Hugging Face's logo
eachadea's picture
47 1 12

eachadea

eachadea
zuracode's profile picture ashishtanwer's profile picture beawnyko's profile picture
·

AI & ML interests

None yet

Organizations

None yet

eachadea's activity

New activity in lmsys/lmsys-chat-1m 7 months ago

Dataset Access

18
#1 opened 7 months ago by puffy310
New activity in eachadea/ggml-vicuna-13b-1.1 8 months ago

newest llama.cpp seems to crash now

7
#21 opened 12 months ago by WizardDave
New activity in NousResearch/Nous-Hermes-Llama2-13b-GGML 10 months ago

Upload ggml-model-f16.bin with huggingface_hub
#2 opened 10 months ago by eachadea

Upload ggml-model-a-q4_K_M.bin with huggingface_hub
#1 opened 10 months ago by eachadea
New activity in NousResearch/Redmond-Puffin-13B-GGML 10 months ago

Upload ggml-model-f16.bin with huggingface_hub
#2 opened 10 months ago by eachadea

Upload ggml-model-q4_K_M.bin with huggingface_hub
#1 opened 10 months ago by eachadea
New activity in eachadea/ggml-vicuna-13b-1.1 11 months ago

Update README.md
#22 opened 11 months ago by VGS52

uncensored version

8
#16 opened about 1 year ago by Feng7815
New activity in eachadea/ggml-vicuna-7b-1.1 12 months ago

Q5_X ggml models are not as accurate as the oldest version

4
#6 opened 12 months ago by KinzyLong
New activity in eachadea/legacy-ggml-vicuna-13b-4bit 12 months ago

Bug?

1
#9 opened 12 months ago by ClaudioItaly
New activity in eachadea/ggml-vicuna-13b-1.1 12 months ago

Are you going to redo ggml-vic13b-uncensored-q8_0.bin as well?

2
#19 opened 12 months ago by WizardDave
New activity in eachadea/ggml-dante-2.8b-gpt4 12 months ago

Purpose of This Model & Binary Format

2
#1 opened 12 months ago by danforbes
New activity in eachadea/ggml-vicuna-13b-1.1 12 months ago

Commercial use

3
#18 opened 12 months ago by Codgas

How to run these quantised model.

4
#17 opened 12 months ago by Tarun1986
New activity in eachadea/ggml-vicuna-7b-1.1 12 months ago

Unable to load with transformers library as config files are missing.

3
#4 opened 12 months ago by mlwithaarvy
New activity in eachadea/ggml-vicuna-13b-1.1 about 1 year ago

ggml-vicuna-13b-1.1-q4_3 unrecognized tensor type 5

6
#10 opened about 1 year ago by NicRaf

"Backwards compatibility" of a model?

5
#13 opened about 1 year ago by endolith
New activity in eachadea/ggml-toolpaca-13b-4bit about 1 year ago

How do you use this?

3
#1 opened about 1 year ago by endolith
New activity in eachadea/ggml-vicuna-13b-1.1 about 1 year ago

ggml-vic13b-uncensored-q5_1.bin and ggml-vic13b-uncensored-q8_0.bin throw errors in newest oobabooga-webui

2
#14 opened about 1 year ago by RandomLegend

AMD GPU Support?

1
#12 opened about 1 year ago by Wats0n
New activity in eachadea/vicuna-13b-1.1 about 1 year ago

just saying it breaks whenever i get individual models to load for oobabooga

3
#5 opened about 1 year ago by hellothereeeee
New activity in eachadea/ggml-vicuna-13b-1.1 about 1 year ago

Will a 1.1-uncensored follow?

3
#11 opened about 1 year ago by Wubbbi
New activity in eachadea/vicuna-13b-1.1 about 1 year ago

running the model in Python

2
#3 opened about 1 year ago by Asaf-Yehudai
New activity in eachadea/ggml-vicuna-7b-1.1 about 1 year ago

AutoModelForCausalLM.from_pretrained() error

1
#2 opened about 1 year ago by liyang31163150
New activity in eachadea/ggml-vicuna-13b-1.1 about 1 year ago

vicuna 1.1 13b q4_1 failed to load (bad float16)

2
#9 opened about 1 year ago by couchpotato888

How to get running using fastchat on a m1 mac?

3
#7 opened about 1 year ago by kkostecky
New activity in eachadea/legacy-ggml-vicuna-7b-4bit about 1 year ago

Outstanding Model

4
#3 opened about 1 year ago by Phew
New activity in eachadea/ggml-vicuna-13b-1.1 about 1 year ago

Memory requirement for 13B 4Bit

1
#4 opened about 1 year ago by afoam

SOLVED Running this v1.1 on llama.cpp

2
#3 opened about 1 year ago by JeroenAdam
New activity in eachadea/vicuna-13b-1.1 about 1 year ago

My observation over the previous model

1
#2 opened about 1 year ago by samjack
New activity in eachadea/legacy-vicuna-13b about 1 year ago

how to get 30B vicuna

3
#6 opened about 1 year ago by baby1
New activity in eachadea/ggml-vicuna-13b-1.1 about 1 year ago

where could get 30B

1
#1 opened about 1 year ago by baby1
New activity in eachadea/legacy-ggml-vicuna-13b-4bit about 1 year ago

The problem in GPTQ Vicuna and GGML Vicuna

1
#8 opened about 1 year ago by Feng7815
New activity in eachadea/vicuna-13b-1.1 about 1 year ago

What's new?

2
#1 opened about 1 year ago by BBLL3456
New activity in eachadea/legacy-vicuna-13b about 1 year ago

what's the origin train data

2
#5 opened about 1 year ago by baby1
New activity in eachadea/legacy-ggml-vicuna-7b-4bit about 1 year ago

Could you try converting AlekseyKorshuk's "ethics filtering free" Vicuna model?

1
#6 opened about 1 year ago by wojhoiw
New activity in jordiclive/gpt4all-alpaca-oa-codealpaca-lora-7b about 1 year ago

Missing config.json?

1
#1 opened about 1 year ago by eachadea
New activity in eachadea/legacy-ggml-vicuna-7b-4bit about 1 year ago

How to configure llama.cpp

1
#5 opened about 1 year ago by killerx7
New activity in eachadea/legacy-ggml-vicuna-13b-4bit about 1 year ago

What is "-rev1" ?

3
#5 opened about 1 year ago by pymike00

What is the source, not anon8231489123_vicuna-13b-GPTQ-4bit-128g?

1
#4 opened about 1 year ago by ai2p
New activity in anon8231489123/vicuna-13b-GPTQ-4bit-128g about 1 year ago

ggml conversion error

6
#1 opened about 1 year ago by Reggie
New activity in eachadea/legacy-ggml-vicuna-7b-4bit about 1 year ago

Safetensors for Oobaboonga?

2
#4 opened about 1 year ago by manolofloyd
New activity in eachadea/legacy-vicuna-13b about 1 year ago

Tokenizer class LlamaTokenizer does not exist

8
#2 opened about 1 year ago by xerxes01
New activity in eachadea/legacy-ggml-vicuna-7b-4bit about 1 year ago

Where did you get model weights from

3
#2 opened about 1 year ago by tarunchand
New activity in eachadea/legacy-ggml-vicuna-13b-4bit about 1 year ago

Could someone put this file in a torrent, please?

4
#2 opened about 1 year ago by edmundronald
New activity in lmsys/vicuna-13b-delta-v0 about 1 year ago

quantized model to 4 but or 8 bit

2
#1 opened about 1 year ago by thefcraft
New activity in eachadea/legacy-ggml-vicuna-13b-4bit about 1 year ago

Unable to run llama.cpp

9
#1 opened about 1 year ago by cestoliv