Qwen2.5-7B Thai fine-tune
Hub tags list Qwen/Qwen2.5-7B as base-model fine-tune, and the model card describes fine-tuning from Qwen2.5-7B on around 100,000 Thai rows.
Open Source Model Profile · Tsunami-th
Tsunami-0.5x-7B-Instruct
Tsunami-0.5x-7B-Instruct is a 7.62B-parameter Qwen2-family Thai instruct model from Tsunami-th. According to the model card, it is fine-tuned from Qwen2.5-7B on around 100,000 Thai dataset rows.
- Publisher
- Tsunami-th
- Task
- text-generation
- Model type
- qwen2
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Tsunami-0.5x-7B-Instruct is published by Tsunami-th as a Transformers text-generation model. The captured configuration identifies Qwen2ForCausalLM and qwen2, and Safetensors metadata reports 7,615,616,512 parameters. Hub tags list Qwen/Qwen2.5-7B as base-model fine-tune, and the model card describes Thai fine-tuning from that base.
Recorded capabilities
Qwen2 architecture and size
Captured config reports Qwen2ForCausalLM and qwen2, with Safetensors metadata reporting about 7.62B parameters.
ChatML prompt template
According to the model card, this model uses the ChatML prompt template.
Publisher-displayed leaderboard figures
According to the captured model-card text, the page displays Open LLM Leaderboard figures including IFEval, BBH, MATH, GPQA, MuSR, and MMLU-PRO; these are publisher-displayed numbers, not Ethen-measured results.
Use cases in the source record
- Thai and English conversational generation using the documented ChatML prompt template.
- Qwen2.5-7B fine-tune experiments for Thai-language instruction following.
Limitations and unknowns
- Leaderboard-style figures appear only in captured model-card text; no independently extracted Ethen evaluation result is present.
- According to the model card, version 0.5x did not train on the whole dataset, so training completeness is limited by the publisher note.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: Tsunami-th/Tsunami-0.5x-7B-Instruct
Captured: Unknown. Processed: 2026-09-07T19:34:38.092636+00:00.
Tsunami-0.5x-7B-Instruct TSUNAMI : Transformative Semantic Understanding and Natural Augmentation Model for Intelligence. TSUNAMI full name was created by ChatGPT. infomation Tsunami-0.5x-7B-Instruct is Thai Large Language Model that fine-tuned from Qwen2.5-7B around 100,000 rows in Thai dataset. Prompt Template This model uses ChatML prompt template: <|im_start|>system {System}<|im_end|> <|im_start|>user {User}<|im_end|> <|im_start|>assistant {Assistant} How to use from transformers import AutoModelForCausalLM, AutoTokenizer import torch model_name = "Tsunami-th/Tsunami-0.5x-7B-Instruct" model = AutoModelForCausalLM.from_pretrained…
F001F002F003F004F005F006F007F008F009F010F011F013F014F015F016F017