laion/exp-uns-tezos-160x_glm_4_7_traces_jupiter_cleaned
The laion/exp-uns-tezos-160x_glm_4_7_traces_jupiter_cleaned model is an 8 billion parameter language model, fine-tuned from Qwen/Qwen3-8B. It was trained on the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent--exp-uns-tezos-160x_glm_4.7_traces_jupiter_cleaned/snapshots/38cee1e75c594948b11cc76e2fa13ac8984ee151_thinking_preprocessed dataset. This model is a specialized fine-tune, indicating potential optimization for tasks related to the specific dataset it was trained on, with a context length of 32768 tokens.
Loading preview...
Overview
This model, laion/exp-uns-tezos-160x_glm_4_7_traces_jupiter_cleaned, is an 8 billion parameter language model derived from the Qwen/Qwen3-8B architecture. It has been specifically fine-tuned on a unique dataset: /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent--exp-uns-tezos-160x_glm_4.7_traces_jupiter_cleaned/snapshots/38cee1e75c594948b11cc76e2fa13ac8984ee151_thinking_preprocessed. The training process involved 7 epochs with a learning rate of 4e-05 and a total batch size of 16 across 8 GPUs, utilizing a cosine learning rate scheduler with a 0.1 warmup ratio.
Key Training Details
- Base Model: Qwen/Qwen3-8B
- Parameter Count: 8 Billion
- Context Length: 32768 tokens
- Fine-tuning Dataset: A specialized dataset, suggesting domain-specific adaptation.
- Hyperparameters:
- Learning Rate: 4e-05
- Optimizer: ADAMW_TORCH_FUSED
- Epochs: 7.0
- Gradient Accumulation Steps: 2
Potential Use Cases
Given its fine-tuning on a specific dataset, this model is likely optimized for tasks related to the content and structure of that particular data. Developers should evaluate its performance on tasks that align with the characteristics of the exp-uns-tezos-160x_glm_4.7_traces_jupiter_cleaned dataset to determine its suitability.