Update README.md

README.md

@@ -12,7 +12,7 @@ pipeline_tag: text-generation
 
 # Qwen3-1.7B (from-scratch, 41B-token pretrain)
 
-A 1.7B-parameter decoder-only transformer (Qwen3 family) pre-trained **from scratch** on ~**41B tokens** of multi-domain text with **BF16 mixed precision** and a **4,096-token** context. Checkpoints are provided in standard Hugging Face format for easy inference and fine-tuning.
+A 1.7B-parameter decoder-only transformer (Qwen3 family) pre-trained **from scratch** on ~**40B tokens** of multi-domain text with **BF16 mixed precision** and a **4,096-token** context. Checkpoints are provided in standard Hugging Face format for easy inference and fine-tuning.
 
 ---
 
@@ -30,7 +30,7 @@ A 1.7B-parameter decoder-only transformer (Qwen3 family) pre-trained **from scra
 ### Model Sources
 
 - **Repository:** https://huggingface.co/qvac/genesisI-model
-- **Paper / Blog :** Coming Soon
+- **Paper / Blog :** https://huggingface.co/blog/qvac/genesis-i
 
 ---
 
@@ -104,7 +104,7 @@ print(tok.decode(out[0], skip_special_tokens=True))
 
 ### Training Data
 
-* **Size:** ~**41B tokens**, single epoch.
+* **Size:** ~**40B tokens**, single epoch.
 * **Domains:** Mixed general + STEM/technical sources (expository text, problem sets, references).
 * **Format:** Hugging Face Datasets (Arrow).
 * **Tokenizer:** **Qwen3** tokenizer.
@@ -262,27 +262,7 @@ srun -N 60 -n 480 --ntasks-per-node=8 --gpus-per-task=1 \
 
 ---
 
-## Citation
-
-If you use this model, please cite:
-
-**BibTeX**
-
-Xxxx
-
-**APA**
-
-xxxxxx
-
----
-
-
-## Model Card Authors
-
-XXXYYYYZZZ
-
----
 
 ## Changelog
 
-* **v0.1 (YYYY-MM-DD):** Initial public release — 41B-token 1-epoch pretrain; HF conversion.
+* **v0.1 (2025-11-17):** Initial public release — 40B-token 1-epoch pretrain; HF conversion.