plan-and-act-planner-70b

Model overview

plan-and-act-planner-70b is published by xTRam1 as a Llama text-generation model. The captured configuration identifies LlamaForCausalLM with model type llama, and Safetensors metadata reports 70,553,706,496 parameters. Card data records the MIT license, Hub tags associate the record with meta-llama/Llama-3.3-70B-Instruct and the plan-and-act dataset, and the model card describes the Planner role in the Plan-and-Act framework.

Recorded capabilities

Use cases in the source record

• High-level plan generation for long-horizon agent tasks, as described in the Plan-and-Act framework paper.
• Web-navigation and LLM-agent planning research consistent with the planning, llm-agents, and web-navigation tagging.

Limitations and unknowns

• No evaluation results were extracted from this record.
• No context-window value was extracted from this record.
• No training epochs, hardware, or duration were extracted from this record.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: xTRam1/plan-and-act-planner-70b

Captured: Unknown. Processed: 2026-09-07T19:36:03.962603+00:00.

Plan-and-Act Planner 70B This is the Planner model used in the Plan-and-Act framework from the paper: Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks Code: https://github.com/SqueezeAILab/plan-and-act The Planner generates structured, high-level plans for long-horizon tasks. Usage from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_id = "xTRam1/plan-and-act-planner-70b" tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code= True ) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map= "auto" , trust_remote_code= True , ) prompt = "Goal:…