summaryrefslogtreecommitdiff
path: root/candle-wasm-examples/llama2-c
Commit message (Collapse)AuthorAgeFilesLines
* Clippy fixes for 1.81.0. (#2461)Laurent Mazare2024-09-051-1/+1
| | | | | * Clippy fixes for 1.81.0. * Another fix.
* Clippy fixes. (#2415)Laurent Mazare2024-08-142-8/+6
| | | | | * Clippy fixes. * Bump the web_sys required version.
* Update gloo requirement from 0.8 to 0.11 (#1558)dependabot[bot]2024-01-101-1/+1
| | | | | | | | | | | | | | | Updates the requirements on [gloo](https://github.com/rustwasm/gloo) to permit the latest version. - [Release notes](https://github.com/rustwasm/gloo/releases) - [Changelog](https://github.com/rustwasm/gloo/blob/master/CHANGELOG.md) - [Commits](https://github.com/rustwasm/gloo/commits) --- updated-dependencies: - dependency-name: gloo dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* Simplifying our internal cargo dependencies. (#1529)Nicolas Patry2024-01-071-3/+3
|
* Fix lints for clippy 1.75. (#1494)Laurent Mazare2023-12-281-6/+6
|
* Bump the crate version to 0.3.3. (#1490)Laurent Mazare2023-12-281-3/+3
|
* Bump the crate version to 0.3.2. (#1452)Laurent Mazare2023-12-171-3/+3
|
* Fix a couple typos (#1451)Laurent Mazare2023-12-172-2/+2
| | | | | * Mixtral quantized instruct. * Fix a couple typos.
* Update for 0.3.1. (#1324)Laurent Mazare2023-11-111-3/+3
|
* llama2-c wasm fix.Laurent2023-11-021-1/+3
|
* Minor cleanup (#1194)Laurent Mazare2023-10-271-17/+3
| | | | | * Add some missing backtraces. * Small cleanup.
* Bump the version to 0.3.0. (#1014)Laurent Mazare2023-10-011-3/+3
| | | | | * Bump the version to 0.3.0. * Changelog update.
* fix firstToken, minor ui changes (#971)Radamés Ajna2023-09-272-100/+101
|
* fix rep penalty min value (#963)Radamés Ajna2023-09-261-1/+1
|
* Bump the crate versions to v0.2.3. (#886)Laurent Mazare2023-09-181-3/+3
| | | | | * Bump the crate version. * Also update the python bindings.
* minor UI fixes (#856)Radamés Ajna2023-09-151-3/+9
| | | | | | | * fixes * remove listener * remove event listener
* Implement top_p / nucleus sampling (#819)Juarez Bochi2023-09-124-12/+57
| | | | | | | | | | | | | * Implement top_p / nucleus sampling * Update changelog * rustfmt * Add tests * Fix clippy warning * Fix another clippy error
* Bump the crate version + update the changelog. (#822)Laurent Mazare2023-09-121-3/+3
|
* force model cache (#751)Radamés Ajna2023-09-062-8/+20
|
* Minor WASM UI improvements (#748)Radamés Ajna2023-09-052-14/+36
| | | | | | | * add stats * random seed btn * minor ui improvoments
* Fix clippy lint. (#736)Laurent Mazare2023-09-041-2/+2
|
* Llama2c WASM UI improvements (#732)Radamés Ajna2023-09-046-2/+464
| | | | | | | | | | | * pass seed, expose model seq_len * wip new llama2.c ui * final new UI example * small coppy * copy
* Avoid some redundant clone. (#731)Laurent Mazare2023-09-041-1/+1
|
* Add a repeat penality to the llama2-c command line example. (#713)Laurent Mazare2023-09-011-1/+1
| | | | | * Add a repeat penality to the llama2-c command line example. * Another fix attempt.
* Handle the empty sequence case properly. (#712)Laurent Mazare2023-09-011-1/+1
| | | | | * Handle the empty sequence case properly. * Proper fix.
* Add a repeat penalty to the llama2.c wasm example. (#709)Laurent Mazare2023-09-013-39/+26
|
* Llama2.c wasm module. (#686)Laurent Mazare2023-08-313-7/+90
|
* Add some documentation. (#673)Laurent Mazare2023-08-301-2/+2
| | | | | * Add some documentation. * Bump the crate version.
* Bump the crate version + update CHANGELOG. (#628)Laurent Mazare2023-08-271-2/+2
|
* Add some group parameter to convolutions. (#566)Laurent Mazare2023-08-231-2/+2
| | | | | | | | | | | | | * Add some group parameter to convolutions. * Avoid some unnecessary groups checks. * Move the tensor convolution bits. * Properh handling of groups. * Bump the crate version. * And add a changelog.
* Bump the crates version to 0.1.2. (#522)Laurent Mazare2023-08-201-2/+2
|
* Add a simple Module trait and implement it for the various nn layers (#500)Laurent Mazare2023-08-181-1/+1
| | | | | | | * Start adding the module trait. * Use the module trait. * Implement module for qmatmul.
* Add an abstract type for RmsNorm. (#499)Laurent Mazare2023-08-181-6/+6
|
* Layer norm tweaks (#482)Laurent Mazare2023-08-171-35/+9
| | | | | | | * Add some options to make layer-norm more configurable. * Add the rms-norm variant. * Replace the RmsNorm with the shared bits.
* Rename vec-dot to vec-ops. (#449)Laurent Mazare2023-08-151-2/+2
| | | | | | | * Rename vec-dot to vec-ops. * Also bump the crate version. * Add a currently empty readme.
* Bugfix for the llama2 wasm example. (#310)Laurent Mazare2023-08-022-9/+37
| | | | | | | | | * Clean-up the llama2.c wasm example. * Use a proper tokenizer. * Add a prompt. * Bugfix for the llama2 wasm example.
* Wasm llama2 tweaks (#309)Laurent Mazare2023-08-026-52/+14
| | | | | * Clean-up the llama2.c wasm example. * Use a proper tokenizer.
* Update the repo location. (#305)Laurent Mazare2023-08-022-10/+8
|
* Add version numbers for all the candle crates (#303)Laurent Mazare2023-08-021-2/+2
| | | | | * Switch to candle-gemm for the time being. * Add the missing versions.
* Rename the candle crate to candle-core (#301)Laurent Mazare2023-08-021-1/+1
| | | | | * Rename to candle-core. * More candle-core renaming.
* Display the temperature being used for text generation. (#278)Laurent Mazare2023-07-301-4/+8
|
* Use u8 tensors for masks. (#273)Laurent Mazare2023-07-291-2/+1
|
* Softmax numerical stability. (#267)Laurent Mazare2023-07-282-3/+3
| | | | | * Softmax numerical stability. * Fix the flash-attn test.
* Updated.Nicolas Patry2023-07-261-1/+1
|
* Simple QOL.Nicolas Patry2023-07-261-1/+12
| | | | | | | - Add ms/token on llama2.c (15ms/token on my personal machine) - Hide `Run` buttons while models are not ready - Add dummy `progress` while weights are downloading (I briefly looked at putting a real progressbar.. and nothing easy enough came up.)
* Add number of tokens.Nicolas Patry2023-07-261-2/+12
|
* Polish the llama2 wasm ui. (#232)Laurent Mazare2023-07-246-8/+34
| | | | | * Polish the llama2 wasm ui. * readme update.
* Re-organize the wasm examples (#231)Laurent Mazare2023-07-248-0/+968
* Move the whisper example. * More renaming. * Add llama2 as a new wasm example. * Live generation. * More of the llama wasm example. * Formatting.