Jack Boot

New activity in nvidia/Llama3-ChatQA-1.5-70B 18 days ago

Concerns regarding Prompt Format

#1 opened 18 days ago by

wolfram

New activity in hjhj3168/Llama-3-8b-Orthogonalized-exl2 18 days ago

🚩 Report: Legal issue(s)

40

#2 opened 19 days ago by

chrisjcundy

New activity in Dogge/Tia-70B-RP-lora 26 days ago

Adapter is 48 bytes?

#1 opened 26 days ago by

New activity in turboderp/Mixtral-8x22B-Instruct-v0.1-exl2 about 1 month ago

Any chance of a 3.75bpw?

5

#3 opened about 1 month ago by

gghfez

New activity in Dracones/WizardLM-2-8x22B_exl2_4.0bpw about 1 month ago

3.75 please?

#2 opened about 1 month ago by

New activity in sophosympatheia/Midnight-Miqu-70B-v1.0 3 months ago

Hi, I made gptq quant.

12

#3 opened 3 months ago by

Kotokin

New activity in miqudev/miqu-1-70b 3 months ago

I managed to get `Miqu` to give up his real template format and he is MUCH better if you use it!!!

24

#25 opened 3 months ago by

jukofyork

New activity in sophosympatheia/Midnight-Miqu-70B-v1.0 3 months ago

Feedback

#6 opened 3 months ago by

Szarka

New activity in Undi95/Miqu-70B-Alpaca-DPO 3 months ago

Why not post the lora?

#2 opened 3 months ago by

New activity in alchemonaut/QuartetAnemoi-70B-t0.0001 3 months ago

Exllamav2 Quants

4

#2 opened 3 months ago by

llmixer

Maybe you can put some sillytavern settings? contects? and preset?

3

#7 opened 3 months ago by

vurkan

New activity in dranger003/miquliz-120b-v2.0-iMat.GGUF 3 months ago

How to use this?

3

#1 opened 3 months ago by

steampunk333

New activity in ShinojiResearch/Senku-70B-Full 3 months ago

Proper prompt?

#3 opened 3 months ago by

damarges

New activity in 152334H/miqu-1-70b-sf 3 months ago

Sticking a restrictive license on a model that's not even yours to begin with?

#14 opened 3 months ago by

candre23

Chat template

9

#11 opened 4 months ago by

MaziyarPanahi

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

Might consider attribution

106

#10 opened 4 months ago by

arthurmensch

New activity in NobodyExistsOnTheInternet/miqu-limarp-70b 4 months ago

miqu truck

#1 opened 4 months ago by

distantquant

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

Model

25

#5 opened 4 months ago by

mrfakename

New activity in 152334H/miqu-1-70b-exl2 4 months ago

Is a higher quant possible?

#1 opened 4 months ago by

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

Please upload the full model first

88

#1 opened 4 months ago by

ChuckMcSneed

gief

#2 opened 4 months ago by

AUTOMATIC

I'm thinking miqu

11

#3 opened 4 months ago by

modster

New activity in LoneStriker/deepseek-llm-67b-Spicy-3.1-1-5.0bpw-h6-exl2 4 months ago

Base? Chat? What format is this?

#1 opened 4 months ago by

New activity in Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss 4 months ago

Finally decent results.

#1 opened 4 months ago by

New activity in sophosympatheia/Aurora-Nights-103B-v1.0 5 months ago

The instruct preset and talking for you.

#2 opened 5 months ago by

New activity in LoneStriker/Aurora-Nights-103B-v1.0-3.5bpw-h6-exl2 5 months ago

Will it squeeze into 48?

4

#1 opened 5 months ago by

New activity in Sao10K/WinterGoddess-1.4x-70B-L2 5 months ago

Suggestion for Instruction Following Model

#1 opened 5 months ago by

PrimeD

New activity in Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-limarp 5 months ago

How is it working?

#1 opened 5 months ago by

New activity in LoneStriker/MixtralRPChat-ZLoss-6.0bpw-h6-exl2 5 months ago

How is it?

#1 opened 5 months ago by

New activity in nsfwthrowitaway69/Venus-103b-v1.1 6 months ago

Not for AI characters.

#1 opened 6 months ago by

New activity in migtissera/Tess-XL-v1.0 6 months ago

Any chance for an EXL2 version?

15

#2 opened 6 months ago by

wolfram

New activity in cognitivecomputations/dolphin-2_2-yi-34b 6 months ago

Can you upload qlora adapter files?

#1 opened 6 months ago by

adamo1139

New activity in 01-ai/Yi-34B 6 months ago

llama-compatibility

34

#11 opened 7 months ago by

ehartford

New activity in migtissera/SynthIA-70B-v1.5-GGUF 7 months ago

Can't download

7

#2 opened 7 months ago by

New activity in maddes8cht/tiiuae-falcon-40b 7 months ago

Model is broken in latest llama.cpp

#1 opened 7 months ago by

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

I have serious repeat problem.

7

#7 opened 8 months ago by

New activity in quantumaikr/falcon-180B-chat-instruct-LoRA 8 months ago

What dataset is it? What does it do?

#1 opened 8 months ago by

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

Switches from English prompt to Chinese response

#6 opened 8 months ago by

Dove5632

New activity in BlackSamorez/HuYaLM-100B-fp16 8 months ago

Possible to convert to GGUF?

3

#1 opened 8 months ago by

New activity in jondurbin/spicyboros-70b-2.2-prequant-merge 8 months ago

The Qlora?

#1 opened 8 months ago by

New activity in fangloveskari/ORCA_LLaMA_70B_QLoRA 9 months ago

Can you post the adapter as well?

#6 opened 9 months ago by

New activity in Gryphe/MythoMax-L2-13b 9 months ago

Make it a 22b

#1 opened 9 months ago by

New activity in jarradh/llama2_70b_chat_uncensored 10 months ago

Upload PEFT?

#4 opened 10 months ago by

New activity in Envoid/Dendrite-II-22B 10 months ago

This model is lit.

#1 opened 10 months ago by

New activity in upstage/SOLAR-0-70b-16bit 10 months ago

Does it say "as an AI"?

5

#2 opened 10 months ago by

New activity in Mikael110/llama-2-70b-guanaco-qlora 10 months ago

Something is off.

#2 opened 10 months ago by

New activity in TheBloke/llama-2-70b-Guanaco-QLoRA-GPTQ 10 months ago

desc_act?

#5 opened 10 months ago by

New activity in CalderaAI/30B-Lazarus 10 months ago

Don't compress emb for context.

#7 opened 10 months ago by

New activity in CalderaAI/30B-Epsilon 10 months ago

The perplexity is bad.

#3 opened 10 months ago by

New activity in CalderaAI/30B-Lazarus 11 months ago

Observations