John Steward

Paper • 2402.11295 • Published Feb 17 • 21 •

New activity in dreamgen/opus-v1.2-llama-3-8b about 1 month ago

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

12

#3 opened about 1 month ago by

DreamGenX

New activity in ByteDance/SDXL-Lightning 3 months ago

Training code

6

#1 opened 3 months ago by

gutianpei

commented a paper 3 months ago

OneBit: Towards Extremely Low-bit Large Language Models

11

New activity in miqudev/miqu-1-70b 4 months ago

Model

25

#5 opened 4 months ago by

mrfakename

New activity in HuggingFaceH4/open_llm_leaderboard 4 months ago

Model failing to run

#557 opened 4 months ago by

NobodyExistsOnTheInternet

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

12

#544 opened 4 months ago by

rishiraj

[ flag ] udkai/Garrulus

#525 opened 4 months ago by

New activity in NousResearch/Nous-Hermes-2-Yi-34B 5 months ago

Apache 2.0?

#1 opened 5 months ago by

amgadhasan

New activity in HuggingFaceH4/open_llm_leaderboard 5 months ago

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

42

#474 opened 5 months ago by

killawhale2

New activity in Undi95/Mixtral-8x7B-MoE-RP-Story 5 months ago

Good stuff

#2 opened 5 months ago by

Paper • 2311.07590 • Published Nov 9, 2023 • 15 •

New activity in HuggingFaceH4/open_llm_leaderboard 5 months ago

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

125

#444 opened 5 months ago by

XXXGGGNEt

commented 2 papers 6 months ago

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

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

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

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

New activity in teknium/OpenHermes-2.5-Mistral-7B 7 months ago

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

4

#1 opened 7 months ago by

Phil337

commented a paper 7 months ago

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

9

New activity in TheBloke/CausalLM-14B-GGUF 7 months ago

No Q_K quants?

#1 opened 7 months ago by

TheYuriLover

New activity in liuhaotian/llava-v1.5-13b 7 months ago

why can not see visual encoder weights?

#1 opened 7 months ago by

lucasjin

New activity in teknium/airoboros-mistral2.2-7b 8 months ago

How to convert to GGUF?

#1 opened 8 months ago by

spaceemotion

New activity in HuggingFaceH4/open_llm_leaderboard 9 months ago

GPT-J is too powerful

#194 opened 9 months ago by

New activity in Blackroot/Llama-2-13B-Storywriter-LORA 10 months ago

Great lora

#1 opened 10 months ago by

New activity in TheBloke/Llama-2-70B-fp16 10 months ago

Do you know that all your work is being stolen and reuploaded?

#1 opened 10 months ago by

rombodawg

New activity in garage-bAInd/Platypus-30B 11 months ago

What is the prompt format?

#4 opened 11 months ago by

New activity in TheBloke/robin-13B-v2-GGML 11 months ago

Probably The Best Multishot Model Series So Far

6

#1 opened 11 months ago by

New activity in HuggingFaceH4/open_llm_leaderboard 11 months ago

Dedup redundant entries (for example we have 3 entries for llama-65 right now)

#71 opened 11 months ago by

henrit

New activity in HuggingFaceH4/open_llm_leaderboard 12 months ago

Wrong Running Config of WizardLM-13B and WizardLM-30B

4

#54 opened 12 months ago by

WizardLM

New activity in digitous/13B-Chimera 12 months ago

Request for GGML version to try this ^_^

#2 opened 12 months ago by

PrimeD

New activity in openaccess-ai-collective/hippogriff-30b-chat 12 months ago

Will you consider releasing a public dataset?

#1 opened 12 months ago by

Jackdiy

New activity in HuggingFaceH4/open_llm_leaderboard 12 months ago

Scores of GPT3.5 and GPT4 for comparison

16

#30 opened 12 months ago by

gsaivinay

New activity in cognitivecomputations/samantha-7b 12 months ago

I do not understand if this is a serious training, with sufficient data

#1 opened 12 months ago by

DaDavinci

New activity in TheBloke/gpt4-x-vicuna-13B-GGML about 1 year ago

Accuracy comparison with wizard-vicuna-13b and stable-vicuna-13b?

6

#1 opened about 1 year ago by

anon7463435254

New activity in chavinlo/alpaca-native about 1 year ago

Will this work on an RTX 3080 10gb?