B-Python-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/CodeLlama3-8B-Python-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/CodeLlama3-8B-Python-GGUF",
	filename="CodeLlama3-8B-Python.IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/CodeLlama3-8B-Python-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/CodeLlama3-8B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/CodeLlama3-8B-Python-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 mradermacher/CodeLlama3-8B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/CodeLlama3-8B-Python-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/CodeLlama3-8B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/CodeLlama3-8B-Python-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/CodeLlama3-8B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/CodeLlama3-8B-Python-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/CodeLlama3-8B-Python-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/CodeLlama3-8B-Python-GGUF with Ollama:
```
ollama run hf.co/mradermacher/CodeLlama3-8B-Python-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/CodeLlama3-8B-Python-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 mradermacher/CodeLlama3-8B-Python-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 mradermacher/CodeLlama3-8B-Python-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/CodeLlama3-8B-Python-GGUF to start chatting

Docker Model Runner
How to use mradermacher/CodeLlama3-8B-Python-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/CodeLlama3-8B-Python-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/CodeLlama3-8B-Python-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/CodeLlama3-8B-Python-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CodeLlama3-8B-Python-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Apr 24, 2024

Commit

ae2954d

verified ·

1 Parent(s): 74ddd27

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +16 -7

README.md CHANGED Viewed

@@ -20,8 +20,8 @@ tags:
 <!-- ### vocab_type:  -->
 static quants of https://huggingface.co/Markhit/CodeLlama3-8B-Python
 <!-- provided-files -->
 ## Usage
 If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -34,12 +34,21 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
-| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-i1-GGUF/resolve/main/CodeLlama3-8B-Python.Q2_K.gguf) | Q2_K | 3.3 |  |
-| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-i1-GGUF/resolve/main/CodeLlama3-8B-Python.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
-| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-i1-GGUF/resolve/main/CodeLlama3-8B-Python.IQ3_M.gguf) | IQ3_M | 3.9 |  |
-| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-i1-GGUF/resolve/main/CodeLlama3-8B-Python.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
-| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-i1-GGUF/resolve/main/CodeLlama3-8B-Python.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
-| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-i1-GGUF/resolve/main/CodeLlama3-8B-Python.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
 Here is a handy graph by ikawrakow comparing some lower-quality quant

 <!-- ### vocab_type:  -->
 static quants of https://huggingface.co/Markhit/CodeLlama3-8B-Python
 <!-- provided-files -->
+weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
 ## Usage
 If you are unsure how to use GGUF files, refer to one of [TheBloke's
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q2_K.gguf) | Q2_K | 3.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.IQ3_XS.gguf) | IQ3_XS | 3.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q3_K_S.gguf) | Q3_K_S | 3.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.IQ3_M.gguf) | IQ3_M | 3.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q3_K_L.gguf) | Q3_K_L | 4.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.IQ4_XS.gguf) | IQ4_XS | 4.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q5_K_S.gguf) | Q5_K_S | 5.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q5_K_M.gguf) | Q5_K_M | 5.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
 Here is a handy graph by ikawrakow comparing some lower-quality quant