Downloads · 30 days
42
52% of all-time downloads
tardellirs/cadif-lever-llama3.1-8b-noinst
cadif-lever-llama3.1-8b-noinst is a machine learning model from tardellirs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.1.
A LoRA adapter for Llama-3.1-8B, trained as the lesion arm: instruction blanked from the training query of the interventional arm of the CADIF study on instruction-following retrieval.
Downloads · 30 days
42
52% of all-time downloads
All-time downloads
81
Public
Repo size
12.1 GB
Likes
0
Public
Click a slice to open those files.
.pt4 GB · 63%
From the Hugging Face model README
A LoRA adapter for Llama-3.1-8B, trained as the lesion arm: instruction blanked from the training query of the interventional arm of the CADIF study on instruction-following retrieval.
The matched twin of instq: same rows, negatives, steps, schedule and seed, with the instruction removed from the training query. The dataset ships instructed and bare queries as separate columns over identical rows, so the lever is a string swap.
Scored through the CADIF assay on FollowIR's full 104-query census (pool 1000), this adapter records a composition contrast of Delta_comp = +0.0387. Delta_comp is the within-model contrast between the real instruction and a placebo that keeps every word and shuffles their order; it is pinned to exactly zero for a bag-of-words ranker by construction, so a positive value is evidence that word order was read rather than vocabulary matched.
Note that this arm is NOT at the lexical floor: +0.0387 has an interval excluding the exact zero, so contrastive training with hard negatives alone already installs some order sensitivity.
The census in the paper is observational. This arm makes it interventional: if a follower can be constructed on demand from a general-purpose base whose own Delta_comp is at the floor, then a null verdict elsewhere is a property of the system rather than an instrument failing to fire.
NousResearch/Meta-Llama-3.1-8B (ungated mirror of meta-llama/Llama-3.1-8B)train_group_size 16samaya-ai/msmarco-w-instructions, has_instruction subset, N=100k frozen at seed 42checkpoint-600A CADIF verdict is a property of a model under a prompt template, on a benchmark, at a pool depth, and all three move verdicts. Numbers above are FollowIR, pool 1000, under the template described in the paper. Do not transport the magnitude across pool depths without rescaling.
Derived from Meta's Llama-3.1-8B and therefore governed by the Llama 3.1 Community License. The name retains "llama3.1" as that licence requires for derivative models. Built with Llama.
See the CADIF paper and the released per-query arrays
(tardellirs/cadif-followir-results, DOI 10.57967/hf/9547) and code (DOI 10.5281/zenodo.21297047).