Downloads · 30 days
54
56% of all-time downloads
tardellirs/cadif-lever-llama3.1-8b-full
cadif-lever-llama3.1-8b-full 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 full recipe (positive control) of the interventional arm of the CADIF study on instruction-following retrieval.
Downloads · 30 days
54
56% of all-time downloads
All-time downloads
97
Public
Repo size
7 GB
Likes
0
Public
Click a slice to open those files.
.pt4.7 GB · 64%
From the Hugging Face model README
A LoRA adapter for Llama-3.1-8B, trained as the full recipe (positive control) of the interventional arm of the CADIF study on instruction-following retrieval.
Trained with the full instance-level recipe: each training example carries its own relevance-defining instruction, with instruction-conditioned negatives.
Scored through the CADIF assay on FollowIR's full 104-query census (pool 1000), this adapter records a composition contrast of Delta_comp = +0.1176 , 95% bootstrap CI [+0.0757, +0.1603]. 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.
This is the arm the paper reports as its known-groups positive control. It stopped at step 700 of a 782-step epoch (89.5%), so the value is a lower bound on what the recipe reaches.
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-700A 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).