IamexperimentingNow

New activity in google/gemma-2b 5 months ago

gemma -2b with multi-gpu

3

#44 opened 5 months ago by

evaluation loss not calculated during during?

#43 opened 5 months ago by

pretraining Gemma for domain dataset

8

#41 opened 6 months ago by

New activity in google/gemma-7b 5 months ago

Very high loss compared to keras

6

#46 opened 6 months ago by

tanimazsin130

Dont download, google scuttled this model

16

#77 opened 6 months ago by

Tom-Neverwinter

FSDP with Nvidia GPU

#84 opened 5 months ago by

Fine-Tune a gemma model for question answering

17

#62 opened 6 months ago by

New activity in google/gemma-2b 6 months ago

Error: RuntimeError: expected mat1 nd mat2 to have the same dtype, but got: float != c10::BFloat16

5

#39 opened 6 months ago by

New activity in defog/sqlcoder-7b-2 6 months ago

description for special tokens

#21 opened 6 months ago by

Fine-tuning with SQL coder

5

#14 opened 6 months ago by

New activity in mistralai/Mistral-7B-Instruct-v0.2 6 months ago

instruction fine tuning template

#57 opened 6 months ago by

New activity in defog/sqlcoder-70b-alpha 6 months ago

About Supervised fine tuning

4

#9 opened 7 months ago by

aniketjha1304

New activity in defog/sqlcoder-7b-2 6 months ago

context length higher than 100K

#13 opened 6 months ago by

New activity in defog/sqlcoder 6 months ago

schema consideration and warnings

5

#3 opened about 1 year ago by

nobitha

New activity in defog/sqlcoder2 6 months ago

how large can database schemas be ?

#1 opened 11 months ago by

PankajShukla

New activity in defog/sqlcoder-70b-alpha 6 months ago

can you share finetune scripts and datasets

#8 opened 7 months ago by

TomPei

New activity in defog/sqlcoder-7b-2 6 months ago

Context-Window

3

#6 opened 7 months ago by

HuggySSO

New activity in databricks/dolly-v2-12b 10 months ago

Adding Buffer memory to Q&A application

#92 opened 10 months ago by

New activity in databricks/dolly-v2-7b about 1 year ago

Dolly answers on its own.

#15 opened about 1 year ago by

New activity in huggyllama/llama-7b about 1 year ago

question answering using llama

#4 opened about 1 year ago by

New activity in openlm-research/open_llama_13b about 1 year ago

question answering using llama

#7 opened about 1 year ago by

New activity in sentence-transformers/all-mpnet-base-v2 about 1 year ago

what happens when I pass out of vocabulary word to this model?

#7 opened about 1 year ago by

New activity in tiiuae/falcon-40b about 1 year ago

can anyone help me get prompt template for Question Answering model

#54 opened about 1 year ago by

New activity in google/flan-t5-xl about 1 year ago

can anyone help me to get Prompt template for question answering model

#18 opened about 1 year ago by

New activity in google/tapas-base-finetuned-wtq over 1 year ago

unable to trace the model using TorchScript

#3 opened over 1 year ago by

New activity in google/flan-t5-xl over 1 year ago

int8 model consumes the same GPU memory as default model.

#15 opened over 1 year ago by

understanding about LLM

#14 opened over 1 year ago by

New activity in databricks/dolly-v2-12b over 1 year ago

Question Answering model using dolly

13

#59 opened over 1 year ago by