Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
Tülu 3 with tool call support
A model finetuned from llama3.1, developed by allenai
num_ctx=131072
This model was created with the goal for a good llama 3 uncencored model with long context. At it worked like a charm.
4 million long context window model built on Llama-3.1.
2 million long context window model built on Llama-3.1.
llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF
Llama 3.1 8B Instruct trained on 9,000,000 Claude Opus/Sonnet tokens
Fine-tuned manim model using Qwen2.5-Coder-14B-Instruct trained on 3blue1brown-manim dataset with 2,407 examples.
PLTA's Fine-tune converted to Ollama model for ease of use. It's a Fine-tune of LlaMa 3.1 8B.
watt-tool-8B is a fine-tuned language model based on LLaMa-3.1-8B-Instruct, optimized for tool usage and multi-turn dialogue. It achieves state-of-the-art performance on the Berkeley Function-Calling Leaderboard (BFCL).
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).
quantized DRXD1000/Phoenix - which was trained with german dpo (ultrachat_200k & ultrafeedback_binarized transl. by haoranxu/ALMA-13B) based on LeoLM/leo-mistral-hessianai-7b
watt-tool-8B is a fine-tuned language model based on LLaMa-3.1-8B-Instruct, optimized for tool usage and multi-turn dialogue.
Tess-v2.5 (Qwen2-72B) was fine-tuned over the newly released Qwen2-72B base, using the Tess-v2.5 dataset that contain 300K samples spanning multiple topics.