Hugging Face's logo
Abhinav Kulkarni's picture
24

Abhinav Kulkarni

abhinavkulkarni
choronz333's profile picture Davide's profile picture ZeroCollabs's profile picture
·
https://www.linkedin.com/in/abhinavmkulkarni/

AI & ML interests

NLP

Organizations

None yet

abhinavkulkarni's activity

New activity in abhinavkulkarni/mosaicml-mpt-30b-chat-w4-g128-awq 11 months ago

Adding `safetensors` variant of this model
#1 opened 11 months ago by
SFconvertbot
New activity in cjpais/llava-1.6-mistral-7b-gguf about 1 year ago

llava_eval_image_embed : failed to eval

5
#6 opened about 1 year ago by
jartine
New activity in abhinavkulkarni/mosaicml-mpt-7b-chat-w4-g128-awq about 1 year ago

Adding `safetensors` variant of this model
#1 opened about 1 year ago by
SFconvertbot
New activity in togethercomputer/StripedHyena-Nous-7B over 1 year ago

Unable to quantize layers one at a time

2
#8 opened over 1 year ago by
abhinavkulkarni

Unable to load the model.. Can you explain..

2
#7 opened over 1 year ago by
jdc4429

Unable to load tokenizer

2
#5 opened over 1 year ago by
abhinavkulkarni
New activity in abhinavkulkarni/codellama-CodeLlama-13b-Instruct-hf-w4-g128-awq over 1 year ago

Adding `safetensors` variant of this model
#1 opened over 1 year ago by
SFconvertbot
New activity in abhinavkulkarni/meta-llama-Llama-2-13b-chat-hf-w4-g128-awq over 1 year ago

70B AWQ model?

1
#2 opened over 1 year ago by
Teja-Gollapudi
New activity in TheBloke/starchat-beta-GPTQ over 1 year ago

is it possible to make this work with huggingface/text-generation-inference ?

1
#5 opened almost 2 years ago by
captainst
New activity in abhinavkulkarni/meta-llama-Llama-2-13b-chat-hf-w4-g128-awq over 1 year ago

The code provided in the model card does not work

3
#1 opened almost 2 years ago by
AnalogAiBert
New activity in VMware/open-llama-13b-open-instruct almost 2 years ago

AWQ 4-bit 128g version of open-llama-13b-open-instruct!
#3 opened almost 2 years ago by
abhinavkulkarni
New activity in mosaicml/mpt-7b-instruct almost 2 years ago

AWQ 4-bit 128g version of mpt-7b-instruct!
#62 opened almost 2 years ago by
abhinavkulkarni
New activity in VMware/open-llama-7b-open-instruct almost 2 years ago

AWQ 4-bit 128g version of open-llama-7b-open-instruct!
#1 opened almost 2 years ago by
abhinavkulkarni
New activity in tiiuae/falcon-7b-instruct almost 2 years ago

AWQ 4-bit 128g version of falcon-7b-instruct!

2
#55 opened almost 2 years ago by
abhinavkulkarni
New activity in abhinavkulkarni/lmsys-vicuna-33b-v1.3-w4-g128-awq almost 2 years ago

Inference

1
#1 opened almost 2 years ago by
bartowski
New activity in abhinavkulkarni/tiiuae-falcon-40b-instruct-w4-g128-awq almost 2 years ago

Fix q_group_size

1
#1 opened almost 2 years ago by
mike-ravkine
New activity in abhinavkulkarni/tiiuae-falcon-7b-instruct-w4-g64-awq almost 2 years ago

Thanks for this model!

4
#1 opened almost 2 years ago by
mike-ravkine
New activity in mosaicml/mpt-7b almost 2 years ago

Is it possible to add logic for handling output_attentions?

5
#30 opened almost 2 years ago by
abhinavkulkarni

How do I manually get the same functionality as device_map="auto", given that device_map="auto" is not supported?

2
#33 opened almost 2 years ago by
narai
New activity in TheBloke/stable-vicuna-13B-GPTQ almost 2 years ago

Basic question about 4-bit quantization

2
#18 opened almost 2 years ago by
abhinavkulkarni