Instructions to use tensorblock/CodeLlama-70b-Python-hf-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/CodeLlama-70b-Python-hf-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/CodeLlama-70b-Python-hf-GGUF",
	filename="CodeLlama-70b-Python-hf-Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/CodeLlama-70b-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 tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K

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 tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K

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 tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/CodeLlama-70b-Python-hf-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/CodeLlama-70b-Python-hf-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/CodeLlama-70b-Python-hf-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K

Ollama
How to use tensorblock/CodeLlama-70b-Python-hf-GGUF with Ollama:
```
ollama run hf.co/tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/CodeLlama-70b-Python-hf-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 tensorblock/CodeLlama-70b-Python-hf-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 tensorblock/CodeLlama-70b-Python-hf-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/CodeLlama-70b-Python-hf-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use tensorblock/CodeLlama-70b-Python-hf-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K
```

Lemonade

How to use tensorblock/CodeLlama-70b-Python-hf-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/CodeLlama-70b-Python-hf-GGUF:Q2_K

Run and chat with the model

lemonade run user.CodeLlama-70b-Python-hf-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Jan 27

Commit

672e26d

verified ·

1 Parent(s): e080268

Keep Q2_K/Q3_K_M gguf only

Browse files

Files changed (13) hide show

CodeLlama-70b-Python-hf-Q3_K_L.gguf +0 -3
CodeLlama-70b-Python-hf-Q3_K_S.gguf +0 -3
CodeLlama-70b-Python-hf-Q4_0.gguf +0 -3
CodeLlama-70b-Python-hf-Q4_K_M.gguf +0 -3
CodeLlama-70b-Python-hf-Q4_K_S.gguf +0 -3
CodeLlama-70b-Python-hf-Q5_0.gguf +0 -3
CodeLlama-70b-Python-hf-Q5_K_M.gguf +0 -3
CodeLlama-70b-Python-hf-Q5_K_S.gguf +0 -3
CodeLlama-70b-Python-hf-Q6_K/CodeLlama-70b-Python-hf-Q6_K-00001-of-00002.gguf +0 -3
CodeLlama-70b-Python-hf-Q6_K/CodeLlama-70b-Python-hf-Q6_K-00002-of-00002.gguf +0 -3
CodeLlama-70b-Python-hf-Q8_0/CodeLlama-70b-Python-hf-Q8_0-00001-of-00003.gguf +0 -3
CodeLlama-70b-Python-hf-Q8_0/CodeLlama-70b-Python-hf-Q8_0-00002-of-00003.gguf +0 -3
CodeLlama-70b-Python-hf-Q8_0/CodeLlama-70b-Python-hf-Q8_0-00003-of-00003.gguf +0 -3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c0611b9f34ad8a3e81db354565e349ac648f64b2c54f7ff674c0aa279335c52
-size 36148000512

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:10bb4c899781fe2c05999d3dc5d6063505d51f06195dab498c6f0a17c136e5f0
-size 29919459072

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:61603e6a9e114ece3e004120cc13adde7cd6530894762222fe3ee9f67aaecad3
-size 38872431360

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:64f3b3662596fac140c53584de6514938839cfc3113d6e626d4d86b1045bde67
-size 41423092480

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d063e161346774df8e0e4bef1abc788af00c2720093c51973efdb869aaf1c3e
-size 39249918720