DCAgent/g1_diverse_tezos_100k_32b
DCAgent/g1_diverse_tezos_100k_32b is a 32 billion parameter language model fine-tuned from Qwen/Qwen3-32B. This model is specifically adapted using a diverse Tezos dataset, focusing on specialized domain understanding. It is optimized for tasks related to the Tezos blockchain ecosystem, leveraging its fine-tuning on specific traces and data.
Loading preview...
Overview
DCAgent/g1_diverse_tezos_100k_32b is a 32 billion parameter language model, fine-tuned from the robust Qwen3-32B architecture. This model has undergone specialized training on a unique dataset, /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--g1_diverse_tezos_top4_100k_glm47_traces, indicating a focus on the Tezos blockchain domain.
Key Characteristics
- Base Model: Qwen/Qwen3-32B, a powerful foundation for language understanding.
- Parameter Count: 32 billion parameters, offering significant capacity for complex tasks.
- Fine-tuning Data: Specialized dataset derived from diverse Tezos traces, suggesting expertise in Tezos-related information.
- Training Hyperparameters: Utilized a learning rate of 4e-05, a total batch size of 96 across 96 devices, and trained for 5 epochs with a cosine learning rate scheduler.
Intended Use Cases
This model is likely best suited for applications requiring deep understanding or generation of content related to the Tezos blockchain. Its fine-tuning on specific Tezos traces implies enhanced performance for:
- Analyzing Tezos smart contracts or transactions.
- Generating documentation or explanations for Tezos-specific concepts.
- Assisting with development or queries within the Tezos ecosystem.