evenfarther
/

Qwen3-14b-chemical-synthesis-adapter

Model card Files Files and versions

evenfarther commited on Sep 20

Commit

4adb946

·

verified ·

1 Parent(s): 8e560d3

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ The base checkpoint is Unsloth’s 4-bit MXFP4 build (`unsloth/Qwen3-14B-unsloth
 - Task: Binary classification (P = synthesizable, U = unsynthesizable)
 - Training Objective: QLoRA with focal loss (gamma = 2.0, alpha_P = 8.12, alpha_U = 1.0)
 - Max Sequence Length (train): 2048 tokens; Evaluation: 180 tokens
-- Dataset: 316,442 train (`train_pu_hem_v2.jsonl`) / 79,114 validation (`validate_pu_hem_v2.jsonl`) samples (~11% P / 89% U)
 - Adapter Size: ~981 MB (`adapter_model.safetensors`)
 ### Prompt & Thinking Prefill

 - Task: Binary classification (P = synthesizable, U = unsynthesizable)
 - Training Objective: QLoRA with focal loss (gamma = 2.0, alpha_P = 8.12, alpha_U = 1.0)
 - Max Sequence Length (train): 2048 tokens; Evaluation: 180 tokens
+- Dataset: 316,442 train (`train_pu_hem.jsonl`) / 79,114 validation (`validate_pu_hem.jsonl`) samples (~11% P / 89% U)
 - Adapter Size: ~981 MB (`adapter_model.safetensors`)
 ### Prompt & Thinking Prefill