Skip to content
This repository was archived by the owner on May 1, 2025. It is now read-only.

Add RWKV models #16

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Add RWKV models #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2a08824
Add RWKV models
guangyusong Jun 5, 2023
5bb1017
Update README.md
guangyusong Jun 5, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,7 @@ The following table shows the supported models with sizes and the tasks that the
| GPT-NeoX | 20B | Pretrained |
| GPT-Neo | 1.3B | Pretrained |
| GPT-J | 6B | Pretrained |
| RWKV | 169M, 430M, 1.5B, 3B, 7B, 14B | Pretrained |
| Incoder | 6B | Pretrained |
| CodeParrot | Small-python (110M), Small-multi(110M), 1.5B | Pretrained |
| CodeBERT | CodeBERT-base, UnixCoder-base, CodeBERTa-small | Pretrained |
Expand Down Expand Up @@ -157,6 +158,12 @@ print(model_zoo)
# codegen2-3.7B pretrained
# codegen2-7B pretrained
# codegen2-16B pretrained
# rwkv-169M pretrained
# rwkv-430M pretrained
# rwkv-1.5B pretrained
# rwkv-3B pretrained
# rwkv-7B pretrained
# rwkv-14B pretrained
# codet5 base-multi-sum pretrained
# base nl2code
# base refine
Expand Down
24 changes: 24 additions & 0 deletions codetf/configs/inference/causal_lm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,4 +68,28 @@ causallm-codegen2-7B-pretrained:
causallm-codegen2-16B-pretrained:
huggingface_url: "Salesforce/codegen2-16B"
tokenizer_url: "Salesforce/codegen2-16B"
max_prediction_length: 512
causallm-rwkv-169M-pretrained:
huggingface_url: "RWKV/rwkv-4-169m-pile"
tokenizer_url: "RWKV/rwkv-4-169m-pile"
max_prediction_length: 512
causallm-rwkv-430M-pretrained:
huggingface_url: "RWKV/rwkv-4-430m-pile"
tokenizer_url: "RWKV/rwkv-4-430m-pile"
max_prediction_length: 512
causallm-rwkv-1.5B-pretrained:
huggingface_url: "RWKV/rwkv-raven-1b5"
tokenizer_url: "RWKV/rwkv-raven-1b5"
max_prediction_length: 512
causallm-rwkv-3B-pretrained:
huggingface_url: "RWKV/rwkv-raven-3b"
tokenizer_url: "RWKV/rwkv-raven-3b"
max_prediction_length: 512
causallm-rwkv-7B-pretrained:
huggingface_url: "RWKV/rwkv-raven-7b"
tokenizer_url: "RWKV/rwkv-raven-7b"
max_prediction_length: 512
causallm-rwkv-14B-pretrained:
huggingface_url: "RWKV/rwkv-raven-14b"
tokenizer_url: "RWKV/rwkv-raven-14b"
max_prediction_length: 512