gliclass-v4
3 TagsUpdated Apache-2.0by Knowledgator
Knowledgator's GLiClass v4, the decoder-KV generation: a Qwen3.5 decoder (2B or 9B) reads the instructions, the state and the labels in one row, a two-layer scorer with up to three reasoning steps scores every label against the text, and the model's own calibrator rescales the logits. Up to 8k-token rows. Text only.
decisionlong-contextfine-tuned2.4b9.5b
Tags
| Name |
|---|
| gliclass-v4latestSame as gliclass-v4:2b.4.8 GB · 8192 ctx · English |
| gliclass-v4:2bgliclass-v4-2b (decoder-KV on Qwen3.5-2B, 2.4B weights read), fp32 compute on BF16 weights: about 7 GB in memory.4.8 GB · 8192 ctx · English |
| gliclass-v4:9bgliclass-v4-9b (decoder-KV on Qwen3.5-9B, 9.5B weights read): about 20 GB in memory.18.0 GB · 8192 ctx · English |
Tags without a suffix load fp16 on a CUDA GPU and fp32 on CPU; add -fp16 or -fp32 to pin one precision.