Qwen2 text-generation architecture
The captured configuration identifies Qwen2ForCausalLM with model type qwen2 and Transformers support.
Open Source Model Profile · M4-ai
Hercules-5.0-Qwen2-1.5B
Hercules-5.0-Qwen2-1.5B is a 1.54B-parameter Qwen2-family text-generation fine-tune from M4-ai. According to the model card, it fine-tunes qwen2-1.5B and uses ChatML.
- Publisher
- M4-ai
- Task
- text-generation
- Model type
- qwen2
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Hercules-5.0-Qwen2-1.5B is published by M4-ai as a text-generation model. The captured configuration identifies Qwen2ForCausalLM with model type qwen2, and Safetensors metadata reports about 1.54B parameters. According to the model card, it is a qwen2-1.5B fine-tune on a high-quality mix for general-purpose assistants using ChatML.
Recorded capabilities
1.54B Qwen2-1.5B fine-tune
Safetensors metadata reports 1,543,714,304 parameters; according to the model card, the model is fine-tuned from qwen2-1.5B.
Documented ChatML format
According to the model card, the publisher uses the ChatML prompt format.
General-assistant positioning
According to the model card, the publisher positions it for general-purpose assistance, question answering, and chain-of-thought use, with English and possibly Chinese.
Disclosed TPU training setup
According to the model card, training used eight Kaggle TPUs with bf16 non-mixed precision, batch size 256, and sequence length 1536.
Use cases in the source record
- General-purpose assistant workflows such as question answering and chain-of-thought prompting, as described by the publisher.
- ChatML-based text-generation experiments consistent with the publisher-documented prompt format and math, coding, and writing focus.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- According to the model card, the publisher includes an anecdotal coding-achievement note; it is a publisher claim, not an Ethen-verified benchmark.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: M4-ai/Hercules-5.0-Qwen2-1.5B
Captured: Unknown. Processed: 2026-09-07T19:34:33.656402+00:00.
Hercules-5.0-Qwen2-1.5B We fine-tuned qwen2-1.5B on a high quality mix for general-purpose assistants. A DPO version of this will be released soon. We use the ChatML prompt format. Model Details Model Description This model has capabilities in math, coding, writing, and more. We fine-tuned it using a high quality mix for general-purpose assistants. Developed by: M4-ai Language(s) (NLP): English and maybe Chinese License: apache-2.0 Finetuned from model: qwen2-1.5B Uses General purpose assistant, question answering, chain-of-thought, etc.. This language model made an impressive achievement, and correctly implemented a Multi Head Atte…
F001F002F003F004F005F006F007F008F010F011F012F013F014F015