You can deploy this model and start earning money today!

hfunknown/
mistral-7b-knapsack-lora-persistent

Name: mistral-7b-knapsack-lora-persistent
Availability: InStock

mistralai/Mistral-7B-v0.3

adapter

Views

No views yet

mistral-7b-knapsack-lora-persistent

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: mistralai/Mistral-7B-v0.3
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 (see paper Appendix for pairing/filtering procedure)

Mistral-7B-v0.3 ships no chat_template -- trained with Axolotl's built-in mistral_v2v3 template; serving/eval uses a hand-written template extending it with system-role support (folded into the next user turn, since mistral_v2v3 only accepts user/assistant).

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/mistral-7b-knapsack-lora-persistent

mistral-7b-knapsack-lora-persistent

Training configuration

Provenance

hfunknown/
mistral-7b-knapsack-lora-persistent