---
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 |