Hugging Face's logo
Nexes the Old's picture
TFLOPS icon 49.0 TFLOPS
104 174

Nexes the Old

Nexesenex
21world's profile picture kyynaama's profile picture Maxxim69's profile picture
·
https://github.com/Nexesenex/kobold.cpp/releases
Nexesenex

AI & ML interests

Playing with the latest features of KoboldCPP and quants of LlamaCPP. Sharing my favorite models quants with everyone.

Organizations

unalignment's profile picture

Nexesenex's activity

New activity in crestf411/L3-70B-daybreak-abliterated-v0.4 22 days ago

Good model

8
#2 opened about 1 month ago by Nexesenex
New activity in legraphista/Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF 29 days ago

Wow!

2
#1 opened 29 days ago by Nexesenex
New activity in DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF-imatrix 29 days ago

Thank you VERY MUCH for this!

5
#1 opened about 1 month ago by Nexesenex
New activity in failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5 about 1 month ago

L3 8b abliterated fp16 gguf measurements for information
#2 opened about 1 month ago by Nexesenex
New activity in MarsupialAI/llama-3-70B-Instruct-abliterated_iMatrix_GGUF about 2 months ago

iMatrix files

8
#1 opened about 2 months ago by Nexesenex
New activity in MarsupialAI/LaDameBlanche-v2-95b 2 months ago

Promising vitrine model for sub-100b frankenmerges of 70b models!

1
#2 opened 2 months ago by Nexesenex
New activity in mradermacher/Tia-70B-RP-GGUF 2 months ago

Split quants

12
#1 opened 2 months ago by Nexesenex
New activity in Nexesenex/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF 3 months ago

iMatrix effect on other languages?

1
#10 opened 3 months ago by Udo0815
New activity in mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF 3 months ago

Quantization of output weight

7
#2 opened 3 months ago by Nexesenex
New activity in Nexesenex/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF 4 months ago

Any chance for new IQ1_S versions?

3
#9 opened 4 months ago by g4be
New activity in Nexesenex/abacusai_Smaug-Yi-34B-v0.1-iMat.GGUF 4 months ago

Smaug 72b q1_s gguf?

2
#2 opened 4 months ago by vonjack
New activity in wolfram/miquliz-120b-v2.0-GGUF 4 months ago

iMatrix, IQ2_XS & IQ2_XXS

13
#2 opened 5 months ago by Nexesenex
New activity in alchemonaut/QuartetAnemoi-70B-t0.0001-GGUF 4 months ago

A good surprise

2
#1 opened 5 months ago by Nexesenex
New activity in Nexesenex/TomGrc_FusionNet_7Bx2_MoE_v0.1-iMat.GGUF 5 months ago

What settings are you using for this iMatrix quant?

3
#1 opened 5 months ago by cosmojg
New activity in Nexesenex/Senku-70b-iMat.GGUF 5 months ago

A request for quantization.

3
#1 opened 5 months ago by Kotokin
New activity in ChuckMcSneed/WolframRavenwolfs_benchmark_results 5 months ago

Graph?

1
#2 opened 5 months ago by Nexesenex
New activity in Nexesenex/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF 5 months ago

103b and 120b models

2
#7 opened 5 months ago by OrangeApples
New activity in ChuckMcSneed/WinterGoddess-1.4x-70b-32k 5 months ago

Your benchs on 2 more models?

8
#1 opened 5 months ago by Nexesenex
New activity in Nexesenex/WinterGoddess-1.4x-limarpv3-70B-L2-32k-Requant.GGUF 5 months ago

Surprisingly good for stories

4
#2 opened 5 months ago by cliffwalls
New activity in TheBloke/Mixtral_34Bx2_MoE_60B-GGUF 5 months ago

Complete the quants
#3 opened 5 months ago by Nexesenex
New activity in Undi95/Miqu-70B-Alpaca-DPO-GGUF 5 months ago

LORA?

3
#1 opened 5 months ago by ProphetOfBostrom
New activity in Artefact2/lzlv_70b-GGUF 5 months ago

iMatrix & remaining quants.

1
#1 opened 5 months ago by Nexesenex
New activity in Artefact2/BagelMIsteryTour-v2-8x7B-GGUF 5 months ago

Quants requests

2
#2 opened 5 months ago by Nexesenex
New activity in NeverSleepHistorical/MiquMaid-v2-70B-alpha-GGUF 5 months ago

Q3_K_M?

4
#1 opened 5 months ago by Nexesenex
New activity in grimulkan/lzlv-longLORA-70b-rope8-32k-fp16 5 months ago

Benchmarks!

3
#2 opened 5 months ago by ChuckMcSneed
New activity in Nexesenex/abacusai_Smaug-Yi-34B-v0.1-iMat.GGUF 5 months ago

q5/q6 GGUF?

