Downloads · 30 days
82
14% of all-time downloads
scbe-coding-agent-vtc-qwen15-v1-gguf
issdandavis/scbe-coding-agent-vtc-qwen15-v1-gguf
scbe-coding-agent-vtc-qwen15-v1-gguf is a machine learning model from issdandavis. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Status: canonical. Current production candidate for the SCBE coding-agent lane. Held-out eval (n=6, identical harness): 5/6 functional, exactoutputonly 0/6 - 6/6 against base. Other scbe-coding- repos in this account…
All-time downloads
580
Public
Repo size
3.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf3.8 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jul 29, 2026
- SHA
- 10809064
Model card
From the Hugging Face model README
<!-- scbe-status -->
Status: canonical. Current production candidate for the SCBE coding-agent lane. Held-out eval (n=6, identical harness): 5/6 functional,
exact_output_only0/6 -> 6/6 against base. Otherscbe-coding-*repos in this account are research history and are taggedsuperseded.
SCBE Coding Agent — Qwen2.5-Coder-1.5B (VTC SFT) — GGUF
LoRA SFT of Qwen/Qwen2.5-Coder-1.5B-Instruct on 4,286 verified SCBE coding-agent trajectories (scbe-coding-agent-sft-full-coding-system-v8). Adapter: issdandavis/scbe-coding-agent-vtc-qwen15-v1.
Eval gate (held-out generic coding, n=6, identical harness across models)
| model | functional | format | exact_output_only |
|---|---|---|---|
| base-1.5b | 5/6 | 6/6 | 0/6 |
| vtc-qwen05-v1 | 3/6 | 6/6 | 6/6 |
| vtc-qwen15-v1 | 5/6 | 6/6 | 6/6 |
The fine-tune matches base correctness (5/6) while learning the bare-code output contract: exact_output_only 0/6 → 6/6 (base wraps every answer in markdown fences; the fine-tune emits pure code). This is the agent-relevant win — consistent with the Superficial Alignment Hypothesis (capability from pretraining, format/contract from SFT).
Files
scbe-coding-agent-vtc-qwen15-v1.Q4_K_M.gguf— Q4_K_M, recommended for Ollama on ≈12GB RAMscbe-coding-agent-vtc-qwen15-v1.Q5_K_M.gguf— Q5_K_M, higher qualityscbe-coding-agent-vtc-qwen15-v1.Q8_0.gguf— near-losslessModelfile— points at Q4_K_M
Ollama
hf download issdandavis/scbe-coding-agent-vtc-qwen15-v1-gguf --local-dir scbe-qwen15
cd scbe-qwen15 && ollama create scbe-coder -f Modelfile
ollama run scbe-coder "Write a Python function add(a, b). Return ONLY the code."
- Created
- Jun 27, 2026
- Updated
- Jul 29, 2026