meta-llama/Llama-3.1-8B-Instruct

#82 opened about 2 months ago by

deshwalmahesh

GSM8K Evaluation Result: 84.5 vs. 76.95

17

#81 opened about 2 months ago by

tanliboy

Deploying Llama3.1 to Nvidia T4 instance (sagemaker endpoints)

#80 opened about 2 months ago by

mleiter

Variable answer is getting predicted for same prompt

#79 opened about 2 months ago by

sjainlucky

Efficiency low after adding the adapter_model.safetensors with base model

#78 opened about 2 months ago by

antony-pk

Minimum gpu ram capacity

#77 opened about 2 months ago by

bob-sj

Tokenizer padding token

#76 opened about 2 months ago by

Rish1

new tokenizer contains the cutoff date and today date by default

#74 opened about 2 months ago by

yuchenlin

New bee questions

#73 opened about 2 months ago by

rkapuaala

Add `base_model` metadata

#72 opened about 2 months ago by

sbrandeis

Full SFT training caused lose its foundational capabilities

#71 opened about 2 months ago by

sinlew

Wrong number of tensors; expected 292, got 291

#69 opened about 2 months ago by

KingBadger

Fine tuned Meta-Llama-3.1-8B-Instruct deployment on AWS Sagemaker fails

#68 opened about 2 months ago by

byamasuwhatnowis

Quick Fix: Rope Scaling or Rope Type Error

#67 opened about 2 months ago by

deepaksiloka

Can't reproduce MATH performance

#66 opened about 2 months ago by

jpiabrantes

Banned for Iranian People

13

#65 opened about 2 months ago by

MustafaLotfi

Inference endpoint deployment for 'meta-llama/Meta-Llama-3.1-8B-Instruct' fails

#62 opened about 2 months ago by

Keertiraj

Meta-Llama-3.1-8B-Instruct deployment on AWS Sagemaker fails

#61 opened about 2 months ago by

Keertiraj

Error Loading the original model file consolidated.00.pth from local

#60 opened about 2 months ago by

chanduvkp

vdl

#59 opened about 2 months ago by

danakin1

Unable to deploy Meta-Llama-3.1-8B-Instruct model on Sagemaker

#58 opened about 2 months ago by

axs531622

CUDA out of memory on RTX A5000 inference.

#57 opened 2 months ago by

RoberyanL

Update README.md to reflect correct transformers version

#56 opened 2 months ago by

priyakhandelwal

Update README.md to reflect correct transformers version

#55 opened 2 months ago by

priyakhandelwal

NotImplementedError: Could not run 'aten::_local_scalar_dense' with arguments from the 'Meta' backend.

#54 opened 2 months ago by

duccio84

Some of you might be interested in my 'silly' experiment.

#52 opened 2 months ago by

ZeroWw

Updated config.json

#51 opened 2 months ago by

WestM

🚀 LMDeploy support Llama3.1 and its Tool Calling. An example of calling "Wolfram Alpha" to perform complex mathematical calculations can be found from here!

#50 opened 2 months ago by

vansin

HF pro subscription for llama 3.1-8b

#49 opened 2 months ago by

ostoslista

Significant bias

#48 opened 2 months ago by

stutteringp0et

`rope_scaling` must be a dictionary with two fields

#46 opened 2 months ago by

thunderdagger

Unable to load Llama 3.1 to Text-Genration WebUI

#45 opened 2 months ago by

keeeeesz

BUG Chat template doesn't respect `add_generation_prompt`flag from transformers tokenizer

#44 opened 2 months ago by

ilu000

How to use the ASR on LLama3.1

#43 opened 2 months ago by

andrygasy

Tokenizer 'apply_chat_template' issue

#42 opened 2 months ago by

Ksgk-fy

Function Calling Evaluation bench Nexus (0-shot)

#41 opened 2 months ago by

WateBear

Error: json: cannot unmarshal array into Go struct field Params.eos_token_id of type int

#40 opened 2 months ago by

SadeghPouriyan

ValueError: Pipeline with tokenizer without pad_token cannot do batching. You can try to set it with `pipe.tokenizer.pad_token_id = model.config.eos_token_id`.

#39 opened 2 months ago by

jsemrau

Run this on CPU and use tool calling

#38 opened 2 months ago by

J22

!!Access Problem

11

#37 opened 2 months ago by

fengzi258

LLama-3.1-8B generates way to long answers!

#36 opened 2 months ago by

ayyylemao

Tokenizer error and/or 'rope_scaling' problem

5

#35 opened 2 months ago by

fazayjo

Deployment to Inference Endpoints

#34 opened 2 months ago by

stmackcat

Best practice for tool calling with meta-llama/Meta-Llama-3.1-8B-Instruct

#33 opened 2 months ago by

zzclynn

The model often enters infinite generation loops

13

#32 opened 2 months ago by

sszymczyk

unable to load 4-bit quantized varient with llama.cpp

#31 opened 2 months ago by

sunnykusawa

Garbage output ?

8

#30 opened 2 months ago by

danielus

Question about chat template and fine-tuning