mradermacher/Llama-2-7b-pruned70-retrained-gsm8k-GGUF

Same weights, converted vs RedHatAI/Llama-2-7b-gsm8k-pruned_70. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse