Saurabh Tripathi

icon company SDE-2 TECH MAHINDRA icon location 5th Delta One Giga Space IT Park Internal Road Viman Nagar Pune Maharashtra 411014 IN, Giga Space IT Park Internal Rd, Sakore Nagar, Viman Nagar, Pune, Maharashtra 411014

Results 9 comments of Saurabh Tripathi

suggest default server port lower than 49152.

server change port has completely changed to server 49152-65535 waiting for the response..... done by danish JR Engineer.. please change the module to hyper v model.

Update finetune.py

diff --git a/finetune/finetune.py b/finetune/finetune.py index 0308169..183a09d 100644 --- a/finetune/finetune.py +++ b/finetune/finetune.py @@ -12,7 +12,8 @@ Trainer, TrainingArguments, BitsAndBytesConfig, -) +)(a href= "ADD link"> TITLE + @dataclass @@ -29,6 +30,8 @@...

[Bad Case]: error loading model architecture: unknown model architecture: 'minicpm3' time=2024-10-12T20:12:01.292+08:00 level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade"

Done On Mon, 14 Oct 2024, 12:33 Hoyxxx, ***@***.***> wrote: > Description / 描述 > > error loading model architecture: unknown model architecture: 'minicpm3' > time=2024-10-12T20:12:01.292+08:00 level=ERROR source=sched.go:456 > msg="error...

[Bad Case]: error loading model architecture: unknown model architecture: 'minicpm3' time=2024-10-12T20:12:01.292+08:00 level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade"

Done with resolution... On Tue, 15 Oct 2024, 07:46 阿丹(adan), ***@***.***> wrote: > ollama暂时还没官方支持，敬请期待 > > — > Reply to this email directly, view it on GitHub > , >...

Training instability with InfLLM v2 on MiniCPM4-8B using sparse attention

This is not my responsibility so kindly forward it to software testers department specifically mentioned by me so i dont have right to ask me this follies question kindly behave...

[Feature Request]: mlcllm support for minicpm3

For your kind information u have to touch with in hr that I have made a leave for today On Tue, 19 Nov 2024, 11:15 Calvin lin, ***@***.***> wrote: >...

[Feature Request]: Script used to convert MiniCPM to Llama format

No I don't have I'm on leave On Mon, 18 Nov 2024, 09:25 Zeguan Xiao, ***@***.***> wrote: > No, just the script for MiniCPM v1. > > — > Reply...

Due to Flashattention, inference cannot be performed on v100

done with caseid 592863

How to finetune BitCPM4-1B

Ok let me try. On Mon, 23 Jun 2025 at 3:21 PM, siddharth28392 ***@***.***> wrote: > *siddharth28392* created an issue (OpenBMB/MiniCPM#301) > > > Do you have a code that...