fhai50032/RolePlayLake-7B

Full fine-tune vs SanjiWatsuki/Silicon-Maid-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1

4 derivatives checked

• mradermacher/RolePlayLake-7B-i1-GGUF: Quantization
• mradermacher/RolePlayLake-7B-GGUF: Same weights, converted
• fhai50032/BeagleLake-7B: Full fine-tune
• fhai50032/Mistral-4B: Partial fine-tune (fewer layers)

4 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse