AI is happening. The future is updating.Llama-3.2-3B-Instruct-NEO-SI-FI-GGUF
It is the new "Llama-3.2-3B-Instruct", max context of 131,000 (128k) with the NEO IMATRIX Science Fiction and Story dataset. The power in this 3B (for its size) is frankly jaw dropping... and at 90 tokens per second + on a GPU. This is a LLAMA 3.2 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 128k.
It is the new "Llama-3.2-3B-Instruct", max context of 131,000 (128k) with the NEO IMATRIX Science Fiction and Story dataset. The power in this 3B (for its size) is frankly jaw dropping... and at 90 tokens per second + on a GPU. This is a LLAMA 3.2 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 128k.