tensorblock/tiny-random-starcoder2-GGUF

Quantization vs hyper-accel/tiny-random-starcoder2. tensorblock/tiny-random-starcoder2-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 22 tensors match exactly and 14 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/10, MLP 0/8, Attention 0/16

On the Hub · Downloads on Model Pulse