mradermacher/lumichats_4Bz_v1.4-GGUF

Same weights, converted (fewer layers) vs adityakum667388/lumichats_4Bz_v1.4. mradermacher/lumichats_4Bz_v1.4-GGUF matches part of adityakum667388/lumichats_4Bz_v1.4 (444 of its 883 tensors; the rest of adityakum667388/lumichats_4Bz_v1.4 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse