Qwen2 1.78B fine-tune
Safetensors metadata reports 1,777,088,000 parameters with a Qwen2ForCausalLM configuration on the documented DeepSeek-R1-Distill-Qwen-1.5B base.
Open Source Model Profile · aayanmishra-ml
Atlas-Flash-1.5B-Preview
Atlas-Flash-1.5B-Preview is a Qwen2 text-generation fine-tune from aayanmishra-ml. Safetensors metadata reports about 1.78B parameters on the documented DeepSeek-R1-Distill-Qwen-1.5B base.
- Publisher
- aayanmishra-ml
- Task
- text-generation
- Model type
- qwen2
- License
- mit
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Atlas-Flash-1.5B-Preview is published by aayanmishra-ml as a Qwen2-family text-generation fine-tune. Safetensors metadata reports 1,777,088,000 parameters. According to the model card, it builds on deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B as the first model in the publisher's Atlas family.
Recorded capabilities
Coding-focused fine-tuning
According to the model card, multi-stage fine-tuning targeted coding, general language tasks, and STEM domains.
Documented training datasets
The model card names BAAI/TACO, GammaCorpus-v1-70k-UNFILTERED, and codeparrot/apps as training datasets.
Use cases in the source record
- Code generation, debugging, explanation, and documentation workflows described in the publisher model card.
- Conversational and STEM problem-solving experiments using the documented fine-tuning focus.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Publisher performance comparisons against Athena-2 and other models are source claims and have not been independently verified by Ethen.
- According to the model card, outputs may reflect training-data bias and underperform in niche domains.
Source and provenance
Source: aayanmishra-ml/Atlas-Flash-1.5B-Preview
Captured: Unknown. Processed: 2026-09-07T19:35:17.725456+00:00.
Model Card: Atlas-Flash Model Overview Atlas-Flash is the first model in the Atlas family , a new generation of AI systems designed to excel in tasks requiring advanced reasoning, contextual understanding, and domain-specific expertise. Built on Deepseek's R1 distilled Qwen models , Atlas-Flash integrates state-of-the-art methodologies to deliver significant improvements in coding , conversational AI , and STEM problem-solving . Atlas is the successor of Athena-2 and outperforms Athena-2 in many aspects, such as coding and NLP tasks. With a focus on versatility and robustness, Atlas-Flash adheres to the core principles established i…
F001F002F003F004F005F006F007F008F009F010F011F013F014F015F016F017F018F020F021F022F023F026