OpenAssistant/oasst-sft-6-llama-30b-xor

#67 opened over 1 year ago by

Meatmms

What happened? This model was removed from chat?

3

#66 opened over 1 year ago by

iNeverLearnedHowToRead

Gpt

#65 opened over 1 year ago by

Sgmod

can someone clarify if the original weights for which version of llama model this requires?

#64 opened over 1 year ago by

kbmlcoding

Is this model censored in any capacity?

#63 opened over 1 year ago by

ReXommendation

What am I supposed to do here ?

#61 opened over 1 year ago by

RahimTS

Integrating LLAMA in Python for generating texts using prompt

#58 opened over 1 year ago by

khorg0sh

commercial use

#57 opened over 1 year ago by

Hans347

Change max_length (characters count) from 2040 to 4096

#53 opened almost 2 years ago by

aman4vr

New token key requirements? How do I call to get a token here:

#51 opened almost 2 years ago by

awacke1

Update README.md

#49 opened almost 2 years ago by

elizeubjunior

Problem with HF LLaMA conversion script step 5

#48 opened almost 2 years ago by

DevVipin

🙏Thanks for this awesome model set and datasets - love this community! 🎓💡

#45 opened almost 2 years ago by

awacke1

Answers coming up just a few words short, literally

#44 opened almost 2 years ago by

Groundarts

Node js transformation

#43 opened almost 2 years ago by

sunil23391

ggml models

#41 opened almost 2 years ago by

Yahir

Update README.md

#39 opened almost 2 years ago by

kraaghavin

System Requirement for oasst-sft-6-llama-30b-xor

#38 opened almost 2 years ago by

Sosothegreat

Checksums

6

#36 opened almost 2 years ago by

abdulsalambande

请求：DOI

6

#34 opened almost 2 years ago by

Redcnn

How to chat with model via API?

7

#33 opened almost 2 years ago by

InsafQ

The josn file seems to be garbled when it is opened

#32 opened almost 2 years ago by

Critejon

training code

#31 opened almost 2 years ago by

winglian

Non-Commericial

#30 opened almost 2 years ago by

jwr1015

It can't answer a lot of questions right.

3

#29 opened almost 2 years ago by

alexchenyu

OSError: It looks like the config file at './data/config.json' is not a valid JSON file.

6

#27 opened almost 2 years ago by

ShyFoo

can we use this model to finetune it on our specific dataset , like how other models hosted on hugging face is done.

#26 opened almost 2 years ago by

MukeshSharma

Model returns empty prompt.

#24 opened almost 2 years ago by

shmalex

HuggingChat hardware requirements

#23 opened almost 2 years ago by

InferencetrainingAI

checksum does not match

11

#22 opened almost 2 years ago by

YannisTevissen

Video needed :)

#20 opened almost 2 years ago by

RedwanEl

XOR conversion fails: missing params.json

#19 opened almost 2 years ago by

ccsum

using pipeline

#18 opened almost 2 years ago by

halow87

Windows coversion almost successful

3

#17 opened almost 2 years ago by

DontLike

Where to find the original weights of LLama?

#15 opened almost 2 years ago by

coiler

How is everyone running/interacting the model?

#10 opened almost 2 years ago by

Elijah-Kulpinski

How can I do inference with this model?

#5 opened almost 2 years ago by

Grambel

Trying to convert LlaMa weights to HF and running out of RAM, but don't want to buy more RAM?

14

#4 opened almost 2 years ago by

daryl149

Converting to ggml and quantizing with llama.cpp

#2 opened almost 2 years ago by

akiselev

Dependency Versions