TxAgent-Instruct tuning
According to the model card, the model was instruction-tuned on TxAgent-Instruct, reported as 378,027 samples built from tooling, therapeutic-question, and reasoning-trace datasets.
Open Source Model Profile · mims-harvard
TxAgent-T1-Llama-3.1-8B
TxAgent-T1-Llama-3.1-8B is an 8.03B-parameter Llama fine-tune from mims-harvard for therapeutic reasoning with 211 biomedical tools and function calls.
- Publisher
- mims-harvard
- Task
- text-generation
- Model type
- llama
- License
- llama3.1
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
TxAgent-T1-Llama-3.1-8B is published by mims-harvard as a Llama-based text-generation fine-tune. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 8,030,261,248 parameters. According to the model card, it was instruction-tuned with the TxAgent-Instruct dataset on a Llama-3.1-8B-Instruct base, and card data records llama3.1.
Recorded capabilities
211-tool biomedical reasoning
According to the model card, TxAgent performs multi-step reasoning with real-time biomedical retrieval across 211 ToolUniverse tools and structured function calls.
Large therapeutic training trace
The model card reports 85,340 therapeutic questions, 177,626 reasoning steps, and 281,695 function calls, with drugs approved after 2023 excluded to avoid evaluation leakage.
Use cases in the source record
- Therapeutic-reasoning research that follows the model card's documented multi-step, tool-assisted workflow for drug interactions and contraindications.
- Function-calling experiments using biomedical tools, which the model card describes as task-driven tool selection with structured calls.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
- Clinical effectiveness claims come from the publisher model card and were not independently verified by Ethen.
Source and provenance
Source: mims-harvard/TxAgent-T1-Llama-3.1-8B
Captured: Unknown. Processed: 2026-09-07T19:35:26.394311+00:00.
TxAgent-T1 Model Model Information TxAgent-T1-Llama-3.1-8B is instruction tuned with TxAgent-Instruct dataset, a diverse synthetic multi-step reasoning and massive function call training dataset anchored in biomedical knowledge. TxAgent-T1-Llama-3.1-8B is finetuned based on Llama3.1-88-Instrcut. Introduction Precision therapeutics require multimodal adaptive models that generate personalized treatment recommendations. We introduce TxAgent, an AI agent that leverages multi-step reasoning and real-time biomedical knowledge retrieval across a toolbox of 211 tools to analyze drug interactions, contraindications, and patient-specific tre…
F001F002F003F004F005F006F007F009F010F011F012F013F014F015F016F017F018F019F020F021