Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · KASP1

ChemDFM-v1.5-8B

ChemDFM-v1.5-8B is an 8.03B-parameter Llama-family text-generation model from KASP1. According to the model card, it applies domain pre-training and instruction tuning on LLaMA-3-8B for chemistry.

Publisher
KASP1
Task
text-generation
Model type
llama
License
agpl-3.0
Library
Unknown
Publication status
Approved for indexing

Model overview

ChemDFM-v1.5-8B is published by KASP1 as a Llama text-generation model with chemistry tags. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 8,030,326,784 parameters. According to the model card, ChemDFM-v1.5-8B was released 2024-11-09 using the publisher's domain procedure on LLaMA-3-8B.

Recorded capabilities

Chemistry domain tuning

According to the model card, the release implements domain pre-training and instruction tuning on a stronger base model, LLaMA-3-8B.

Local loading example

According to the model card, local inference loads the model with torch, AutoTokenizer, LlamaForCausalLM, and GenerationConfig.

Series release context

According to the model card, related ChemDFM releases include ChemDFM-R-14B, ChemDFM-v2.0-14B on Qwen2.5-14B, and the earlier ChemDFM-13B paper lineage.

Use cases in the source record

  • Chemistry and molecular-science dialogue workflows consistent with the chemistry tags and the publisher's foundation-model description.
  • Local inference experiments using the torch and LlamaForCausalLM loading example the card documents.

Limitations and unknowns

  • Performance comparisons with other open models and GPT-4 in the card are publisher claims and were not independently verified.
  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: KASP1/ChemDFM-v1.5-8B

Captured: Unknown. Processed: 2026-09-07T19:35:40.425398+00:00.

ChemDFM: A Large Language Foundation Model for Chemistry ChemDFM is the pioneering open-sourced dialogue foundation model for Chemistry and molecular science, which is built based on LLaMa-13B. ChemDFM outperforms the open-sourced LLMs in all the typical tasks of chemistry, and even reaches comparable or higher performances to GPT-4. For more details, please refer to our paper . News 2025-10-26 : The parameter of ChemDFM-R-14B is open-sourced! 2025-10-26 : ChemDFM-v2.0-14B is released! The improved domain pre-training and instruction tuning procedure is implemented on Qwen2.5-14B to achieve a more advanced general LLM in Chemistry.…

F001F002F003F004F005F006F007F008F009F010F011F012F013F014F015F016F017