Hugging Face's logo
Mayank Mishra's picture
TFLOPS icon 1815797.7 TFLOPS
59 30 7

Mayank Mishra

mayank-mishra
CircusPtr's profile picture DA1212's profile picture ameyv6's profile picture
·
https://mayank31398.github.io/
mishramish98
mayank31398

AI & ML interests

Large Language Models, Distributed Training and Inference

Articles

Organizations

IBM's profile picture BigCode's profile picture Ontocord's M*DEL's profile picture Blog-explorers's profile picture Aurora-M's profile picture IBM Granite's profile picture

mayank-mishra's activity

New activity in ibm-granite/granite-8b-code-instruct 1 day ago

[AUTOMATED] Model Memory Requirements
#4 opened about 1 month ago by model-sizer-bot

Function calling and Streaming support

2
#5 opened 22 days ago by skumarai
New activity in mayank-mishra/glaive-code-assisstant-v3-20k 2 days ago

[bot] Conversion to Parquet
#1 opened 21 days ago by parquet-converter
New activity in ibm-granite/granite-8b-code-instruct 20 days ago

Input context length

3
#6 opened 20 days ago by dyoung
New activity in ibm-granite/granite-8b-code-instruct 22 days ago

Official quants?

3
#2 opened about 1 month ago by joshuaturner
New activity in ibm-granite/granite-20b-code-instruct 22 days ago

Is it fine to do granite-20b model's inference with bfloat16 dtype?

3
#1 opened 24 days ago by lkm1
New activity in ibm-granite/granite-3b-code-instruct-GGUF 23 days ago

Issue to run the model on Ollama.

3
#1 opened 26 days ago by vperrinfr
New activity in ibm-granite/granite-3b-code-base 24 days ago

Release GGUF models?

3
#5 opened about 2 months ago by CosmicSound
commented a paper about 1 month ago
New activity in ibm-granite/granite-20b-code-base-GGUF about 1 month ago

3b, 8b, and 34b versions of GGUF?

1
#1 opened about 1 month ago by tombenninger
New activity in ibm-granite/granite-3b-code-base about 1 month ago

Licensing

6
#4 opened about 2 months ago by tonylek
New activity in ibm-granite/granite-34b-code-base about 1 month ago

update transformers also for this ?

3
#1 opened about 1 month ago by talrid
New activity in ibm-granite/granite-3b-code-instruct about 1 month ago

Onnx Model Produces Different Output

2
#2 opened about 1 month ago by runski
New activity in ibm-granite/granite-8b-code-instruct about 1 month ago

Response is not good as expected

5
#3 opened about 1 month ago by skumarai
New activity in ibm-granite/granite-3b-code-base about 2 months ago

Why was the logo removed?

1
#6 opened about 2 months ago by mrfakename
New activity in ibm-granite/granite-8b-code-instruct about 2 months ago

Model template

3
#1 opened about 2 months ago by alex0dd
New activity in ibm-granite/granite-3b-code-base about 2 months ago

Context length

5
#3 opened about 2 months ago by mrfakename

Question

3
#2 opened about 2 months ago by mrfakename
New activity in ibm-granite/granite-3b-code-instruct about 2 months ago

Fix trailing , in generation_config.json

2
#1 opened about 2 months ago by mike-ravkine
New activity in ibm-granite/granite-3b-code-base about 2 months ago

Initial model card version
#1 opened about 2 months ago by amezasor
commented a paper 2 months ago
commented 11 papers 3 months ago
New activity in blog-explorers/README 3 months ago

[Support] Community Articles

28
#5 opened 3 months ago by victor
New activity in ibm/MoLFormer-XL-both-10pct 3 months ago

Adding `safetensors` variant of this model
#1 opened 3 months ago by SFconvertbot
New activity in aurora-m/aurora-m-biden-harris-redteamed 4 months ago

Update README.md

1
#1 opened 4 months ago by cabbage972
New activity in bigcode/starcoder 9 months ago

May I ask if there are plans to provide 8-bit or 4-bit quantized versions?

10
#19 opened about 1 year ago by intelligencegear
New activity in tiiuae/falcon-180B 9 months ago

Is Gigatron open source?
#6 opened 10 months ago by mayank-mishra
New activity in tiiuae/falcon-180B 10 months ago

Tensor parallel version of this for efficient inference?
#5 opened 10 months ago by mayank-mishra
New activity in mayank-mishra/starcoder-GPTQ-4bit-128g about 1 year ago

extreme slowdown and weird output.

9
#4 opened about 1 year ago by abhimortal6

Compatibility with HF Code extension

2
#2 opened about 1 year ago by yclicc
New activity in mosaicml/mpt-7b about 1 year ago

Add eos_token_id to generation config

1
#26 opened about 1 year ago by mayank-mishra
New activity in mayank-mishra/starcoder-GPTQ-4bit-128g about 1 year ago

Can I use this model in text-generation-webui?

11
#1 opened about 1 year ago by CyberTimon
New activity in mayank-mishra/starcoderbase-GPTQ-8bit-128g about 1 year ago

Running this on consumer hardware

2
#1 opened about 1 year ago by piratos
New activity in bigcode/starcoder about 1 year ago

What are 0..7.bin?

2
#14 opened about 1 year ago by lozhnikov
New activity in bigcode/starcoderbase about 1 year ago

KeyError: 'gpt_bigcode'

1
#4 opened about 1 year ago by Bilibili
New activity in bigcode/gpt_bigcode-santacoder about 1 year ago

fix eos_token and bos_token in config

1
#1 opened about 1 year ago by mayank-mishra
New activity in bigcode/santacoder over 1 year ago

fix sequence length in santacoder and introduce new model type
#23 opened over 1 year ago by mayank-mishra

make santacoder onnx compatible

1
#21 opened over 1 year ago by mayank-mishra
New activity in bigscience/bloom over 1 year ago

Where can I find a script to fine tune Bloom?

4
#129 opened over 1 year ago by mishavee

What gpu power do you need just to run Bloom, not fine tune?

1
#130 opened over 1 year ago by mishavee

how can i train bloom

4
#111 opened almost 2 years ago by s3rgio27

How much GPU memory needed?

4
#109 opened almost 2 years ago by mazib
New activity in bigscience/bloom almost 2 years ago

Inference on BLOOM 165B is too slow

15
#59 opened almost 2 years ago by mayank-mishra

Finetuning BLOOM 175-B

6
#54 opened almost 2 years ago by mayank-mishra

Facing using while doing token classification using BLOOM LLM Model

1
#55 opened almost 2 years ago by SourabhSahu