Views
No views yet
ornith-ai/Ornith-1.5-9B for ExLlamaV3 / TabbyAPI.| Branch | Decoder | lm_head | Size | Notes |
|---|---|---|---|---|
main / 4.0bpw | 4.0 | 6 | 6.8 G | Default. Fits a 24 GB card with context. |
5.0bpw | 5.0 | 6 | 7.6 G | Extra quality vs 4.0. |
6.0bpw | 6.0 | 6 | 8.4 G | Highest of the three. Two shards. |
1oxfrug/Ornith-1.5-9B-exl3 # 4.0 on main
2oxfrug/Ornith-1.5-9B-exl3:4.0bpw
3oxfrug/Ornith-1.5-9B-exl3:5.0bpw
4oxfrug/Ornith-1.5-9B-exl3:6.0bpw| Tool | ExLlamaV3 convert.py |
| Cal | 250 rows × 2048 cols (library default) |
| Codebook | mul1 |
| Vision | stored unquantized (16-bit) |
| MTP | not included — base config.json sets mtp_num_hidden_layers: 1 but the published safetensors have no mtp.* tensors |
lambda x: x ** 2 — correctis_even(n) with docstring — correct<think>…</think> as designed. These are not the official BF16 agentic scores from the base card.temperature=0.6, top_p=0.95; general temperature=1.0, presence_penalty=1.5. Tool parser: Qwen3 XML.