mradermacher/TinySolar-248m-4k-code-instruct-GGUF

Same weights, converted vs upstage/TinySolar-248m-4k-code-instruct. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/48

On the Hub · Downloads on Model Pulse