HerrHruby/mr_midtrained_9b_v3_async_v2_cispo_step_150
VISIONConcurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 11, 2026Architecture:Transformer Featherless Exclusive Cold
HerrHruby/mr_midtrained_9b_v3_async_v2_cispo_step_150 is a 9 billion parameter language model, initialized from HerrHruby/MR_midtrain_9B_v3 and further trained for 150 steps. This checkpoint is specifically designed for inference and evaluation tasks. With a context length of 32768 tokens, it offers robust performance for applications requiring extensive context understanding.
Loading preview...
Overview
HerrHruby/mr_midtrained_9b_v3_async_v2_cispo_step_150 is a 9 billion parameter language model, representing a specific checkpoint (step 150) from the wdblemve training run. It was initialized from the HerrHruby/MR_midtrain_9B_v3 model, indicating a continuation of a pre-existing training process.
Key Characteristics
- Parameter Count: 9 billion parameters, offering a balance between performance and computational efficiency.
- Context Length: Supports a substantial context window of 32768 tokens, enabling the model to process and understand long inputs.
- Training Origin: Derived from
HerrHruby/MR_midtrain_9B_v3, suggesting a foundation in a previously established model version. - Checkpoint Specificity: This particular version is checkpoint
step 150, indicating a specific stage in its asynchronous training process.
Intended Use
This model checkpoint is primarily intended for:
- Inference: Generating text, answering questions, or performing other language-based tasks.
- Evaluation: Assessing its performance on various benchmarks and datasets to understand its capabilities and limitations.