๐ Tema_Q-X2-Thinking
๐ฅ ใขใใซๆฆ่ฆ
Tema_Q-X2-Thinking๏ผๅคฉ้ฆฌๆฑ๏ผ ใฏใใขใชใใใ้็บใใใขใใซ Qwen3.5 4B ใๅบ็คใซใใใๆฅๆฌ่ชใ่ฑ่ชๅใใฎๆน่ฏ็ๅคง่ฆๆจก่จ่ชใขใใซ๏ผLLM๏ผใงใใ
้ๅธธใฎQwenใขใใซใงใฏๅ็ญใ้ฃใใใใญใณใใใซๅฏพใใฆใใใใ่ช็ฑใงๆ็จใชๅฟ็ญใ็ๆใงใใใใ่จญ่จใใใฆใใพใใ4BใขใใซใฎใใใThinkingไฝฟ็จๆใฏDRYใใใซใใฃใผใ0.5๏ฝ0.6็จๅบฆไธใใฆใใ ใใ๏ผๆ่ก็ใซ็นฐใ่ฟใใ็บ็ใใใใใขใใซใฎใใใงใ๏ผใ
Tema_Q-X2-Thinking (Tema Q) is an improved large-scale language model (LLM) for Japanese and English based on the model Qwen3.5 4B developed by Alibaba.
It is designed to generate more flexible and useful responses to prompts that are difficult to answer using the standard Qwen model.Since this is a 4B model, please give a DRY penalty of about 0.3 to 0.6 when using Thinking.
| ้ ็ฎ | ่ฉณ็ดฐ |
|---|---|
| ใใผในใขใใซ | Qwen3.5 9B |
| ใขใใซๅ | Tema_Q-X2-Thinking |
| ๅฏพๅฟ่จ่ช | ๆฅๆฌ่ช (JA), ่ฑ่ช (EN) |
| ใขใใซใตใคใบ | 4 Billion Parameters |
| ใฉใคใปใณใน | Qwenใฎใฉใคใปใณในใซๆบๆ |
| ้็บ | Tema_Q้็บใใผใ |
๐ก๏ธ ่ฒฌไปปใใAIๅฉ็จใจๅญฆ็ฟใใผใฟใฎๅฎๅ จๆง
โ ๏ธ ่ฒฌไปปใใๅฉ็จใฎๅพนๅบ
- ใฆใผใถใผใฎ่ฒฌไปป: ใขใใซใฎๅฉ็จ่ ใฏใ็ๆใใใใณใณใใณใใใ้ฉ็จใใใๆณๅพใ่ฆๅถใใใใณHugging Faceใฎๅฉ็จ่ฆ็ด/ใณใณใใณใใใชใทใผใซๆบๆ ใใใใจใๅ จ้ข็ใซไฟ่จผใใๅฟ ่ฆใใใใพใใ
- ็ฆๆญขไบ้ : ใใฎใขใใซใใใใใชใๅทฎๅฅใใใฉในใกใณใใๆดๅใ้ๆณ่ก็บใใใใณๆๅฎณใช็ฎ็ใฎใใใซๅฉ็จใใใใจใๅบใ็ฆใใพใใ
- Downloads last month
- 10