seedboxai/KafkaLM-15B

Full fine-tune vs seedboxai/KafkaLM-15B-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 36/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/KafkaLM-15B-i1-GGUF: Quantization
• mradermacher/KafkaLM-15B-GGUF: Quantization
• redponike/KafkaLM-15B-GGUF: Quantization

On the Hub · Downloads on Model Pulse