Listed QVikhr base and physics dataset
Hub tags identify Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r as the base and RomanNeobutov/PhysicsSchoolbooks as the linked dataset.
Open Source Model Profile · RomanNeobutov
PhysicsOnBooks
PhysicsOnBooks is a 1.54B-parameter Qwen2 text-generation model from RomanNeobutov. Tags link it to a QVikhr base and physics data, and the card says it used AutoTrain.
- Publisher
- RomanNeobutov
- Task
- text-generation
- Model type
- qwen2
- License
- other
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
PhysicsOnBooks is published by RomanNeobutov as a text-generation model. The captured configuration identifies Qwen2ForCausalLM with a qwen2 model type, and Safetensors metadata reports 1,543,298,048 parameters. Hub tags link it to a QVikhr-2.5-1.5B-Instruct-r base and a physics schoolbooks dataset, and the model card says it was trained using AutoTrain.
Recorded capabilities
AutoTrain training
According to the model card, the model was trained using AutoTrain.
Qwen2 1.54B configuration
Captured config identifies Qwen2ForCausalLM and qwen2, with Safetensors metadata reporting 1,543,298,048 parameters.
Transformers loading pattern
The model card documents loading with AutoModelForCausalLM and AutoTokenizer from transformers.
Use cases in the source record
- Conversational text generation using the card's documented transformers AutoModelForCausalLM loading pattern.
- Physics-schoolbook-linked fine-tune research building on the tagged QVikhr base and dataset linkage.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value, hardware requirement, or training-hyperparameter detail was extracted.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Base, dataset, and AutoTrain details come from hub tags and a brief publisher card and were not independently verified by Ethen.
Source and provenance
Source: RomanNeobutov/PhysicsOnBooks
Captured: Unknown. Processed: 2026-09-07T19:35:15.345568+00:00.
Model Trained Using AutoTrain This model was trained using AutoTrain. For more information, please visit AutoTrain . Usage from transformers import AutoModelForCausalLM, AutoTokenizer model_path = "PATH_TO_THIS_REPO" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, device_map= "auto" , torch_dtype= 'auto' ). eval () # Prompt content: "hi" messages = [ { "role" : "user" , "content" : "hi" } ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize= True , add_generation_prompt= True , return_tensors= 'pt' ) output_ids = model.generate(input_ids.to( 'cuda…
F001F002F003F004F005F006F007F009F010F011F012F013