Hugging Face's logo
Akarshan Biswas's picture
26 33 76

Akarshan Biswas

qnixsynapse
shtefcs's profile picture julien-c's profile picture ruchir28's profile picture
ยท

AI & ML interests

NLP, models, quantization

Recent Activity

new activity 4 days ago
google/gemma-2-9b-it:Tool calling support in Gemma 2
liked a Space 4 days ago
webml-community/attention-visualization
reacted to suayptalha's post with ๐Ÿ‘€ 7 days ago
๐Ÿš€ Introducing ๐…๐ข๐ซ๐ฌ๐ญ ๐‡๐ฎ๐ ๐ ๐ข๐ง๐  ๐…๐š๐œ๐ž ๐ˆ๐ง๐ญ๐ž๐ ๐ซ๐š๐ญ๐ข๐จ๐ง ๐จ๐Ÿ ๐ฆ๐ข๐ง๐†๐‘๐” ๐Œ๐จ๐๐ž๐ฅ๐ฌ from the paper ๐–๐ž๐ซ๐ž ๐‘๐๐๐ฌ ๐€๐ฅ๐ฅ ๐–๐ž ๐๐ž๐ž๐๐ž๐? ๐Ÿ–ฅ I have integrated ๐ง๐ž๐ฑ๐ญ-๐ ๐ž๐ง๐ž๐ซ๐š๐ญ๐ข๐จ๐ง ๐‘๐๐๐ฌ, specifically minGRU, which offer faster performance compared to Transformer architectures, into HuggingFace. This allows users to leverage the lighter and more efficient minGRU models with the "๐ญ๐ซ๐š๐ง๐ฌ๐Ÿ๐จ๐ซ๐ฆ๐ž๐ซ๐ฌ" ๐ฅ๐ข๐›๐ซ๐š๐ซ๐ฒ for both usage and training. ๐Ÿ’ป I integrated two main tasks: ๐Œ๐ข๐ง๐†๐‘๐”๐…๐จ๐ซ๐’๐ž๐ช๐ฎ๐ž๐ง๐œ๐ž๐‚๐ฅ๐š๐ฌ๐ฌ๐ข๐Ÿ๐ข๐œ๐š๐ญ๐ข๐จ๐ง and ๐Œ๐ข๐ง๐†๐‘๐”๐…๐จ๐ซ๐‚๐š๐ฎ๐ฌ๐š๐ฅ๐‹๐Œ. ๐Œ๐ข๐ง๐†๐‘๐”๐…๐จ๐ซ๐’๐ž๐ช๐ฎ๐ž๐ง๐œ๐ž๐‚๐ฅ๐š๐ฌ๐ฌ๐ข๐Ÿ๐ข๐œ๐š๐ญ๐ข๐จ๐ง: You can use this class for ๐’๐ž๐ช๐ฎ๐ž๐ง๐œ๐ž ๐‚๐ฅ๐š๐ฌ๐ฌ๐ข๐Ÿ๐ข๐œ๐š๐ญ๐ข๐จ๐ง tasks. I also trained a Sentiment Analysis model with stanfordnlp/imdb dataset. ๐Œ๐ข๐ง๐†๐‘๐”๐…๐จ๐ซ๐‚๐š๐ฎ๐ฌ๐š๐ฅ๐‹๐Œ: You can use this class for ๐‚๐š๐ฎ๐ฌ๐š๐ฅ ๐‹๐š๐ง๐ ๐ฎ๐š๐ ๐ž ๐Œ๐จ๐๐ž๐ฅ tasks such as GPT, Llama. I also trained an example model with roneneldan/TinyStories dataset. You can fine-tune and use it! ๐Ÿ”— ๐‹๐ข๐ง๐ค๐ฌ: Models: https://huggingface.co/collections/suayptalha/mingru-676fe8d90760d01b7955d7ab GitHub: https://github.com/suayptalha/minGRU-hf LinkedIn Post: https://www.linkedin.com/posts/suayp-talha-kocabay_mingru-a-suayptalha-collection-activity-7278755484172439552-wNY1 ๐Ÿ“ฐ ๐‚๐ซ๐ž๐๐ข๐ญ๐ฌ: Paper Link: https://arxiv.org/abs/2410.01201 I am thankful to Leo Feng, Frederick Tung, Mohamed Osama Ahmed, Yoshua Bengio and Hossein Hajimirsadeghi for their papers.
View all activity

Organizations

None yet

qnixsynapse's activity

New activity in google/gemma-2-9b-it 4 days ago

Tool calling support in Gemma 2

2
#50 opened 27 days ago by
qnixsynapse
New activity in bartowski/OLMoE-1B-7B-0924-Instruct-GGUF 4 months ago

Is this really an Instruct model?
#1 opened 4 months ago by
qnixsynapse
New activity in huggingchat/chat-ui 5 months ago

[MODELS] Discussion

546
#372 opened 11 months ago by
victor

[TOOLS] Community Discussion

27
#455 opened 8 months ago by
victor
New activity in meta-llama/Llama-3.1-8B-Instruct 5 months ago

Wrong number of tensors; expected 292, got 291

6
#69 opened 5 months ago by
KingBadger
New activity in huggingchat/chat-ui 5 months ago

[FEATURE] Tools

69
#470 opened 7 months ago by
victor
New activity in meta-llama/Llama-3.1-8B-Instruct 6 months ago

Utterly based

1
#9 opened 6 months ago by
llama-anon
New activity in ggml-org/gguf-my-repo 6 months ago

Add IQ Quantization support with the help of imatrix and GPUs

8
#35 opened 9 months ago by
qnixsynapse
New activity in huggingchat/chat-ui 6 months ago

Suggestion: Host Gemma2 using keras_nlp instead of transformers library for the time being

2
#498 opened 6 months ago by
qnixsynapse
New activity in meta-llama/Meta-Llama-3-8B-Instruct 9 months ago

The best 8B in the planet right now. PERIOD!

2
#22 opened 9 months ago by
cyberneticos
New activity in mistral-community/Mixtral-8x22B-v0.1 9 months ago

How many active parameters does this model have?

3
#6 opened 9 months ago by
lewtun
New activity in google/gemma-7b 9 months ago

7B or 8B?

4
#24 opened 11 months ago by
amgadhasan
New activity in huggingchat/chat-ui 9 months ago

Which model is responsible for naming of the thread?

8
#402 opened 9 months ago by
qnixsynapse
New activity in google/gemma-1.1-7b-it 9 months ago

Consider adding <start_of_context> and <stop_of_context> or similar special tokens for context ingestion.
#13 opened 9 months ago by
qnixsynapse

Number of parameters

7
#9 opened 9 months ago by
HugoLaurencon
New activity in TheBloke/Llama-2-7B-Chat-GGUF 11 months ago

RMSNorm eps value is wrong
#20 opened 11 months ago by
qnixsynapse

RMSNorm eps value is wrong
#19 opened 11 months ago by
qnixsynapse
New activity in TheBloke/llama2_70b_chat_uncensored-GGML over 1 year ago

Loading the model

3
#3 opened over 1 year ago by
PyrroAiakid
New activity in TheBloke/Llama-2-70B-Chat-GGML over 1 year ago

Looking for GGUF format for this model

1
#14 opened over 1 year ago by
barha
New activity in TheBloke/Llama-2-13B-chat-GGML over 1 year ago

Help needed to load model

19
#13 opened over 1 year ago by
sanjay-dev-ds-28