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

#123 opened 9 months ago by

alice86

where to update max_prompt_len(to solve max_prompt_len <= params.max_seq_len, preferably using AWS JumpStart)

#121 opened 9 months ago by

wichofer

Getting "Killed" out of memeory after shards is executed

4

#119 opened 10 months ago by

nitin1607

[IFEVAL Dataset] Inquiry on Performance Metrics Decrease in LLaMA 3.1 Strict Levels Between July 18 and 22 Versions

👀 2

#118 opened 10 months ago by

linmoska

Seems overcooked in comparison to LLama 3.0 - short feedback

#117 opened 10 months ago by

Dampfinchen

how should i provide prompts to the model that is locally downloaded and then used?

#116 opened 10 months ago by

ayadav1

Update config.json

#115 opened 10 months ago by

mohdazlah

Need a little guidance accessing https://huggingface.co/spaces/stevenijacobs/AI4Reading using an API. I'm trying to setup a resource to help students with learning disabilities.

#114 opened 10 months ago by

stevenijacobs

Add missing space in prompt template

🔥 1

5

#113 opened 10 months ago by

Rocketknight1

UPDATE README.md

#112 opened 10 months ago by

Kryslynn93

tokenizer offset_mapping is incorrect

#111 opened 10 months ago by

Aflt98

KeyError: 'llama'

#110 opened 10 months ago by

ronnief1

OutOfMemoryError: CUDA out of memory

#109 opened 10 months ago by

sieudd

Issue with accessing gated repo

7

#107 opened 10 months ago by

vdcapriles

Deploy error (RuntimeError: weight lm_head.weight does not exist)

#106 opened 10 months ago by

steveleancommerce

"TypeError: Object of type Undefined is not JSON serializable" when tokenizing tool_call inputs

#104 opened 10 months ago by

ztgeng

Formats for prompting the model using Hugging face

#103 opened 10 months ago by

javalenzuela

Request: DOI

#102 opened 10 months ago by

guicozmaciel

Time Module issue or Model?

#101 opened 10 months ago by

rkapuaala

Issues with Tools use and Chat templates

#99 opened 10 months ago by

pyrator

Upgrading Linux Dist

#98 opened 10 months ago by

rkapuaala

Clone Repository

👍 2

#96 opened 10 months ago by

clearcash

llama3.1 gguf format

#95 opened 10 months ago by

davidomars

Crashes

#94 opened 10 months ago by

wing1x

how can i use git clone Meta-Llama-3.1-8B-Instruct

#93 opened 10 months ago by

xiangsuyu

Asking for Pro subscription

6

#92 opened 10 months ago by

Mayo133

update rope_scaling

#91 opened 10 months ago by

Arunjith

Update for correct tool use system prompt

#90 opened 10 months ago by

ricklamers

What call() function parameters besides "query" can be used by the model when doing brave_search and wolfram_alpha tool calls?

#89 opened 10 months ago by

sszymczyk

What form of the built-in brave_search and wolfram_alpha tool call output is expected by the model?

➕ 1

#88 opened 10 months ago by

sszymczyk

ValueError

#87 opened 10 months ago by

Bmurug3

Request: DOI

#86 opened 10 months ago by

sanjeev929

Request: DOI

#85 opened 10 months ago by

moh996

The model repeatedly outputs a large amount of text and does not comply with the instructs.

10

#84 opened 10 months ago by

baremetal

Llama repo access not aproved yet

#83 opened 10 months ago by

APaul1

Throwing Error for AutoModelForSequence Classification

#82 opened 10 months ago by

deshwalmahesh

GSM8K Evaluation Result: 84.5 vs. 76.95

17

#81 opened 10 months ago by

tanliboy

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

4

#80 opened 10 months ago by

mleiter

Variable answer is getting predicted for same prompt

#79 opened 10 months ago by

sjainlucky

Efficiency low after adding the adapter_model.safetensors with base model

#78 opened 10 months ago by

antony-pk

Minimum gpu ram capacity

🔥 2

12

#77 opened 10 months ago by

bob-sj

Tokenizer padding token

#76 opened 10 months ago by

Rish1

new tokenizer contains the cutoff date and today date by default

5

#74 opened 10 months ago by

yuchenlin

New bee questions

#73 opened 10 months ago by

rkapuaala

Add `base_model` metadata

#72 opened 10 months ago by

sbrandeis

Full SFT training caused lose its foundational capabilities

10

#71 opened 10 months ago by

sinlew

Wrong number of tensors; expected 292, got 291

6

#69 opened 11 months ago by

KingBadger

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

➕ 7

#68 opened 11 months ago by

byamasuwhatnowis

Quick Fix: Rope Scaling or Rope Type Error

4

#67 opened 11 months ago by

deepaksiloka

Can't reproduce MATH performance