128k version of YARN
#6
by
sovetboga
- opened
Hello, does this model have the same situation as in Qwen3. Is it possible to get the 128k version?
https://github.com/THUDM/GLM-4#model-and-prompt-implementation
Hi there good idea we'll see waht we can do :)
It would be awesome, looking for it.
Would love to see this!
GLM-4 32b seems a lot more reliable for coding that Qwen 3, just needs it's context extended.
This would be great!
Yes so where is the long context window size version this is ridiculous it is still not available.