Instructions to use Colby/starcoder-7b-agent-0.5-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Colby/starcoder-7b-agent-0.5-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Colby/starcoder-7b-agent-0.5-gguf",
	filename="starcoder-7b-agent-0.5-f16.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 Colby/starcoder-7b-agent-0.5-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 Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Colby/starcoder-7b-agent-0.5-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 Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Colby/starcoder-7b-agent-0.5-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 Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Colby/starcoder-7b-agent-0.5-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 Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M

Use Docker

docker model run hf.co/Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use Colby/starcoder-7b-agent-0.5-gguf with Ollama:
```
ollama run hf.co/Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M
```

Unsloth Studio

How to use Colby/starcoder-7b-agent-0.5-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 Colby/starcoder-7b-agent-0.5-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 Colby/starcoder-7b-agent-0.5-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Colby/starcoder-7b-agent-0.5-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use Colby/starcoder-7b-agent-0.5-gguf with Docker Model Runner:
```
docker model run hf.co/Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M
```

Lemonade

How to use Colby/starcoder-7b-agent-0.5-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Colby/starcoder-7b-agent-0.5-gguf:Q4_K_M

Run and chat with the model

lemonade run user.starcoder-7b-agent-0.5-gguf-Q4_K_M

List all available models

lemonade list

starcoder-7b-agent-0.5-gguf / README.md

Colby

Upload README.md with huggingface_hub

b8aa0b4 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

912 Bytes

	---
	base_model: Colby/starcoder-7b-agent-0.3-merged
	tags:
	- gguf
	- starcoder
	- agentic-coding
	- tool-use
	- sft
	---

	# starcoder-7b-agent-0.5-gguf

	GGUF conversion of [Colby/starcoder-7b-agent-0.5](https://huggingface.co/Colby/starcoder-7b-agent-0.5),
	fine-tuned from [Colby/starcoder-7b-agent-0.3-merged](https://huggingface.co/Colby/starcoder-7b-agent-0.3-merged).

	v0.5 adds 6 special tokens (`<tool_call>`, `</tool_call>`, `<tool_response>`,
	`</tool_response>`, `<think>`, `</think>`) with dedicated embeddings (vocab 49162).

	Chat format: StarCoderChat with `<think>...</think>` and `<tool_call>`/`<tool_response>` blocks.

	## Quantizations

	\| File \| Format \| Size \|
	\|------\|--------\|------\|
	\| starcoder-7b-agent-0.5-f16.gguf \| FP16 \| ~14 GB \|
	\| starcoder-7b-agent-0.5-q8_0.gguf \| Q8_0 \| ~7 GB \|
	\| starcoder-7b-agent-0.5-q5_k_m.gguf \| Q5_K_M \| ~5 GB \|
	\| starcoder-7b-agent-0.5-q4_k_m.gguf \| Q4_K_M \| ~4 GB \|