Instructions to use tensorblock/starcoder2-15b-instruct-v0.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/starcoder2-15b-instruct-v0.1-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="tensorblock/starcoder2-15b-instruct-v0.1-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/starcoder2-15b-instruct-v0.1-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/starcoder2-15b-instruct-v0.1-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/starcoder2-15b-instruct-v0.1-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/starcoder2-15b-instruct-v0.1-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/starcoder2-15b-instruct-v0.1-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/starcoder2-15b-instruct-v0.1-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/starcoder2-15b-instruct-v0.1-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/starcoder2-15b-instruct-v0.1-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/starcoder2-15b-instruct-v0.1-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/starcoder2-15b-instruct-v0.1-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/starcoder2-15b-instruct-v0.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/starcoder2-15b-instruct-v0.1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/starcoder2-15b-instruct-v0.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF:Q2_K

SGLang

How to use tensorblock/starcoder2-15b-instruct-v0.1-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/starcoder2-15b-instruct-v0.1-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/starcoder2-15b-instruct-v0.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/starcoder2-15b-instruct-v0.1-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/starcoder2-15b-instruct-v0.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use tensorblock/starcoder2-15b-instruct-v0.1-GGUF with Ollama:
```
ollama run hf.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF:Q2_K
```
Unsloth Desktop
Docker Model Runner
How to use tensorblock/starcoder2-15b-instruct-v0.1-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF:Q2_K
```

Lemonade

How to use tensorblock/starcoder2-15b-instruct-v0.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/starcoder2-15b-instruct-v0.1-GGUF:Q2_K

Run and chat with the model

lemonade run user.starcoder2-15b-instruct-v0.1-GGUF-Q2_K

List all available models

lemonade list

Atomic Chat

morriszms commited on Nov 16, 2024

Commit

7adf391

verified ·

1 Parent(s): 537d8ea

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -12

README.md CHANGED Viewed

@@ -103,8 +103,16 @@ This repo contains GGUF format model files for [bigcode/starcoder2-15b-instruct-
 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
 ```
 <|endoftext|>You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
@@ -118,18 +126,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
-| [starcoder2-15b-instruct-v0.1-Q2_K.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q2_K.gguf) | Q2_K | 5.768 GB | smallest, significant quality loss - not recommended for most purposes |
-| [starcoder2-15b-instruct-v0.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q3_K_S.gguf) | Q3_K_S | 6.507 GB | very small, high quality loss |
-| [starcoder2-15b-instruct-v0.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q3_K_M.gguf) | Q3_K_M | 7.492 GB | very small, high quality loss |
-| [starcoder2-15b-instruct-v0.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q3_K_L.gguf) | Q3_K_L | 8.350 GB | small, substantial quality loss |
-| [starcoder2-15b-instruct-v0.1-Q4_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q4_0.gguf) | Q4_0 | 8.443 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
-| [starcoder2-15b-instruct-v0.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q4_K_S.gguf) | Q4_K_S | 8.532 GB | small, greater quality loss |
-| [starcoder2-15b-instruct-v0.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q4_K_M.gguf) | Q4_K_M | 9.183 GB | medium, balanced quality - recommended |
-| [starcoder2-15b-instruct-v0.1-Q5_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q5_0.gguf) | Q5_0 | 10.265 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
-| [starcoder2-15b-instruct-v0.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q5_K_S.gguf) | Q5_K_S | 10.265 GB | large, low quality loss - recommended |
-| [starcoder2-15b-instruct-v0.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q5_K_M.gguf) | Q5_K_M | 10.646 GB | large, very low quality loss - recommended |
-| [starcoder2-15b-instruct-v0.1-Q6_K.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q6_K.gguf) | Q6_K | 12.201 GB | very large, extremely low quality loss |
-| [starcoder2-15b-instruct-v0.1-Q8_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/tree/main/starcoder2-15b-instruct-v0.1-Q8_0.gguf) | Q8_0 | 15.800 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
 ```
 <|endoftext|>You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
+| [starcoder2-15b-instruct-v0.1-Q2_K.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q2_K.gguf) | Q2_K | 5.768 GB | smallest, significant quality loss - not recommended for most purposes |
+| [starcoder2-15b-instruct-v0.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_S.gguf) | Q3_K_S | 6.507 GB | very small, high quality loss |
+| [starcoder2-15b-instruct-v0.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_M.gguf) | Q3_K_M | 7.492 GB | very small, high quality loss |
+| [starcoder2-15b-instruct-v0.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_L.gguf) | Q3_K_L | 8.350 GB | small, substantial quality loss |
+| [starcoder2-15b-instruct-v0.1-Q4_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q4_0.gguf) | Q4_0 | 8.443 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [starcoder2-15b-instruct-v0.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q4_K_S.gguf) | Q4_K_S | 8.532 GB | small, greater quality loss |
+| [starcoder2-15b-instruct-v0.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q4_K_M.gguf) | Q4_K_M | 9.183 GB | medium, balanced quality - recommended |
+| [starcoder2-15b-instruct-v0.1-Q5_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q5_0.gguf) | Q5_0 | 10.265 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [starcoder2-15b-instruct-v0.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q5_K_S.gguf) | Q5_K_S | 10.265 GB | large, low quality loss - recommended |
+| [starcoder2-15b-instruct-v0.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q5_K_M.gguf) | Q5_K_M | 10.646 GB | large, very low quality loss - recommended |
+| [starcoder2-15b-instruct-v0.1-Q6_K.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q6_K.gguf) | Q6_K | 12.201 GB | very large, extremely low quality loss |
+| [starcoder2-15b-instruct-v0.1-Q8_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q8_0.gguf) | Q8_0 | 15.800 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction