Hugging Face's logo
Man Cub's picture
43 3

Man Cub

mancub

AI & ML interests

None yet

Organizations

None yet

mancub's activity

New activity in TheBloke/LlongOrca-7B-16K-GPTQ 11 months ago

Lack of 33B models?

7
#1 opened 11 months ago by mancub
New activity in TheBloke/galactica-30B-evol-instruct-70K-GPTQ about 1 year ago

No config.json ?

3
#1 opened about 1 year ago by 0x12d3
New activity in TheBloke/starchat-beta-GPTQ about 1 year ago

is this working properly?

23
#1 opened about 1 year ago by Boffy
New activity in TheBloke/Nous-Hermes-13B-GGML about 1 year ago

Uh oh, the "q's"...

27
#2 opened about 1 year ago by mancub
New activity in TheBloke/starchat-beta-GGML about 1 year ago

Are you making k-quant series of this model?

3
#1 opened about 1 year ago by mancub
New activity in TheBloke/falcon-40b-instruct-GPTQ about 1 year ago

Issues with Auto

3
#15 opened about 1 year ago by Devonance

Unfortunately I can't run on text-generation-webui

11
#1 opened about 1 year ago by Suoriks
New activity in TheBloke/Falcon-7B-Instruct-GPTQ about 1 year ago

Getting 0 tokens while running using text-generation -webui

6
#4 opened about 1 year ago by avatar8875
New activity in TheBloke/guanaco-33B-GPTQ about 1 year ago

Could this model be loaded in 3090 GPU?

24
#6 opened about 1 year ago by Exterminant
New activity in TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ about 1 year ago

Error when loading the model in ooba's UI (colab version)

14
#3 opened about 1 year ago by PopGa
New activity in TheBloke/guanaco-65B-GPTQ about 1 year ago

not enough memory

2
#15 opened about 1 year ago by nikocraft
New activity in TheBloke/WizardLM-30B-Uncensored-GPTQ about 1 year ago

How much vram+ram 30B needs? I have 3060 12gb + 32gb ram.

21
#1 opened about 1 year ago by DaveScream
New activity in TheBloke/WizardLM-30B-GPTQ about 1 year ago

Won't load... GPTQ....

13
#1 opened about 1 year ago by vdruts
New activity in TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GPTQ about 1 year ago

Unable to load/use this model.

11
#5 opened about 1 year ago by vdruts
New activity in TheBloke/falcon-40b-instruct-GPTQ about 1 year ago

error when loading sucessful and prompting simple text

19
#11 opened about 1 year ago by joseph3553
New activity in TheBloke/WizardLM-Uncensored-Falcon-40B-GPTQ about 1 year ago

What hardware do I need for reasonable performance?

4
#3 opened about 1 year ago by TS0001
New activity in TheBloke/Wizard-Vicuna-30B-Uncensored-GGML about 1 year ago

Still not fully Uncensored.

3
#1 opened about 1 year ago by Flanua
New activity in lukasmoeller/replit-code-v1-3b-ggml about 1 year ago

Access denied to the model file?

4
#1 opened about 1 year ago by mancub
New activity in TheBloke/guanaco-65B-GPTQ about 1 year ago

Is there a way to finetune the model?

3
#9 opened about 1 year ago by Trinad
New activity in TheBloke/Falcon-7B-Instruct-GPTQ about 1 year ago

About these warnings...

2
#7 opened about 1 year ago by mancub
New activity in timdettmers/guanaco-33b-merged about 1 year ago

Best version for fine tuning.

2
#5 opened about 1 year ago by psych0v0yager
New activity in TheBloke/VicUnlocked-alpaca-65B-QLoRA-GGML about 1 year ago

About this model

43
#1 opened about 1 year ago by giftbest71
New activity in cognitivecomputations/samantha-7b about 1 year ago

Dataset

9
#2 opened about 1 year ago by tensiondriven
New activity in timdettmers/guanaco-33b-merged about 1 year ago

Whats the difference?

21
#3 opened about 1 year ago by ehartford
New activity in TheBloke/guanaco-33B-GPTQ about 1 year ago

Correct prompt?

2
#5 opened about 1 year ago by mancub
New activity in TheBloke/VicUnlocked-30B-LoRA-GGML about 1 year ago

Error loading the model - missing tensor weight?

9
#4 opened about 1 year ago by mancub
New activity in TheBloke/Manticore-13B-GGML about 1 year ago

It's a runaway train at times...

11
#2 opened about 1 year ago by mancub
New activity in TheBloke/VicUnlocked-30B-LoRA-GGML about 1 year ago

Hardware recommendations

3
#3 opened about 1 year ago by Romanserk

Thank you

1
#2 opened about 1 year ago by mancub
New activity in TheBloke/Wizard-Vicuna-13B-Uncensored-GGML about 1 year ago

New quant 8bit method, how is it performing on your CPU? (share your token/s, CPU model and -- thread)

24
#2 opened about 1 year ago by alphaprime90
New activity in reeducator/vicuna-13b-cocktail about 1 year ago

Cocktail Testing and Discussion

156
#1 opened about 1 year ago by deleted
New activity in TheBloke/h2ogpt-oasst1-512-30B-GGML about 1 year ago

I have a question with the tokens

5
#1 opened about 1 year ago by RedXeol
New activity in reeducator/vicuna-13b-cocktail about 1 year ago

Great triton-4bit-128g.safetensors is giving me giberish?

3
#6 opened about 1 year ago by Goldenblood56
New activity in reeducator/vicuna-13b-free about 1 year ago

v230502 Testing and Discussion

89
#23 opened about 1 year ago by deleted

V4.3 Early Testing.

109
#15 opened about 1 year ago by deleted

Something wrong with bin files?

2
#18 opened about 1 year ago by mancub

Slow inference speed using default vs 3rd party tokenizer files

3
#19 opened about 1 year ago by mancub

Do I just copy over the config, tokenizer_config, and tokenizer.model from another 13B Vicuna Model to get this working in ooba? I am getting error.

10
#17 opened about 1 year ago by Goldenblood56
New activity in lmsys/vicuna-13b-v1.1 about 1 year ago

sharegpt dataset

1
#3 opened about 1 year ago by winglian
New activity in reeducator/vicuna-13b-free about 1 year ago

Run the model with oobabooga/text-generation-webui - missing config.json, etc.

5
#6 opened about 1 year ago by mancub

Thank you

12
#3 opened about 1 year ago by anon8231489123
New activity in anon8231489123/ShareGPT_Vicuna_unfiltered about 1 year ago

Is there a model based on this dataset yet?

78
#1 opened about 1 year ago by spanielrassler
New activity in anon8231489123/vicuna-13b-GPTQ-4bit-128g about 1 year ago

Uncensored

33
#5 opened about 1 year ago by synthetisoft