29c7f2565d
Add some reinforcement learning example. ( #1090 )
...
* Add some reinforcement learning example.
* Python initialization.
* Get the example to run.
* Vectorized gym envs for the atari wrappers.
* Get some simulation loop to run.
2023-10-14 16:46:43 +01:00
890d069092
Self-contained safetensor wrappers ( #946 )
...
* Self-contained safetensor wrappers.
* Use the new safetensor container in varbuilders.
2023-09-23 20:39:52 +01:00
aa8ec06fd2
Add the t5-xxl version. ( #924 )
2023-09-21 14:48:13 +01:00
9b24d89d2d
Tracing mode for T5. ( #913 )
...
* Tracing mode for T5.
* Tracing for the linear layer.
2023-09-20 15:03:35 +01:00
8696f64bae
Fix T5 kv cache ( #899 )
...
* Fix T5 kv cache
* Add argument for decoder prompt
* Fix range
2023-09-19 20:36:15 +01:00
1542e92629
T5: Add option to override use_cache from config ( #892 )
...
* Add option to override use_cache from config
* Disable cache by default and cleanup code
2023-09-18 20:20:21 +01:00
7f65af1f0d
Avoid re-encoding the input in the T5 example. ( #875 )
2023-09-17 10:25:54 +01:00
eeb54716dd
Tweaks for the T5 example. ( #874 )
2023-09-17 10:05:15 +01:00
1a276b5da7
Add a KV cache to T5. ( #873 )
...
* Add a KV cache to T5.
* Suggest using release mode.
* Use the kv cache in decoding.
* Add a comment.
2023-09-17 08:00:45 +01:00
3e49f8fce5
Implement T5 decoding ( #864 )
...
* Load t5 decoder
* Run enc, dec, and lm head, but no cross attn
* Cross-attention over key_value_states
* New arg for decoder input ids
* Add mask, don't forward position biases through decoder
* Update t5 examples
* Clippy + rustfmt
2023-09-15 22:05:12 +02:00
31ab2ddaeb
Remove the padding. ( #838 )
2023-09-13 13:00:59 +01:00
3e94324012
Add some sentence similarity part to the t5 example. ( #835 )
...
* Add some sentence similarity part to the t5 example.
* Clippy fix.
2023-09-13 10:44:02 +01:00
e4553fb355
T5 tweaks ( #831 )
...
* Use default values rather than options.
* Avoid exposing the device field.
* More tweaks.
2023-09-13 07:37:04 +01:00
9daa6dbe87
Extract T5 module and add main function to use it ( #829 )
...
* Extract t5 out of musicgen
* Add main for t5 module
2023-09-13 07:14:05 +01:00
