Hugging Face's logo

evenfarther
/
DeepSeek-R1-Distill-Qwen-14b-chemical-synthesis-adapter-high-TPR

PEFT
Safetensors
English
chemistry
synthesis
classification
deepseek-r1
qwen
qlora
Model card Files
xet
 Community
evenfarther commited on
Commit
ef364ba
·
verified ·
1 Parent(s): b465df7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -30,7 +30,7 @@ This repository contains the LoRA adapter for a DeepSeek‑R1‑Distill‑Qwen
30
  - Dataset (train): `train_pu_hem.jsonl` (316,442 samples)
31
  - Dataset (val): `validate_pu_hem.jsonl` (79,114 samples)
32
  - Adapter size: ~1.10 GB (`adapter_model.safetensors`)
33
- - Checkpoint: Epoch 2 — `checkpoint-496` (best Balanced Accuracy among evaluated epochs)
34
 
35
  The checkpoint includes a `chat_template.jinja` to ensure prompt formatting matches SFT conditions.
36
 
 
30
  - Dataset (train): `train_pu_hem.jsonl` (316,442 samples)
31
  - Dataset (val): `validate_pu_hem.jsonl` (79,114 samples)
32
  - Adapter size: ~1.10 GB (`adapter_model.safetensors`)
33
+ - Checkpoint: Epoch 2 — `checkpoint-496` (best TPR among evaluated epochs)
34
 
35
  The checkpoint includes a `chat_template.jinja` to ensure prompt formatting matches SFT conditions.
36