Upload folder using huggingface_hub

6439bd4 verified about 2 months ago

1.34 kB

license: apache-2.0
base_model: allenai/OLMo-2-1124-7B-Instruct
tags:
  - stem
  - mathematics
  - olympiad-physics
  - qlora
  - unsloth
  - trl
  - 4-bit
pipeline_tag: text-generation

Specialist 1: OLMo-2-13B Pure Astronomy & Scientific Logic

Model Summary

Base Architecture: allenai/OLMo-2-1124-7B-Instruct
Quantization: 4-bit NormalFloat4 (NF4) with Double Quantization (BitsAndBytesConfig)
LoRA Configuration: $r=64$, $\alpha=128$, dropout=0.05, 7 linear projection targets (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj)
Loss Masking: Prompt loss masking (train_on_inputs: false) via DataCollatorForCompletionOnlyLM
Training Datasets: shreyansh12183/qwen-72b-sovereign-stem-master-500k (Math/Physics) + allenai/tulu-3-sft-mixture
Target Repository: shreyansh12183/olmo2-7b-astro-logic (100% PRIVATE 🔒)

Live 5-Prompt Benchmark Results

#	Domain / Problem	Status
1	Keplers Third Law Derivation	PASSED
2	Schwarzschild Horizon	PASSED
3	Resolution Inference Proof	PASSED
4	Hubble Expansion Formulation	PASSED
5	Halting Problem Undecidability	PASSED

Zero Cloud Spend Compliance

Trained 100% on Kaggle Dual Tesla T4 GPUs (NvidiaTeslaT4x2).
AWS Spend: $0.00.