Downloads · 30 days
5
15% of all-time downloads
ornith-1.5-9b-spreadsheetbench-merged
ciocan/ornith-1.5-9b-spreadsheetbench-merged
ornith-1.5-9b-spreadsheetbench-merged is a machine learning model from ciocan. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
The merged weights of ciocan/ornith-1.5-9b-spreadsheetbench-lora applied to ornith-ai/Ornith-1.5-9B, as served for Ambit Labs' Ylookup x Encode hackathon entry. Harness, data recipe, evaluation and write-up: https://g…
All-time downloads
33
Public
Parameters
9B
17.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.9 GB · 100%
At a glance
- License
- mit
- Model type
- qwen3_5_text
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- 8c79162e
Base models
Model card
From the Hugging Face model README
Ornith 1.5 9B, SpreadsheetBench LoRA fine-tune, merged bf16 weights
The merged weights of ciocan/ornith-1.5-9b-spreadsheetbench-lora applied to ornith-ai/Ornith-1.5-9B, as served for Ambit Labs' Ylookup x Encode hackathon entry. Harness, data recipe, evaluation and write-up: https://github.com/Ambit-Labs/hacks-enyl-research.
Serve with vLLM 0.28:
vllm serve <this repo> --served-model-name Ornith-9B-ft \
--tool-call-parser qwen3_xml --reasoning-parser qwen3 --enable-auto-tool-choice \
--max-model-len 32768 --trust-remote-code
Use chat_template_kwargs: {"enable_thinking": false} for structured tool calls at temperature 0. Results and caveats are on the adapter's model card.
- Type
- qwen3_5_text
- License
- mit
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026