Downloads · 30 days
4
13% of all-time downloads
qwen3-8b-knapsack-lora-persistent-seed3407
hfunknown/qwen3-8b-knapsack-lora-persistent-seed3407
qwen3-8b-knapsack-lora-persistent-seed3407 is a text generation model from hfunknown. Use it when you need the model to write or continue text. It is set up for peft.
Anonymous supplementary release for a double-blind workshop submission. This is one of six LoRA adapters (persistent/stateless training regime x 3 seeds) fine-tuned on the Opaque Knapsack agentic task.
All-time downloads
30
Public
Repo size
710 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors698 MB · 98%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026
- SHA
- 170c8461
Try a prompt
Base models
Model card
From the Hugging Face model README
qwen3-8b-knapsack-lora-persistent-seed3407
Anonymous supplementary release for a double-blind workshop submission. This is one of six LoRA adapters (persistent/stateless training regime x 3 seeds) fine-tuned on the Opaque Knapsack agentic task.
- 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 0.13.2, 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 (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.
- Task
- Text Generation
- Library
- peft
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026