John Steward's picture

John Steward

HDiffusion

·

AI & ML interests

None yet

Recent Activity

liked a model about 3 hours ago

VITA-MLLM/VITA-1.5

liked a model 1 day ago

cyberagent/Mistral-Nemo-Japanese-Instruct-2408

upvoted a paper 7 days ago

1.58-bit FLUX

View all activity

Organizations

HDiffusion's activity

New activity in HDiffusion/t5-v1_1-xxl_safetensors 9 months ago

Adding `safetensors` variant of this model

#1 opened 9 months ago by

New activity in dreamgen/opus-v1.2-llama-3-8b 9 months ago

Model won't stop generating [llama.cpp / koboldcpp]

#3 opened 9 months ago by

New activity in ByteDance/SDXL-Lightning 11 months ago

Training code

#1 opened 11 months ago by

commented a paper 11 months ago

OneBit: Towards Extremely Low-bit Large Language Models

Paper • 2402.11295 • Published Feb 17, 2024 • 23 •

New activity in miqudev/miqu-1-70b 11 months ago

Model

#5 opened 11 months ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 12 months ago

Model failing to run

#557 opened 12 months ago by

NobodyExistsOnTheInternet

The Unintended Consequences of Model Merging in the AI Landscape: A Case Study of the Marcoroni-7B-v3 Model

#544 opened 12 months ago by

[ flag ] udkai/Garrulus

#525 opened 12 months ago by

New activity in NousResearch/Nous-Hermes-2-Yi-34B about 1 year ago

Apache 2.0?

#1 opened about 1 year ago by

New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

Potential data contamination with regards to ultrafeedback-binarized and Nectar datasets

#474 opened about 1 year ago by

New activity in Undi95/Mixtral-8x7B-MoE-RP-Story about 1 year ago

Good stuff

#2 opened about 1 year ago by

New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

[FLAG] fblgit/una-xaberius-34b-v1beta

#444 opened about 1 year ago by

commented 2 papers about 1 year ago

Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure

Paper • 2311.07590 • Published Nov 9, 2023 • 16 •

mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

Paper • 2311.04257 • Published Nov 7, 2023 • 20 •

New activity in teknium/OpenHermes-2.5-Mistral-7B about 1 year ago

This LLM does in fact appear to be more logical, but it hallucinates more at the fringes of knowledge.

#1 opened about 1 year ago by deleted

commented a paper about 1 year ago

LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Paper • 2310.20624 • Published Oct 31, 2023 • 12 •

New activity in TheBloke/CausalLM-14B-GGUF about 1 year ago

No Q_K quants?

#1 opened about 1 year ago by

New activity in liuhaotian/llava-v1.5-13b about 1 year ago

why can not see visual encoder weights?

#1 opened about 1 year ago by

New activity in teknium/airoboros-mistral2.2-7b over 1 year ago

How to convert to GGUF?

#1 opened over 1 year ago by

New activity in open-llm-leaderboard/open_llm_leaderboard over 1 year ago

GPT-J is too powerful

#194 opened over 1 year ago by