cloudyu (hai) – Community Activity

#1 opened 13 days ago by

gopi87

New activity in mlx-community/Meta-Llama-3-8B-Instruct-8bit 28 days ago

when tryy the code, AttributeError: type object 'QuantizedLinear' has no attribute 'quantize_module' report

#1 opened about 1 month ago by

New activity in HuggingFaceH4/open_llm_leaderboard about 1 month ago

"status" is "FINISHED", but I cannot find the result of my model

#694 opened about 1 month ago by

New activity in mlx-community/c4ai-command-r-plus-4bit about 1 month ago

output is not correct.

#7 opened about 1 month ago by

flymonk

New activity in mradermacher/WizardLM-2-8x22B-GGUF about 1 month ago

how to run WizardLM-2-8x22B.Q4_K_S.gguf.part2of2 and part1?

#1 opened about 1 month ago by

New activity in mlx-community/Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx about 1 month ago

can you plesse share how to make this version?

#3 opened about 1 month ago by

New activity in mlx-community/c4ai-command-r-plus-4bit about 2 months ago

How much RAM does it need to run on Mac m1?

5

#2 opened about 2 months ago by

davideuler

New activity in CohereForAI/c4ai-command-r-plus about 2 months ago

MMLU is only 25.64, anything wrong?

5

#8 opened about 2 months ago by

New activity in wolfram/miquliz-120b-v2.0 about 2 months ago

VRAM Estimates

5

#3 opened 3 months ago by

ernestr

New activity in cloudyu/Mixtral_34Bx2_MoE_60B about 2 months ago

From your work, I find a new way to do model ensemble

#14 opened about 2 months ago by

xxx1

New activity in cloudyu/Mixtral_11Bx2_MoE_19B 2 months ago

Hardware requirement

#5 opened 2 months ago by

Dtree07

Adding Evaluation Results

#4 opened 2 months ago by

ac-automata

New activity in cloudyu/Yi-34Bx2-MoE-60B 2 months ago

4x version

#15 opened 2 months ago by

ehartford

New activity in cloudyu/mistral_pretrain_demo 3 months ago

Very interesting

#1 opened 3 months ago by

ehartford

New activity in cloudyu/google-gemma-7b-chinese-sft-v1 3 months ago

Thank you for your continued contribution to Chinese-language community|感谢你对中文社区的持续贡献

#1 opened 3 months ago by

sdakfjlkfasf

Why did you take down gemma-7b-it-dpo-v1

#2 opened 3 months ago by

rombodawg

New activity in LayerDiffusion/layerdiffusion-v1 3 months ago

how to run this model?

#1 opened 3 months ago by

New activity in cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO 3 months ago

Adding Evaluation Results

#1 opened 3 months ago by

leaderboard-pr-bot

New activity in yunconglong/MoE_13B_DPO 3 months ago

这个是基于中文的微调吗效果这么好

#2 opened 4 months ago by

xuan0126

New activity in cloudyu/Mixtral_7Bx4_MOE_DPO 3 months ago

Train after merging?

#1 opened 3 months ago by

adi-kmt

New activity in becausecurious/stable-video-diffusion-img2vid-fp16 3 months ago

how to run this model

#2 opened 3 months ago by

New activity in cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 4 months ago

Upload tokenizer.model

#1 opened 4 months ago by

Nexesenex

New activity in cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO 4 months ago

Upload tokenizer.model

#2 opened 4 months ago by

Nexesenex

fp16

#1 opened 4 months ago by

Nexesenex

New activity in 152334H/miqu-1-70b-sf 4 months ago

how to dequantised from q5 to f16?

#7 opened 4 months ago by

New activity in yunconglong/Mixtral_7Bx2_MoE_13B_DPO 4 months ago

Update README.md

#2 opened 4 months ago by

Update README.md

#1 opened 4 months ago by

New activity in cloudyu/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE 4 months ago

Can you make a 2.4bpw exl2 quantisation for this model?

