You can deploy this model and start earning money today!

hfunknown/
qwen3-8b-rule_diagnosis-lora-persistent

Name: qwen3-8b-rule_diagnosis-lora-persistent
Availability: InStock

Views

No views yet

qwen3-8b-rule_diagnosis-lora-persistent

Anonymous supplementary release for a double-blind workshop submission. This is one of four LoRA adapters (rule_diagnosis / navigation task family x persistent/stateless training regime), fine-tuned on the rule_diagnosis agentic task (online hypothesis-repair via probe/check() calls against a hidden boolean function). It is the second-family generalization arm alongside the primary Opaque Knapsack result (see the sibling Qwen3-8B knapsack release).

Base model: Qwen/Qwen3-8B
Training regime: persistent (trained with a persistent Python interpreter runtime (state carries over across agent turns))
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
lora_target_modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
learning_rate	1e-4
lr_scheduler	cosine
optimizer	adamw_torch
epochs	3.0
micro_batch_size	1
gradient_accumulation_steps	16
sequence_len	16384
sample_packing	false
seed	3407
training data	paired traces for the "persistent" regime on rule_diagnosis, see paper Appendix for pairing/filtering procedure

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.

hfunknown/qwen3-8b-rule_diagnosis-lora-persistent

qwen3-8b-rule_diagnosis-lora-persistent

Training configuration

Provenance

hfunknown/
qwen3-8b-rule_diagnosis-lora-persistent