robit/ qwen3.5-9b-r7-research-vision:q4km

73 3 days ago

Fine-tuned Qwen3.5-9B with distilled reasoning and full vision support. 883 tensors (427 text + 441 vision + 15 MTP) — vision tower preserved byte-for-byte from base via llama-export-lora merge.

vision tools thinking
... /
params
b19632edf522 · 82B
{
"num_ctx": 262144,
"stop": [
"<|im_end|>"
],
"temperature": 0.6,
"top_p": 0.95
}