meta-llama/Meta-Llama-3-8B-Instruct

Using Llama offline with transformers is slow and response is repeating itself

#139 opened over 1 year ago by

AyoxRay

Request to access the repo

#138 opened over 1 year ago by

anatris

Meta-Llama-3-8B-Instruct: "max_new_tokens" is not working for /v1/chat/completions

🔥 1

#137 opened over 1 year ago by

kuswe

Add co2_eq_emissions to README so that the HF API exposes this info to users.

#136 opened over 1 year ago by

selenecodes

Despite latest transformers version '4.41.1', I get the error: The model 'LlamaModel' is not supported for text-generation

#134 opened over 1 year ago by

guptaansit

Changing maximum input length

#133 opened over 1 year ago by

shipWr3ck

How to introduce stop_strings in llama3?

#132 opened over 1 year ago by

Srinjoy

*** OSError: meta-llama/Meta-Llama-3-8B-Instruct does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.

3

#131 opened over 1 year ago by

akjagadish

use inference api

6

#127 opened over 1 year ago by

Miralaeeop1

How to stop Llama from generating follow-up questions and excessive conversation with langchain

1

#125 opened over 1 year ago by

pelumifagbemi

Compatibility with llama-cpp-python and Ollama

#124 opened over 1 year ago by

liashchynskyi

Cloning 'Meta-Llama-3-8B-Instruct' taking excessively long time

#121 opened over 1 year ago by

guptaansit

Discrepancy between Base and Instruct model eos_token.

👀 1

#119 opened over 1 year ago by

richardlian

System prompt during Fine Tuning

#117 opened over 1 year ago by

matteoperiani

Local configuration with LlamaCpp

#116 opened over 1 year ago by

alessandervs

login does not work on fine tuned model

🔥 1

2

#114 opened over 1 year ago by

Dave-theGr8

Original Directory

#113 opened over 1 year ago by

raunakkumar

It can be used with JavaScript if yes, how can I assign a role and some custom parameters

#111 opened over 1 year ago by

vdggds

Request: DOI

#110 opened over 1 year ago by

SushantGautam

tokenizer.model can't be loaded by SentencePiece: "RuntimeError: Internal: could not parse ModelProto from tokenizer.model"

👍 6

9

#109 opened over 1 year ago by

ericx134

PrivateGPT settings

#108 opened over 1 year ago by

kickinai

Possible stopping issues?

4

#106 opened over 1 year ago by

Dampfinchen

Tokenizer Chat Template

4

#103 opened over 1 year ago by

Sm1Ling

It`s a great job ~!!!!!!

#102 opened over 1 year ago by

MallemJerry

Why there is not pad token?

25

#101 opened over 1 year ago by

Imran1

Slow API Calls in Transformers

🤝 3

4

#98 opened over 1 year ago by

Zifeng01code

Llama3 8b related model has bursting issues when it generates emotion-related words

👍 2

#95 opened over 1 year ago by

HyperBlaze

Where can I get a config.json file for Meta-Llama-3-8B-instruct?

2

#93 opened over 1 year ago by

gdb94086

Local Mobile Device Hosting

1

#91 opened over 1 year ago by

suguspnk

How should names & fewshot examples be encoded?

👀 8

#89 opened over 1 year ago by

theobjectivedad

Please provide some guidance or documentation on tool usage.

👍 2

#88 opened over 1 year ago by

lcahill

AttributeError: type object 'AttentionMaskConverter' has no attribute '_ignore_causal_mask_sdpa'

#87 opened over 1 year ago by

gy19

Your request to access this repo has been successfully submitted, and is pending a review from the repo's authors.

1

#86 opened over 1 year ago by

g3stz

Model Generating Prefix

👍 1

1

#85 opened over 1 year ago by

dongyulin

cant get access

1

#84 opened over 1 year ago by

ERmak158

Meta-Llama-3-8B-Instruct does not appear to have a file named config.json

9

#82 opened over 1 year ago by

RK-RK

Access issues via Meta website and HF

#81 opened over 1 year ago by

GiorgioDiSalvo

Plans for a 13B model?

#80 opened over 1 year ago by

Cheeto96

not getting the right output

2

#79 opened over 1 year ago by

Sardarmoazzam

what memory needed ?

1

#78 opened over 1 year ago by

francescofiamingo

Key Error 'llma' in configuration_auto.py

1

#76 opened over 1 year ago by

himasrikode

Your request to access this repo has been rejected by the repo's authors.

13

#74 opened over 1 year ago by

Hoo1196

Changing "eos_token" to eot-id fix the issue of overflow of model response - at least using the Messages API.

👍 1

1

#73 opened over 1 year ago by

myonlyeye

How to Fine-tune Llama-3 8B Instruct.

➕ 👀 2

8

#72 opened over 1 year ago by

elysiia

Update config.json

1

#71 opened over 1 year ago by

ArthurZ

The request to access the repo has been sent for several days, why hasn't it passed yet?

7

#70 opened over 1 year ago by

water-cui

AttributeError: type object 'AttentionMaskConverter' has no attribute '_ignore_causal_mask_sdpa' [ ]:

4

#69 opened over 1 year ago by

tianke0711

Access given still not working.

10

#68 opened over 1 year ago by

adityar23

请321

#67 opened over 1 year ago by

xumeng

Uncaught (in promise) SyntaxError: Unexpected token 'E', "Expected r"... is not valid JSON

🤯 1

5

#66 opened over 1 year ago by

sxmss1