1
#1 opened 5 months ago by johnnnna
New activity in Nexesenex/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF 5 months ago

Graphed by gpt4

6
#4 opened 5 months ago by ipechman
New activity in Nexesenex/WinterGoddess-1.4x-limarpv3-70B-L2-32k-Requant.GGUF 5 months ago

Interesting fate of my quant

9
#1 opened 5 months ago by mishima
New activity in Nexesenex/brucethemoose_Yi-34B-200K-DARE-megamerge-v8-iMat.GGUF 5 months ago

Thanks for the new quants

2
#1 opened 5 months ago by FlareRebellion
New activity in Nexesenex/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF 5 months ago

Q6/Q8 variants?

2
#6 opened 5 months ago by gileneo
New activity in cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 5 months ago

Upload tokenizer.model

1
#1 opened 5 months ago by Nexesenex
New activity in cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO 5 months ago

Upload tokenizer.model
#2 opened 5 months ago by Nexesenex
New activity in TomGrc/FusionNet_34Bx2_MoE_v0.1 5 months ago

Some benchs

1
#1 opened 5 months ago by Nexesenex
New activity in DrNicefellow/ChatAllInOne-Yi-34B-200K-V1 5 months ago

Low perplexity!

1
#1 opened 5 months ago by brucethemoose
New activity in cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO 5 months ago

fp16

4
#1 opened 5 months ago by Nexesenex
New activity in Nexesenex/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF 5 months ago

CodeLlama-70B

2
#5 opened 5 months ago by eramax
New activity in grimulkan/llama2_70b_longlora_fp16_32k_ROPE8 5 months ago

Benchs

8
#1 opened 5 months ago by Nexesenex
New activity in miqudev/miqu-1-70b 5 months ago

An interesting yet useless consideration over the fp16 being out or not.

6
#21 opened 5 months ago by Nexesenex
New activity in brucethemoose/Yi-34B-200K-DARE-megamerge-v8 5 months ago

34b models tests

7
#1 opened 5 months ago by Nexesenex
New activity in Kooten/MiquMaid-v1-70B-IQ2-GGUF 5 months ago

Thanks man!

10
#1 opened 5 months ago by Nexesenex
New activity in NeverSleep/MiquMaid-v1-70B 5 months ago

Kyllene and MergeMonster

1
#4 opened 5 months ago by Nexesenex
New activity in Nexesenex/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF 5 months ago

Generational loss?

5
#1 opened 5 months ago by FlareRebellion
New activity in NeverSleep/MiquMaid-v1-70B-GGUF 5 months ago

Kooten made IQ quants of Miqumaid v1

1
#3 opened 5 months ago by Nexesenex

Memory usage

6
#2 opened 5 months ago by sergkisel3v
New activity in NeverSleep/MiquMaid-v1-70B 5 months ago

Benchs are a clean sheet.

1
#2 opened 5 months ago by Nexesenex
New activity in NeverSleep/MiquMaid-v1-70B-GGUF 5 months ago

A one-shot comparison of Miqu IQ2 vs MiquMaid Q2.

4
#1 opened 5 months ago by SabinStargem
New activity in miqudev/miqu-1-70b 5 months ago

Might consider attribution

106
#10 opened 5 months ago by arthurmensch
New activity in Nexesenex/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF 5 months ago

Arch speculations

6
#3 opened 5 months ago by grimulkan

miqu-1-70b-Requant-b2007-iMat-c32_ch400-IQ3_XXS.gguf Errors

2
#2 opened 5 months ago by snombler
New activity in miqudev/miqu-1-70b 5 months ago

Model

25
#5 opened 5 months ago by mrfakename
New activity in abacusai/Smaug-34B-v0.1 5 months ago

Some benchs

4
#2 opened 5 months ago by Nexesenex
New activity in miqudev/miqu-1-70b 5 months ago

Please upload the full model first

88
#1 opened 5 months ago by ChuckMcSneed
New activity in TeeZee/Kyllene-34B-v1.1 5 months ago

What is this?

6
#1 opened 5 months ago by brucethemoose
New activity in KnutJaegersberg/2-bit-LLMs 5 months ago

Gratitude

7
#1 opened 5 months ago by Nexesenex
New activity in yunconglong/Mixtral_7Bx2_MoE_13B_DPO 5 months ago

Upload tokenizer.model
#3 opened 5 months ago by Nexesenex
New activity in zgce/Yi-34b-200K-alpaca-rpv3-scipy_GGUF 5 months ago

Q8_0
#2 opened 5 months ago by Nexesenex
New activity in filipealmeida/samantha-yi-34b-GGUF 5 months ago

Upload samantha-yi-34b-AR-Q4_K_M.gguf
#1 opened 5 months ago by Nexesenex
New activity in ikawrakow/various-2bit-sota-gguf 5 months ago

What -ctx and -chunks parameters did you use to make the iMatrix of the Lllama 2 70b?

1
#9 opened 5 months ago by Nexesenex
New activity in grimulkan/aurelian-alpha0.1-70b-rope8-32K-fp16 5 months ago

2 bits GGUF SOTA quants?

31
#2 opened 6 months ago by Nexesenex
New activity in Artefact2/Aurora-Nights-70B-v1.0-GGUF-2bit 5 months ago

Merci Romain !

18
#1 opened 6 months ago by Nexesenex