YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Sagheer-100M-Instruct

Converted from the 100mVast custom checkpoint to HuggingFace Transformers LlamaForCausalLM format for leaderboard benchmarking.

Note: The original model uses QK-norm, which is not available in the standard Llama architecture. This converted checkpoint therefore runs without QK-norm, so outputs may differ slightly from the native checkpoint.

Downloads last month
13
Safetensors
Model size
99.8M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support