watt-tool-70B is a fine-tuned language model based on LLaMa-3.3-70B-Instruct, optimized for tool usage and multi-turn dialogue. It achieves state-of-the-art performance on the Berkeley Function-Calling Leaderboard (BFCL).
1,281 Pulls 1 Tag Updated 1 year ago
I-quants for llama-3.3-70b-instruct
649 Pulls 11 Tags Updated 1 year ago
llama-3-taiwan(70B-Instruct, 70B-Instruct-DPO, 70B-Instruct-128k, 8B-Instruct, 8B-Instruct-DPO) (FP16, Q8_0, Q6_K, Q5_1, Q5_0, Q5_K_M, Q5_K_S, Q4_1, Q4_0, Q4_K_M, Q3_K_L, Q4_K_S, Q3_K_M, Q3_K_S)
3,289 Pulls 70 Tags Updated 1 year ago
I-quants for meta-llama-3.1-70b-instruct-abliterated
927 Pulls 6 Tags Updated 1 year ago
The model used is a quantized version of `Llama-3-Taiwan-70B-Instruct`. More details can be found on the website (https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct)
370 Pulls 11 Tags Updated 1 year ago
I-quants for llama-3.1-nemotron-70b-instruct-hf
249 Pulls 7 Tags Updated 1 year ago