Hugging Face's logo
Mukesh Sharma's picture
16 1

Mukesh Sharma

MukeshSharma
·

AI & ML interests

None yet

Organizations

None yet

MukeshSharma's activity

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 9 months ago

Failed to import transformers.models.mixtral.modeling_mixtral because of the following error (look up to see its traceback): libcudart.so.12: cannot open shared object file: No such file or directory

1
#66 opened 9 months ago by MukeshSharma
New activity in bigcode/starcoder about 1 year ago

How to stop the prediction once the model is generated a sufficient solution for the asked prompt ?

9
#49 opened over 1 year ago by MukeshSharma

Solved
#55 opened over 1 year ago by MukeshSharma
New activity in EleutherAI/gpt-j-6b over 1 year ago

what changes exactly need to be done to make use of Horovod library for distributed parallel training on multiple server

#22 opened over 1 year ago by MukeshSharma
New activity in OpenAssistant/oasst-sft-6-llama-30b-xor over 1 year ago

can we use this model to finetune it on our specific dataset , like how other models hosted on hugging face is done.

2
#26 opened over 1 year ago by MukeshSharma

Trying to convert LlaMa weights to HF and running out of RAM, but don't want to buy more RAM?

14
#4 opened over 1 year ago by daryl149
New activity in bigscience/bloom over 1 year ago

Is the 14 programming Laungugae dataset uploaded on hugging face ? Any other option to doenload the data

1
#201 opened over 1 year ago by MukeshSharma
New activity in EleutherAI/gpt-j-6b over 1 year ago

How can we add ability remember the conversation ??

1
#14 opened over 1 year ago by MukeshSharma
New activity in togethercomputer/GPT-JT-6B-v1 almost 2 years ago

Do GPT-JT-6B-v1 model has the ability of follow up questions like CHATGPT

1
#16 opened almost 2 years ago by MukeshSharma

Training code

5
#8 opened almost 2 years ago by philschmid

What is the fine tuning process of GPT-JT-6B-v1 Copied ? Any Docs available ?

5
#15 opened almost 2 years ago by MukeshSharma
New activity in EleutherAI/gpt-j-6b almost 2 years ago

GPTJForCausalLM hogs memory - inference only

2
#9 opened almost 2 years ago by mrmartin
New activity in hivemind/gpt-j-6B-8bit almost 2 years ago

hivemind / gpt-j-6B-8bit , How can i use Multiple GPU , I treid using accelerate and also using torch.nn.dataparallel() nothing works out

1
#11 opened almost 2 years ago by MukeshSharma
New activity in hivemind/gpt-j-6B-8bit about 2 years ago

When will the error get resolved ?Can't load tokenizer using from_pretrained, please update its configuration

1
#5 opened about 2 years ago by MukeshSharma

Error at the moment of training

8
#3 opened about 2 years ago by AuraM

bitsandbytes-cuda111==0.26.0 not found

4
#4 opened about 2 years ago by tomwjhtom
New activity in EleutherAI/gpt-j-6b about 2 years ago

EleutherAI / gpt-j-6B

2
#2 opened about 2 years ago by MukeshSharma