You can deploy this model and start earning money today!

Siddharth85/
kvbridge-qwen3-1.7b-to-qwen3-4b

Name: kvbridge-qwen3-1.7b-to-qwen3-4b
Availability: InStock

Views

No views yet

kvbridge Qwen3-1.7B -> Qwen3-4B (top_k=12)

A fitted KV cache mapper: it converts a Qwen3-1.7B KV cache into one Qwen3-4B can generate from, so the prompt is prefilled once on the small model instead of on the big one.

python

from kvbridge import Mapper, transfer

mapper = Mapper.from_pretrained("Siddharth85/kvbridge-qwen3-1.7b-to-qwen3-4b")
small_cache = small(prompt_ids, use_cache=True).past_key_values
big_cache = transfer(small_cache, mapper)
big.generate(input_ids=prompt_ids, past_key_values=big_cache, max_new_tokens=128)

Code, results and fitting instructions: https://github.com/Sidd03192/kvbridge

Fit on 500 FineWeb-Edu sequences x 1024 tokens, stride-4 subsampled, ridge lambda=0.01. Mean in-sample R^2: K 0.813, V 0.718. Weights are bfloat16.

Method: Cross-Model KV Cache Transfer in LLM Families (Heo et al., NVIDIA, arXiv:2608.03893).