laion/Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jan 18, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The laion/Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k model is an 8 billion parameter language model, fine-tuned from Qwen/Qwen3-8B. It is specifically adapted using the open-athena/Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k_neulab-agenttuning-db-sandboxes dataset. This model is optimized for agent tuning within sandbox environments, leveraging a 32K token context length. Its primary strength lies in its specialized fine-tuning for specific agent-based tasks.

Loading preview...

Model Overview

This model, laion/Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k, is an 8 billion parameter language model derived from Qwen/Qwen3-8B. It has been fine-tuned on the open-athena/Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k_neulab-agenttuning-db-sandboxes dataset, indicating a specialization in agent-tuning tasks within sandbox environments.

Key Characteristics

  • Base Model: Qwen3-8B architecture.
  • Context Length: Supports a context window of 32,768 tokens.
  • Fine-tuning Focus: Specialized for agent-tuning, likely involving interaction with web-based or sandbox environments as suggested by the dataset name.

Training Details

The model was trained with a learning rate of 4e-05, using a total batch size of 16 (1 per device across 8 GPUs with 2 gradient accumulation steps) over 7 epochs. The optimizer used was ADAMW_TORCH_FUSED with cosine learning rate scheduling and a 0.1 warmup ratio.

Potential Use Cases

  • Developing and testing AI agents in simulated or sandbox environments.
  • Tasks requiring understanding and interaction within structured digital interfaces.
  • Applications benefiting from a model specifically tuned for agentic behavior and decision-making.