gbyuvd commited on
Commit
c84417f
·
verified ·
1 Parent(s): 8298ad5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -14,6 +14,9 @@ tags:
14
 
15
  ChemQ3MTP-base is a lightweight generative model for chemistry, trained on 2.33 million valid bioactive and natural product molecules dataset curated from ChemBL34, COCONUTDB, and SuperNatural3. It is built on a compact Qwen2-like transformer backbone and employs a multi-horizon predictive (MTP) loss objective to model molecular structures in SELFIES representation.
16
 
 
 
 
17
  Current version (0.1) (Lic for Code: MIT; Weights: Apache 2.0)
18
 
19
  A custom Qwen2-style language model, adapted for molecular generation:
 
14
 
15
  ChemQ3MTP-base is a lightweight generative model for chemistry, trained on 2.33 million valid bioactive and natural product molecules dataset curated from ChemBL34, COCONUTDB, and SuperNatural3. It is built on a compact Qwen2-like transformer backbone and employs a multi-horizon predictive (MTP) loss objective to model molecular structures in SELFIES representation.
16
 
17
+ Train Loss: 1.1720 → Perplexity: ~3.23
18
+ Validation Loss: 1.0448 → Perplexity: ~2.84
19
+
20
  Current version (0.1) (Lic for Code: MIT; Weights: Apache 2.0)
21
 
22
  A custom Qwen2-style language model, adapted for molecular generation: