Gustavo de Rosa

#68 opened 9 days ago by

philschmid

New activity in microsoft/Phi-3-small-128k-instruct 11 days ago

Upload 3 files

#1 opened 11 days ago by

bapatra

New activity in microsoft/Phi-3-small-8k-instruct 11 days ago

Upload 3 files

#1 opened 11 days ago by

bapatra

New activity in microsoft/Phi-3-mini-128k-instruct-onnx 23 days ago

error in tokenizer

#5 opened 24 days ago by

Algaliarept

New activity in microsoft/Phi-3-mini-128k-instruct 23 days ago

Upload 25 files

#59 opened 24 days ago by

jf8441

New activity in microsoft/Phi-3-mini-4k-instruct 28 days ago

Fine-tuning is not improving the domain knowledge? it is very complicated, could you help?

5

#50 opened about 1 month ago by

aaditya

New activity in microsoft/Phi-3-mini-128k-instruct 29 days ago

Model can't stop from explaining itself

8

#53 opened 29 days ago by

fedeparra

Pipeline tokenizer does not get initialized when loading from string

#50 opened 30 days ago by

connorboyle

model destroyed by deleting tokens?

#52 opened 29 days ago by

NickyNicky

Phi-3 instruct model continuously repeating the answer

#55 opened 29 days ago by

bitmman-nch

Get target_modules

#56 opened 29 days ago by

danny3

New activity in microsoft/Phi-3-mini-4k-instruct 29 days ago

System prompts ignored in chat completions

12

#51 opened about 1 month ago by

joshuaturner

Phi-3 support for GPU training with MPS on Mac

#52 opened 30 days ago by

chaishirin

Leaking Training Data

3

#40 opened about 1 month ago by

qunitindk

New activity in microsoft/Phi-3-mini-128k-instruct 29 days ago

fix(tokenizer_config): Adjusts `rstrip` of special tokens.

#54 opened 29 days ago by

gugarosa

New activity in microsoft/Phi-3-mini-4k-instruct 29 days ago

fix(tokenizer_config): Adjusts `rstrip` of special tokens.

#53 opened 29 days ago by

gugarosa

New activity in microsoft/Phi-3-mini-4k-instruct about 1 month ago

Instruct model needs work

8

#35 opened about 1 month ago by

Nafnlaus

New activity in microsoft/Phi-3-mini-128k-instruct about 1 month ago

gguf

30

#24 opened about 1 month ago by

LaferriereJC

Very good model for its size (7b and 14b are gonna be amazing)

4

#43 opened about 1 month ago by

rombodawg

Lmsys Leaderboard Update! Impressive MMLU Scores

#44 opened about 1 month ago by

saishf

Probably Memory Leak issue？

#46 opened about 1 month ago by

Tieni

clarification on the usage of `short_factor` and `long_factor`?

#49 opened about 1 month ago by

J22

Could you aid in getting Llama.cpp to support the 128K version?

#48 opened about 1 month ago by

BoscoTheDog

Tokenizer

#23 opened about 1 month ago by

vschindepalli

New activity in microsoft/Phi-3-mini-4k-instruct about 1 month ago

the phi3 model not learning from training data using orpo.

3

#44 opened about 1 month ago by

Imran1

is the '\n' after `'<|end|>'`?

#43 opened about 1 month ago by

J22

Cant download the model in databricks

#36 opened about 1 month ago by

Buchhibabu

ImportError: This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`

#48 opened about 1 month ago by

Sulilili

Loading SPM tokenizer shows 32000 vocab size instead of 32064

4

#47 opened about 1 month ago by

jrc

How to configure config.json properly to suppress noise?

#49 opened about 1 month ago by

don412

New activity in microsoft/Phi-3-mini-4k-instruct-gguf about 1 month ago

New gguf chat template ignores the 'system' role when preparing chat completions

3

#11 opened about 1 month ago by

joshuaturner

Model breaks if I use word "unani".

#9 opened about 1 month ago by

mdmujtabaraza

More quants?

4

#5 opened about 1 month ago by

MoonRide

Can't reproduce

5

#3 opened about 1 month ago by

ayyylol

New activity in microsoft/phi-1_5 about 1 month ago

Something broken on last update

7

#85 opened about 1 month ago by

Nayjest

New activity in microsoft/Phi-3-mini-128k-instruct about 1 month ago

No base model?

#45 opened about 1 month ago by

ucalyptus

Unable to deploy this model on databricks due to transformers version

#47 opened about 1 month ago by

enkefalos

New activity in microsoft/Phi-3-mini-4k-instruct-onnx about 1 month ago

What is the difference between "cpu-int4-rtn-block-32-acc-level-4" and "cpu-int4-rtn-block-32"?

#3 opened about 1 month ago by

Zhubarb

New activity in microsoft/Phi-3-mini-4k-instruct about 1 month ago

Is the system message irrelevant for Phi3? I don't see any system message in the chat template of tokenizer_config.json.

#46 opened about 1 month ago by

Snehith749

New activity in microsoft/Phi-3-mini-4k-instruct-gguf about 1 month ago

general.architecture = 'llama' in .gguf metadata

#6 opened about 1 month ago by

mattjcly

New activity in microsoft/Phi-3-mini-128k-instruct about 1 month ago

Adding Evaluation Results

#41 opened about 1 month ago by

leaderboard-pr-bot

Update sample_finetune.py

#42 opened about 1 month ago by

wwwaj

New activity in microsoft/Phi-3-mini-4k-instruct about 1 month ago

Adding Evaluation Results

#41 opened about 1 month ago by

leaderboard-pr-bot

Update sample_finetune.py

#42 opened about 1 month ago by

wwwaj

is phi-3 foundation model was released or only instruct fine tuned models relasesd

#37 opened about 1 month ago by

naveen237

Update tokenizer_config.json

#39 opened about 1 month ago by

mrm8488

Update config.json

#38 opened about 1 month ago by

mrm8488

[AUTOMATED] Model Memory Requirements

#33 opened about 1 month ago by

[AUTOMATED] Model Memory Requirements

#32 opened about 1 month ago by

[AUTOMATED] Model Memory Requirements

#31 opened about 1 month ago by

[AUTOMATED] Model Memory Requirements

#30 opened about 1 month ago by

[AUTOMATED] Model Memory Requirements

#29 opened about 1 month ago by

[AUTOMATED] Model Memory Requirements

#28 opened about 1 month ago by

Why is EOS token added at the end of chat template?

#26 opened about 1 month ago by

mspanrin

Is sliding window used or not?

#25 opened about 1 month ago by

J22

你好呀

#24 opened about 1 month ago by

dddfhrs

[AUTOMATED] Model Memory Requirements

#23 opened about 1 month ago by

[AUTOMATED] Model Memory Requirements

#22 opened about 1 month ago by

[AUTOMATED] Model Memory Requirements

#21 opened about 1 month ago by

New activity in microsoft/Phi-3-mini-128k-instruct about 1 month ago

Deployment in dedicated endpoint failing with `Please pass the argument `trust_remote_code=True` to allow custom code to be run.` error