microsoft
/

phi-2

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (95)

Minumum gpu ram to fine tune phi-2 on custom data and what should be the datarows to fine tune phi-2 model.

#126 opened 24 days ago by

Model inference speed is too slow (positively related to max_new_tokens length)

#125 opened 29 days ago by

inference Endpoints error

#124 opened about 1 month ago by

Generation after finetuning does not ends at EOS token

#123 opened about 1 month ago by

Trouble with Phi2 Tokenisation

#116 opened 2 months ago by

Target modules {'out_proj', 'Wqkv'} is not found in the phi-2 model how can I fix this error?

#115 opened 2 months ago by

Fine tuned phi2 model loses context once loaded from local

#112 opened 3 months ago by

Disabled autocast

#109 opened 3 months ago by

Model not loading from local directory

#108 opened 3 months ago by

Phi-2 prompt engineering

#107 opened 3 months ago by

Training model breaks with flash_attn_2. Error "NameError: name 'index_first_axis' is not defined"

#105 opened 3 months ago by

I encountered an error when attempting to train phi

#104 opened 3 months ago by

instruct fone tune phi2 on custom data

#103 opened 3 months ago by

How to finetune Phi2 using RoPE and QLoRA for long text summary generation?

#102 opened 3 months ago by

supervised finetuning error

#96 opened 4 months ago by

How to generate a gguf file from a fine tuned phi-2 ?

#93 opened 4 months ago by

Loading a qlora finetuned checkpoint with the new updates outputs differently

#88 opened 4 months ago by

How to reduce nonsense generation?

#81 opened 4 months ago by

Cannot load the model PhiForSequenceClassificationModified(basemodel.config)

#80 opened 4 months ago by

Irrelevant text generation while prompting

#63 opened 4 months ago by

run Phi-2 on your CPU

#62 opened 4 months ago by

J22

Responses by phi-2 are off, it's depressed and insults me for no reason whatsover?

#61 opened 4 months ago by

"Instruct: <prompt>\nOutput:" or "Instruction: <prompt>\nOutput:"

#60 opened 4 months ago by

J22

What is the best way for the inference process in LORA in PEFT approach

#53 opened 4 months ago by

[Positivity] What is it good for?

#52 opened 4 months ago by

Review on Phi-2

#45 opened 5 months ago by

Can inference be done with the model converted to OpenVINO?

#44 opened 5 months ago by

Unimpressed by Phi-2

#39 opened 5 months ago by

How to fine-tune this? + Training code

#19 opened 5 months ago by