KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
Full fine-tune vs HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 48/49, MLP 72/72, Attention 168/168
3 derivatives checked
- Aashraf995/KaLM-embedding-multilingual-mini-instruct-v2.5-Q8_0-GGUF: Quantization
- mradermacher/KaLM-embedding-multilingual-mini-instruct-v2.5-GGUF: Same weights, converted
- HIT-TMG/JevEmbed-KaLM-Embedding-V2.5: LoRA-style