laion/Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k
The Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k model by laion is an 8 billion parameter language model fine-tuned from Qwen/Qwen3-8B. It was trained on the open-athena/Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k_neulab-agenttuning-kg-sandboxes dataset, featuring a context length of 32768 tokens. This model is specifically adapted for tasks related to agent tuning and knowledge graph sandboxes, leveraging its base architecture for enhanced performance in these specialized domains.
Loading preview...
Model Overview
The Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k is an 8 billion parameter language model developed by laion. It is a fine-tuned variant of the Qwen/Qwen3-8B base model, specifically adapted for specialized applications. The model was trained using the open-athena/Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k_neulab-agenttuning-kg-sandboxes dataset, indicating a focus on agent tuning and knowledge graph sandbox environments.
Training Details
The fine-tuning process utilized a learning rate of 4e-05 with an AdamW optimizer. Training was conducted across 8 GPUs with a total batch size of 16, accumulating gradients over 2 steps. A cosine learning rate scheduler with a 0.1 warmup ratio was employed over 7 epochs. The model supports a substantial context length of 32768 tokens, which is beneficial for tasks requiring extensive contextual understanding.
Intended Use
While specific intended uses and limitations are not detailed, the model's training dataset suggests its primary application areas involve:
- Agent Tuning: Potentially for optimizing AI agent behaviors or responses.
- Knowledge Graph Sandboxes: Likely for tasks within simulated or experimental knowledge graph environments, such as data extraction, reasoning, or interaction.
Further evaluation is needed to fully understand its performance characteristics and optimal use cases.