laion/exp-gfi-staqc-askllm-filtered-10K_glm_4_7_traces_jupiter_cleaned

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Feb 26, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The laion/exp-gfi-staqc-askllm-filtered-10K_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-gfi-staqc-askllm-filtered-10K_glm_4.7_traces_jupiter_cleaned/snapshots/6b97b7d8d3baf1c49d01353ea2647df88727ddd8_thinking_preprocessed dataset. This model is designed for specific applications related to its fine-tuning data, offering a 32768 token context length.

Loading preview...

Model Overview

This model, laion/exp-gfi-staqc-askllm-filtered-10K_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-gfi-staqc-askllm-filtered-10K_glm_4.7_traces_jupiter_cleaned/snapshots/6b97b7d8d3baf1c49d01353ea2647df88727ddd8_thinking_preprocessed, suggesting a specialization for tasks related to the content of this training data.

Key Training Details

The fine-tuning process involved the following hyperparameters:

  • Learning Rate: 4e-05
  • Batch Size: 1 (train), 8 (eval)
  • Gradient Accumulation Steps: 2, leading to a total train batch size of 16
  • Optimizer: ADAMW_TORCH_FUSED
  • LR Scheduler: Cosine type with a 0.1 warmup ratio
  • Epochs: 7.0

The model was trained using Transformers 4.57.6, Pytorch 2.9.0+cu128, Datasets 4.4.1, and Tokenizers 0.22.2.

Intended Use

Given its fine-tuning on a specific dataset, this model is likely intended for applications that align with the characteristics and domain of its training data. Users should consider the nature of the exp-gfi-staqc-askllm-filtered-10K_glm_4.7_traces_jupiter_cleaned dataset when evaluating its suitability for their specific use cases.