Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / ofirpress/attention_with_linear_biases issues and pull requests
#20 - ALiBi during inference
Issue -
State: closed - Opened by VarunGumma 8 months ago
- 1 comment
Labels: question
#19 - Imeplementation about ALibi
Issue -
State: closed - Opened by DreamShibei about 1 year ago
- 1 comment
Labels: question
#18 - implementation detail about alibi_mask
Issue -
State: open - Opened by bugm about 1 year ago
Labels: question
#17 - For a value of `12` I'm seeing a jump in the plotting of values, e.g. `0.7` shown below.
Issue -
State: open - Opened by razodactyl over 1 year ago
#16 - What is the extrapolation method used in the paper?
Issue -
State: closed - Opened by XinyuDu over 1 year ago
- 1 comment
Labels: question
#15 - can you tell me how to use alibi while fine-tuning LLAMA model?
Issue -
State: closed - Opened by kiran1501 over 1 year ago
- 1 comment
Labels: question
#14 - Have you initialized the model with other model checkpoints during training?
Issue -
State: closed - Opened by Victoriaheiheihei over 1 year ago
- 1 comment
Labels: question
#13 - could we apply Alibi with rotary position embedding?
Issue -
State: closed - Opened by xiaoxiawu-microsoft almost 2 years ago
- 1 comment
Labels: question
#12 - Is there any easy way to get a HF compatible version of your checkpoints?
Issue -
State: closed - Opened by petroskarypis almost 2 years ago
- 2 comments
Labels: question
#11 - How can I apply ALiBi Position Encoding into huggingface model?
Issue -
State: closed - Opened by hjsg1010 almost 2 years ago
- 3 comments
Labels: question
#10 - How to perform sliding window evaluation?
Issue -
State: closed - Opened by chijames over 2 years ago
- 2 comments
Labels: question
#9 - The numerical value of ALiBi attn_mask
Issue -
State: closed - Opened by chijames over 2 years ago
- 3 comments
Labels: question
#8 - ALiBi in Parallel Attention
Issue -
State: closed - Opened by conceptofmind over 2 years ago
- 2 comments
Labels: question
#7 - Explanation regarding multiplying linear biases with q.k^T
Issue -
State: closed - Opened by sayakpaul almost 3 years ago
- 4 comments
#6 - Integration with `transformers`
Issue -
State: closed - Opened by sayakpaul almost 3 years ago
- 1 comment
#5 - Modifying ALiBi for Encoder-Attention or Cross-Attention
Issue -
State: open - Opened by ofirpress over 3 years ago
- 29 comments
Labels: question
#4 - ALiBi in self-Attention
Issue -
State: closed - Opened by Ldoun over 3 years ago
- 2 comments
Labels: question
#3 - Abili on LongformerEncoderDecoder
Issue -
State: closed - Opened by beaupranisaa over 3 years ago
- 1 comment
Labels: question
#2 - unrecognized argument --max-lr
Issue -
State: closed - Opened by cifkao over 3 years ago
- 3 comments
Labels: bug
#1 - Fix preprocess.py path
Pull Request -
State: closed - Opened by cifkao over 3 years ago
- 3 comments