Upload Telugu GPT-MoE Sangraha 10k checkpoint

README.md

@@ -40,9 +40,12 @@ It is a research/personal pretraining checkpoint, not an instruction-tuned assis
 - Experts: 4 experts, top-1 routing
 - Attention backend: PyTorch SDPA / FlashAttention when available
 - Vocabulary size: 68,096
+- Unique parameters: 297,720,576 (~298M)
+- Raw tied state-dict parameters: 350,018,304
+- Weight format: `model.safetensors`
 - Tokenizer: pre-existing Sarvam tokenizer files saved with the checkpoint
 
-This is a custom PyTorch architecture. It is **not** loadable as a stock Hugging Face `AutoModelForCausalLM` model without the included model code.
+This is a custom PyTorch architecture. It loads through Hugging Face Auto classes with `trust_remote_code=True`.
 
 ## Training Data
 

pytorch_model.bin → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe513c799a9b37f425684c05c8b4a30d8caf67b30b22ddc6202781aa6bddf1b
-size 1190958203
+oid sha256:242a4efe0db8e7d689ae31612eedd3a57ebd563a3c32fb65a04a7ffbe33c0303
+size 1190901944