Instructions to use tensorblock/starcoder2-3b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/starcoder2-3b-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tensorblock/starcoder2-3b-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/starcoder2-3b-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/starcoder2-3b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/starcoder2-3b-GGUF",
	filename="starcoder2-3b-Q2_K.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 tensorblock/starcoder2-3b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/starcoder2-3b-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/starcoder2-3b-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/starcoder2-3b-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/starcoder2-3b-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/starcoder2-3b-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/starcoder2-3b-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/starcoder2-3b-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/starcoder2-3b-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/starcoder2-3b-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/starcoder2-3b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/starcoder2-3b-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/starcoder2-3b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensorblock/starcoder2-3b-GGUF:Q2_K

SGLang

How to use tensorblock/starcoder2-3b-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tensorblock/starcoder2-3b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/starcoder2-3b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tensorblock/starcoder2-3b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/starcoder2-3b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use tensorblock/starcoder2-3b-GGUF with Ollama:
```
ollama run hf.co/tensorblock/starcoder2-3b-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/starcoder2-3b-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/starcoder2-3b-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/starcoder2-3b-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/starcoder2-3b-GGUF to start chatting

Docker Model Runner
How to use tensorblock/starcoder2-3b-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/starcoder2-3b-GGUF:Q2_K
```

Lemonade

How to use tensorblock/starcoder2-3b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/starcoder2-3b-GGUF:Q2_K

Run and chat with the model

lemonade run user.starcoder2-3b-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Nov 16, 2024

Commit

2130a1f

verified ·

1 Parent(s): f6a2a8a

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -12

README.md CHANGED Viewed

@@ -84,8 +84,16 @@ This repo contains GGUF format model files for [bigcode/starcoder2-3b](https://h
 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
 ## Prompt template
 ```
 ```
@@ -94,18 +102,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
-| [starcoder2-3b-Q2_K.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q2_K.gguf) | Q2_K | 1.139 GB | smallest, significant quality loss - not recommended for most purposes |
-| [starcoder2-3b-Q3_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q3_K_S.gguf) | Q3_K_S | 1.273 GB | very small, high quality loss |
-| [starcoder2-3b-Q3_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q3_K_M.gguf) | Q3_K_M | 1.455 GB | very small, high quality loss |
-| [starcoder2-3b-Q3_K_L.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q3_K_L.gguf) | Q3_K_L | 1.618 GB | small, substantial quality loss |
-| [starcoder2-3b-Q4_0.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q4_0.gguf) | Q4_0 | 1.629 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
-| [starcoder2-3b-Q4_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q4_K_S.gguf) | Q4_K_S | 1.642 GB | small, greater quality loss |
-| [starcoder2-3b-Q4_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q4_K_M.gguf) | Q4_K_M | 1.758 GB | medium, balanced quality - recommended |
-| [starcoder2-3b-Q5_0.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q5_0.gguf) | Q5_0 | 1.964 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
-| [starcoder2-3b-Q5_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q5_K_S.gguf) | Q5_K_S | 1.964 GB | large, low quality loss - recommended |
-| [starcoder2-3b-Q5_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q5_K_M.gguf) | Q5_K_M | 2.031 GB | large, very low quality loss - recommended |
-| [starcoder2-3b-Q6_K.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q6_K.gguf) | Q6_K | 2.320 GB | very large, extremely low quality loss |
-| [starcoder2-3b-Q8_0.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/tree/main/starcoder2-3b-Q8_0.gguf) | Q8_0 | 3.003 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction

 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
 ## Prompt template
 ```
 ```
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
+| [starcoder2-3b-Q2_K.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q2_K.gguf) | Q2_K | 1.139 GB | smallest, significant quality loss - not recommended for most purposes |
+| [starcoder2-3b-Q3_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q3_K_S.gguf) | Q3_K_S | 1.273 GB | very small, high quality loss |
+| [starcoder2-3b-Q3_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q3_K_M.gguf) | Q3_K_M | 1.455 GB | very small, high quality loss |
+| [starcoder2-3b-Q3_K_L.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q3_K_L.gguf) | Q3_K_L | 1.618 GB | small, substantial quality loss |
+| [starcoder2-3b-Q4_0.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q4_0.gguf) | Q4_0 | 1.629 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [starcoder2-3b-Q4_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q4_K_S.gguf) | Q4_K_S | 1.642 GB | small, greater quality loss |
+| [starcoder2-3b-Q4_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q4_K_M.gguf) | Q4_K_M | 1.758 GB | medium, balanced quality - recommended |
+| [starcoder2-3b-Q5_0.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q5_0.gguf) | Q5_0 | 1.964 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [starcoder2-3b-Q5_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q5_K_S.gguf) | Q5_K_S | 1.964 GB | large, low quality loss - recommended |
+| [starcoder2-3b-Q5_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q5_K_M.gguf) | Q5_K_M | 2.031 GB | large, very low quality loss - recommended |
+| [starcoder2-3b-Q6_K.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q6_K.gguf) | Q6_K | 2.320 GB | very large, extremely low quality loss |
+| [starcoder2-3b-Q8_0.gguf](https://huggingface.co/tensorblock/starcoder2-3b-GGUF/blob/main/starcoder2-3b-Q8_0.gguf) | Q8_0 | 3.003 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction