Mohammed Faheem's picture

Mohammed Faheem

thefaheem

·

AI & ML interests

NLP, LMs

Recent Activity

upvoted an article 9 days ago

ScreenEnv: Deploy your full stack Desktop Agent

upvoted a paper 4 months ago

Token-Efficient Long Video Understanding for Multimodal LLMs

liked a model 10 months ago

abertsch/unlimiformer-bart-govreport-alternating

View all activity

Organizations

commented a paper 12 months ago

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities

Paper • 2407.14482 • Published Jul 19, 2024 • 27 •

New activity in skeskinen/TinyStories-hf almost 2 years ago

gpt-4 version of the dataset

#3 opened almost 2 years ago by

commented a paper about 2 years ago

AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn

Paper • 2306.08640 • Published Jun 14, 2023 • 26 •

New activity in TheBloke/Falcon-7B-Instruct-GPTQ about 2 years ago

TypeError: RefinedWebModel isn't supported yet.

#9 opened about 2 years ago by

New activity in TheBloke/WizardLM-Uncensored-Falcon-7B-GPTQ about 2 years ago

TypeError: RefinedWebModel isn't supported yet.

#1 opened about 2 years ago by

New activity in TheBloke/Falcon-7B-Instruct-GPTQ about 2 years ago

Custom 4-bit Finetuning 5-7 times faster inference than QLora

#5 opened about 2 years ago by

New activity in TheBloke/Manticore-13B-GGML about 2 years ago

RWKV Quantisation

#1 opened about 2 years ago by

New activity in wojtab/llava-7b-v0-4bit-128g about 2 years ago

It's not compatible with text generation webUI, what IS it compatible with?

#1 opened about 2 years ago by

New activity in liuhaotian/LLaVA-Lightning-MPT-7B-preview about 2 years ago

Using with the Script

#1 opened about 2 years ago by

New activity in liuhaotian/LLaVA-13b-delta-v0 about 2 years ago

LLaVa Applied Weights

#2 opened about 2 years ago by

New activity in junelee/wizard-vicuna-13b about 2 years ago

Prompt Format?

#1 opened about 2 years ago by

New activity in TheBloke/wizard-vicuna-13B-GGML about 2 years ago

Perfomance of the model

#1 opened about 2 years ago by

New activity in TheBloke/stable-vicuna-13B-GPTQ about 2 years ago

using with transformers

#11 opened about 2 years ago by

Model's VRAM Utilisation

#10 opened about 2 years ago by

the model thinks its chatgpt, lobotomy is advised

#4 opened about 2 years ago by