Views
No views yet
This is NOT my model. All weights and training are by DeepReinforce (deepreinforce-ai/Ornith-1.0-9B). This is an independent repack that fixes one packaging bug and adds an honest third-party evaluation. No weights were modified.
tokenizer.chat_template. As a result, Ollama and llama.cpp fall back to a raw passthrough template ({{ .Prompt }}), the model never sees its ChatML format, and it degenerates into repetition loops — input tokens freeze, the same phrase repeats, the agent never acts.chat_template.jinja into the file metadata, so it works out-of-the-box in Ollama (auto-detected) and llama.cpp (--jinja). A bug-report note is also embedded in general.description.tokenizer.chat_template to your official GGUF exports — it's a one-line metadata fix that makes the GGUFs usable.| model | SWE | note |
|---|---|---|
| base Qwen3.5-9B | 1/6 | baseline |
| Ornith-1.0-9B | 2/6 | real fine-tune, beats base |
NRS_QWEN_MYTHOS_1M ("100x reasoning" hype) | 0/6 | hype, worse than base |
| Ornith-9B, only the change shown | result |
|---|---|
| temp 0.1, raw template | 0/6 (repetition loops) |
| temp 1.0 + this fixed template | 2/6 (healthy) |
⚠️ These are relative numbers on a tiny probe — NOT comparable 1:1 to DeepReinforce's official 69.4 SWE-bench Verified (measured on the OpenHands harness with their<function=>tool format, temp 1.0, top_p 0.95). Use the official numbers for leaderboard comparison. The point here is: the model works once configured right.
FINDINGS.md.1ollama run hf.co/KikoCis/Ornith-1.0-9B-Ollama-fixed-GGUF
2# or: ollama create ornith -f Modelfile && ollama run ornithllama-server -m ornith-1.0-9b-Q8_0-fixed.gguf --jinja -c 32768temperature 1.0, top_p 0.95. Low temperature (e.g. 0.1) causes repetition loops on this model — use ~1.0.chat_template.jinja: © DeepReinforce — Ornith-1.0, GrandCode paper, deep-reinforce.com.chat_template, general.description) added.