jaspionjader/Kosmos-EVAA-PRP-8B

Full fine-tune vs Gryphe/Pantheon-RP-1.0-8b-Llama-3. 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

3 derivatives checked

• mradermacher/Kosmos-EVAA-PRP-8B-i1-GGUF: Quantization
• mradermacher/Kosmos-EVAA-PRP-8B-GGUF: Same weights, converted
• jaspionjader/Kosmos-EVAA-PRP-light-8B: Full fine-tune

On the Hub · Downloads on Model Pulse