Drop-in
transformers
repack of
EssentialAI/rnj-1.5-instruct
intended for quick inference tests, downstream software compatiblity (
transformers/torch itself, llama.cpp, etc
):
Upstream declares
layer_types: chunked_attention
, which
modeling_gemma3.py
doesn't implement - inference crashes with
KeyError: 'chunked_attention'
. This repo swaps those entries to
sliding_attention
so the model loads under stock
transformers
. Weights unchanged, resaved in bf16.
Sliding window (8192) is not identical to the original block-local attention - equivalent for prompts ~< 8192 tokens, divergent beyond that. For faithful long-context inference, use vLLM 0.20.0 against the upstream repo.
rnj-1.5-instruct huggingface.co is an AI model on huggingface.co that provides rnj-1.5-instruct's model effect (), which can be used instantly with this pszemraj rnj-1.5-instruct model. huggingface.co supports a free trial of the rnj-1.5-instruct model, and also provides paid use of the rnj-1.5-instruct. Support call rnj-1.5-instruct model through api, including Node.js, Python, http.
rnj-1.5-instruct huggingface.co is an online trial and call api platform, which integrates rnj-1.5-instruct's modeling effects, including api services, and provides a free online trial of rnj-1.5-instruct, you can try rnj-1.5-instruct online for free by clicking the link below.
pszemraj rnj-1.5-instruct online free url in huggingface.co:
rnj-1.5-instruct is an open source model from GitHub that offers a free installation service, and any user can find rnj-1.5-instruct on GitHub to install. At the same time, huggingface.co provides the effect of rnj-1.5-instruct install, users can directly use rnj-1.5-instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.