Imran Ullah

After fine tuning gpt3 model, how to know f1 score as a evaluation?

1

After fine tuning gpt3 for text generation, so how I can know f1 score using openai cli ?

Add text generation example

1

### 🚀 The feature, motivation, and pitch I'm working on poetry generation. Please add a text generation example using RLHF. ### Alternatives Text generation example ### Additional context ...

AttributeError: 'NoneType' object has no attribute 'device'

4

why this happening? ``` batch = tokenizer("Two things are infinite: ", return_tensors="pt") with torch.cuda.amp.autocast(): output_tokens = model.generate(**batch, max_new_tokens=50) print("\n\n", tokenizer.decode(output_tokens[0], skip_special_tokens=True)) ``` its give the following error **AttributeError: 'NoneType' object...

TypeError: dispatch_model() got an unexpected keyword argument 'offload_index'

15

================================ ruuning the following code on kaggle notebook give me this error ================================ `import os os.environ["CUDA_VISIBLE_DEVICES"]="0" import torch import torch.nn as nn import bitsandbytes as bnb from transformers import AutoTokenizer,...

RuntimeError: self and mat2 must have the same dtype

8

i got this error when i run the following code ``` import transformers from datasets import load_dataset data = load_dataset('csv',data_files='/content/fyp.csv') data = data.map(lambda samples: tokenizer(samples['completion']), batched=True) trainer = transformers.Trainer( model=model,...

contrastive search and do_sampling

4

I trained bloom17b but for inference they not support both _**contrastive search**_ and _**do_sample**_ parameters The out put are repeating the text Here are the code ``` batch = tokenizer("...

I'm using pytorch 2 for faster training, getting thiserror

3

Getting the following error `ValueError:--optim adamw_torch_fused with --fp16 requires PyTorch>2.0` Using the following code torch_compile=True, optim="adamw_torch_fused", ``` import transformers from datasets import load_dataset datasets = data.map( tokenize, batched=True, remove_columns=data["train"].column_names )...

I trained bloom7b model but for inference they give me error

4

This is the code ``` batch = tokenizer("Two things are infinite: ", return_tensors="pt") with torch.cuda.amp.autocast(): output_tokens = model.generate(**batch, max_new_tokens=50) print("\n\n", tokenizer.decode(output_tokens[0], skip_special_tokens=True)) ``` The error is `AttributeError: 'NoneType' object has...

model saving error

10

the trainer not save the mode weights . its give me the following error ``` OutOfMemoryError: CUDA out of memory. Tried to allocate 16.00 MiB (GPU 0; 14.75 GiB total...

Why langchain embading missing the information.

1

For some questions they give me answer but not for other. But the data are already available in my dataset. How I can improve this!? 😌