#1 opened 4 months ago by

xldistance

New activity in mlabonne/phixtral-4x2_8 4 months ago

How did you train the gating?

10

#6 opened 4 months ago by

osanseviero

New activity in cloudyu/Mixtral_7Bx4_MOE_24B 4 months ago

Unable to access cloudyu/Pluto_24B_DPO_400

#1 opened 4 months ago by

umarbutler

New activity in jondurbin/truthy-dpo-v0.1 4 months ago

this is really great dataset

#2 opened 4 months ago by

New activity in cloudyu/Pluto_13B_DPO 4 months ago

Could you share the training script?

#1 opened 4 months ago by

andysalerno

New activity in cloudyu/Yi-34Bx2-MoE-60B 4 months ago

vllm

#10 opened 4 months ago by

regzhang

New activity in HuggingFaceH4/open_llm_leaderboard 4 months ago

Announcement: Flagging merged models with incorrect metadata

78

#510 opened 5 months ago by

clefourrier

New activity in moreh/MoMo-72B-lora-1.8.6-DPO 4 months ago

congrat！new SOTA!

#1 opened 4 months ago by

New activity in cloudyu/Yi-34Bx2-MoE-60B 4 months ago

How many GPU memories that the MoE module needs?

#8 opened 4 months ago by

Jazzlee

New activity in cloudyu/Mixtral_34Bx2_MoE_60B 4 months ago

The function_calling and translation abilities are weaker than Mixtral 8x7b

#11 opened 4 months ago by

bingw5

New activity in cloudyu/Yi-34Bx2-MoE-60B 4 months ago

Multi-langua?

#7 opened 4 months ago by

oFDz

New activity in LoneStriker/Mixtral_34Bx2_MoE_60B-6.0bpw-h6-exl2 4 months ago

8.0bpw-h8-exl2 quant of this model

6

#1 opened 4 months ago by

Light4Bear

New activity in mlabonne/phixtral-4x2_8 4 months ago

The difference of prompt template between base models

#8 opened 4 months ago by

Cartinoe5930

New activity in cloudyu/Mixtral_7Bx2_MoE 4 months ago

Do you need fine-tune after merging?

#5 opened 4 months ago by

tanganke

New activity in cloudyu/Yi-34Bx2-MoE-60B 4 months ago

Can VLLM be used for inference acceleration?

#2 opened 4 months ago by

obtion

New activity in cloudyu/Mixtral_34Bx2_MoE_60B 4 months ago

Vram

#7 opened 4 months ago by

DKRacingFan

New activity in cloudyu/Mixtral_34Bx2_MoE_60B 5 months ago

source code and paper?

8

#6 opened 5 months ago by

josephykwang

How does the MoE work?

#5 opened 5 months ago by

PacmanIncarnate

Should not be called mixtral, the models made into the moe are yi based

9

#2 opened 5 months ago by

teknium

New activity in cloudyu/Mixtral_7Bx2_MoE 5 months ago

Problem with tokenizer

#4 opened 5 months ago by

ipechman

One or two models during inference?

#3 opened 5 months ago by

Venkman42

Can You Share Your Config

#2 opened 5 months ago by

Weyaxi

How to merge models into moe?

#1 opened 5 months ago by

Yhyu13

New activity in cognitivecomputations/dolphin-2.5-mixtral-8x7b 5 months ago

Why is not working? Please advice as I'm a complete beginner

#14 opened 5 months ago by

ciclide80

New activity in Xwin-LM/Xwin-LM-70B-V0.1 8 months ago

Switches from English prompt to Chinese response

6

#6 opened 8 months ago by

Dove5632

It's a bit difficult to deploy the 70B model for verification, so let's keep an eye on how things develop

#4 opened 8 months ago by

wawoshashi

New activity in breadlicker45/museRWKV-test 9 months ago

how to run this model?

#2 opened 9 months ago by