bartowski (Bartowski) – Community Activity

#84 opened 4 days ago by

New activity in bartowski/Smegmma-9B-v1-GGUF 1 day ago

GGUF IQuants of TheDrummer/Smegmma-Deluxe-9B-v1?

#1 opened 1 day ago by

Joseph717171

New activity in bartowski/gemma-2-27b-it-GGUF 3 days ago

ValueError: Failed to load model from file: models\gemma-2-27b-it-Q3_K_M.gguf

#8 opened 3 days ago by

Star81

New activity in bartowski/gemma-2-27b-it-GGUF 4 days ago

"Experimental" = ZeroWw method.

37

#7 opened 7 days ago by

ZeroWw

New activity in bartowski/Gemma-2-9B-It-SPPO-Iter3-GGUF 4 days ago

Problem Model

13

#1 opened 6 days ago by

ClaudioItaly

New activity in bartowski/gemma-2-9b-it-GGUF 4 days ago

Q6_K response quality diverges (in a bad way)

34

#4 opened 8 days ago by

thethinkmachine

New activity in bartowski/internlm2_5-7b-chat-1m-GGUF 5 days ago

prompt template?

#1 opened 5 days ago by

mirek190

New activity in Locutusque/Hercules-5.0-Qwen2-7B 5 days ago

Upload Qwen2ForCausalLM

#5 opened 7 days ago by

Locutusque

New activity in bartowski/Phi-3.1-mini-4k-instruct-GGUF 5 days ago

GGUF Model

#2 opened 5 days ago by

Pecc

New activity in ZeroWw/Phi-3-mini-128k-instruct-GGUF 6 days ago

FYI: likely broken 128k - maybe not, maybe only PPL

#1 opened 6 days ago by

New activity in bartowski/Phi-3.1-mini-4k-instruct-GGUF 6 days ago

Experimental = ZeroWw way.

#1 opened 6 days ago by

ZeroWw

New activity in microsoft/Phi-3-mini-4k-instruct 6 days ago

Uploaded GGUF and exl2 as Phi 3.1

5

#80 opened 7 days ago by

New activity in bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF 6 days ago

It seems the quants were created before the BPE pre-tokenizer fix?

#1 opened about 1 month ago by

skruse

New activity in bartowski/gemma-2-27b-it-GGUF 7 days ago

More gemma 2 llama.cpp merges, do they require GGUF regen again?

#6 opened 7 days ago by

IHadToMakeAccount

New activity in microsoft/Phi-3-mini-4k-instruct 7 days ago

Updated model should have a new version number

#79 opened 7 days ago by

EwoutH

New activity in arcee-ai/Arcee-Spark-GGUF 7 days ago

Template ? not able t use it.

7

#1 opened 9 days ago by

NK-Spacewalk

New activity in bartowski/gemma-2-27b-it-GGUF 8 days ago

Load gemma-2-27b-it-Q4_K_S.gguf from LMStudio always crashed my MacBook Pro M2

#4 opened 10 days ago by

Million

New activity in bartowski/WizardLM-2-8x22B-GGUF 8 days ago

which quaint to I use to fit on a single 24GB video card on a PC Running Windows 11? (4090)

#3 opened 8 days ago by

clevnumb

New activity in arcee-ai/Arcee-Spark-GGUF 8 days ago

ChatML template is not working

#2 opened 9 days ago by

NK-Spacewalk

New activity in bartowski/gemma-2-27b-it-GGUF 8 days ago

Llama.cpp fixes have been merged, requires gguf regen

#5 opened 9 days ago by

RamoreRemora

New activity in bartowski/llama3-turbcat-instruct-8b-GGUF 9 days ago

Pretty good stuff!

#1 opened 10 days ago by

Razrien

New activity in bartowski/gemma-2-27b-it-GGUF 9 days ago

Prompt format <bos> not needed?

16

#3 opened 11 days ago by

eamag

New activity in bartowski/llama-3-70B-Instruct-abliterated-GGUF 9 days ago

OOM when trying to load the Q8 in Oobabooga (I have 98GB VRAM)

#1 opened 9 days ago by

AIGUYCONTENT

New activity in bartowski/gemma-2-9b-it-GGUF 10 days ago

METAL and FLASH ATTENTION: Why does the Non-Linear IQ4_NL Quant run faster than the IQ4_K_M Quants when I use larger Quants (see file size in GB) of LLaMa-3-8B-Instruct with no issues?

#2 opened 10 days ago by

Joseph717171

New activity in google/gemma-2-27b-it 10 days ago

Hallucinations, misspellings etc. Something seems broken?

16

#10 opened 11 days ago by

sam-paech

New activity in bartowski/gemma-2-27b-it-GGUF 11 days ago

'LlamaCppModel' object has no attribute 'model'

10

#2 opened 11 days ago by

DrNicefellow

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma2'

#1 opened 11 days ago by

cloudyu

New activity in bartowski/gemma-2-9b-it-GGUF 11 days ago

Tokenizer was broken in the PR when these were made, now fixed(?)

#1 opened 11 days ago by

Fizzarolli

New activity in bartowski/Samantha-Qwen-2-7B-GGUF 11 days ago

Testing experimental quants

31

#2 opened 22 days ago by

New activity in lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF 12 days ago

"llama.cpp error: 'error loading model architecture: unknown model architecture: 'deepseek2''"

8

#3 opened 13 days ago by

ZeroCool22

New activity in bartowski/Meta-Llama-3-8B-Instruct-GGUF 12 days ago

Llama 3 8B Instruct - Q8 vs FP16 vs FP32

#8 opened 14 days ago by

Hearcharted

New activity in bartowski/Yi-9B-Coder-GGUF 14 days ago

Update README.md with license information

#1 opened 14 days ago by

Chen-01AI

New activity in bartowski/Replete-Coder-Llama3-8B-exl2 14 days ago

Update README.md

#1 opened 14 days ago by

rombodawg

New activity in bartowski/Replete-Coder-Llama3-8B-GGUF 14 days ago

Update prompt template

#1 opened 14 days ago by

rombodawg

New activity in Qwen/Qwen1.5-7B-Chat-GGUF 14 days ago

Please post f16 quantization.

8

#1 opened about 2 months ago by

ZeroWw

New activity in bartowski/Hathor_Stable-L3-8B-v0.5-exl2 15 days ago

I made a mild oopsie.

#1 opened 15 days ago by

Nitral-AI

New activity in Nitral-Archive/Hathor_Gamma-L3-8B-0.6 15 days ago

Fix GGUF link

#1 opened 15 days ago by

New activity in bartowski/Qwen2-7B-Instruct-GGUF 15 days ago

Poor Chinese performance

#2 opened 15 days ago by

yttria

New activity in bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF 16 days ago

Error loading model

14

#1 opened 21 days ago by

smchapman54

New activity in arcee-ai/Llama-3-SEC-Chat-GGUF 16 days ago

Anyway to quantize this further down to 4090 level (24Gb VRAM), at Q2_K.gguf level already not sure if it is possible

#1 opened 16 days ago by

askyforever

New activity in bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF 17 days ago

Thank you for quants! 🤗

#1 opened 17 days ago by

SicariusSicariiStuff

New activity in bartowski/Meta-Llama-3-8B-Instruct-GGUF 17 days ago

Create config.json

#7 opened 17 days ago by

standingout

New activity in mistralai/Mistral-7B-Instruct-v0.3 17 days ago

Please check these quantizations.