models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-uncensored-heretic-GGUFnesso-0.4B-agenticgemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-uncensored-hereticllm-agents_tora-code-7b-v1.0-GGUFtora-code-7b-v1.0nesso2-0.4B-agentictora-7b-v1.0tora-code-13b-v1.0tora-code-34b-v1.0tora-70b-v1.0Fabliq-8B-Agent-Reasoningtora-13b-v1.0Fabliq-8B-Agent-FromBase-ReasoningFabliq-8B-AgentFabliq-8B-Agent-FromBaseLlama-3.2-3B-Instruct-sft-alfworld-iter0LFM2.5-8B-A1B-KO-Agentic-SFTmatsuo-llm-advanced-household-agentdiag_agent_deepseek-llm-7b-basehotpotqa-agent-sft-llmQwen2.5-4B-AgentBench-llm2025_v10_silentLlama-3.2-3B-Instruct-online-dpo-alfworld-iter1exp-0223-027-realobs-llmagent-qwen2.5-7bLlama-3.1-8B-Instruct-sft-alfworld-iter0llm-chess-agent-v2Llama-3.2-3B-Instruct-sft-alfworld-leap-iter1LFM2.5-8B-A1B-KO-Legal-RAG-Agentic-LoRA-v5llmagent4incident-responsellm-chess-agent-v3-half-trainingqwen3-4b-agent-trajectory-lora-202602182321
