Modelpublic

hfunknown/llama31-8b-knapsack-lora-stateless

sourceHugging Faceupdated 1mo agoView on Hugging Face

0likes1.2kdownloads

Model Card

llama31-8b-knapsack-lora-stateless

Anonymous supplementary release for a double-blind workshop submission. This is one of four LoRA adapters (Mistral-7B-v0.3 / Llama-3.1-8B base model x persistent/stateless training regime) fine-tuned on the Opaque Knapsack agentic task, extending a prior single-base-model result (see the sibling Qwen3-8B release) to a second base model family for the same reproducibility review.

—Base model: meta-llama/Llama-3.1-8B
—Training regime: stateless (trained with a stateless Python interpreter runtime (interpreter state is reset every agent turn))
—Seed: 3407

Training configuration

Fine-tuned with Axolotl, LoRA adapter, 4-bit NF4 quantized base:

Hyperparameter	Value
lora_r	64
lora_alpha	128
lora_dropout	0.05
loratargetmodules	qproj, kproj, vproj, oproj, gateproj, upproj, down_proj
learning_rate	1e-4
lr_scheduler	cosine
optimizer	adamw_torch
epochs	3.0
microbatchsize	1
gradientaccumulationsteps	16
sequence_len	16384
sample_packing	false
seed	3407
training data	paired traces for the "stateless" regime (see paper Appendix for pairing/filtering procedure)

Base checkpoint's own chat-format tokens (e.g. <|eot_id|>) are untrained on this base (non-instruct) checkpoint -- trained and served with a hand-written minimal template using only real trained tokens (BOS/EOS + plain-text role prefixes), not Llama's native instruct template.

Provenance

Released anonymously alongside a NeurIPS workshop submission for reproducibility review. Non-anonymous release (paper citation, full code, full training traces) will follow after the review process concludes.