| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| Support boxed variants of chat and completion models (#329)
* Support boxed variants of chat and completion models
* Document boxed chat methods | 1 年前 |
| Support boxed variants of chat and completion models (#329)
* Support boxed variants of chat and completion models
* Document boxed chat methods | 1 年前 |
| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| Generalize task chunker and add more logging (#423)
* generalize task chunker and add more logging
* Fix misleading variable name in chunking example (#429)
* Initial plan
* Fix variable name: rename hypothetical to summarizer in chunking.rs example
Co-authored-by: ealmloff <66571940+ealmloff@users.noreply.github.com>
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ealmloff <66571940+ealmloff@users.noreply.github.com>
* fix formatting
---------
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> | 2 个月前 |
| Add support for Qwen 2.5 Vision (#382)
* implement qwen vision embed and patch merger
* implement qwen vision block
* calculate the rope index of images and videos
* add get_window_index
* fix get window index
* unwrap less
* Create media source api
* integrate the new media support into the language model trait
* Create QwenVisionTransformer
* implement QwenVisionTransformer::forward
* fix formatting
* fix loading qwen 2.5 vl
* fix rot_pos_emb
* add image preprocessing utilities
* fix vision rope
* fix mask
* Fix feed forward
* qwen vision forward working
* unwrap less
* clean up
* create tensor tools cli
* fix cli
* fix fuse tokenizer
* move parse into its own module
* Use llama.cpp compatible tensor names
* add preset
* load qwen vision metadata from the gguf file
* fix loading the vision encoder
* test process image
* forward eps and add more tests
* fix image processing
* implement image chat templating
* full pipeline running
* fix formatting
* use 3d rope index
* fix dimension_sections decoding
* qwen vl rope working
* remove logs
* fix rope tests
* fix rope size
* fix rope index to tensor conversion
* Fix rope updates
* normalize image input
* match image resize behavior
* fix fullatt_block calculation
* vision model works
* remove logs
* add more qwen vl presets
* fix some clippy lints
* fix clippy
* Fix ToChatMessage
* expose image processing hints
* remove unwraps
* fix unwraps in tests
* fix more examples | 11 个月前 |
| Add support for Qwen 2.5 Vision (#382)
* implement qwen vision embed and patch merger
* implement qwen vision block
* calculate the rope index of images and videos
* add get_window_index
* fix get window index
* unwrap less
* Create media source api
* integrate the new media support into the language model trait
* Create QwenVisionTransformer
* implement QwenVisionTransformer::forward
* fix formatting
* fix loading qwen 2.5 vl
* fix rot_pos_emb
* add image preprocessing utilities
* fix vision rope
* fix mask
* Fix feed forward
* qwen vision forward working
* unwrap less
* clean up
* create tensor tools cli
* fix cli
* fix fuse tokenizer
* move parse into its own module
* Use llama.cpp compatible tensor names
* add preset
* load qwen vision metadata from the gguf file
* fix loading the vision encoder
* test process image
* forward eps and add more tests
* fix image processing
* implement image chat templating
* full pipeline running
* fix formatting
* use 3d rope index
* fix dimension_sections decoding
* qwen vl rope working
* remove logs
* fix rope tests
* fix rope size
* fix rope index to tensor conversion
* Fix rope updates
* normalize image input
* match image resize behavior
* fix fullatt_block calculation
* vision model works
* remove logs
* add more qwen vl presets
* fix some clippy lints
* fix clippy
* Fix ToChatMessage
* expose image processing hints
* remove unwraps
* fix unwraps in tests
* fix more examples | 11 个月前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Add support for Qwen 2.5 Vision (#382)
* implement qwen vision embed and patch merger
* implement qwen vision block
* calculate the rope index of images and videos
* add get_window_index
* fix get window index
* unwrap less
* Create media source api
* integrate the new media support into the language model trait
* Create QwenVisionTransformer
* implement QwenVisionTransformer::forward
* fix formatting
* fix loading qwen 2.5 vl
* fix rot_pos_emb
* add image preprocessing utilities
* fix vision rope
* fix mask
* Fix feed forward
* qwen vision forward working
* unwrap less
* clean up
* create tensor tools cli
* fix cli
* fix fuse tokenizer
* move parse into its own module
* Use llama.cpp compatible tensor names
* add preset
* load qwen vision metadata from the gguf file
* fix loading the vision encoder
* test process image
* forward eps and add more tests
* fix image processing
* implement image chat templating
* full pipeline running
* fix formatting
* use 3d rope index
* fix dimension_sections decoding
* qwen vl rope working
* remove logs
* fix rope tests
* fix rope size
* fix rope index to tensor conversion
* Fix rope updates
* normalize image input
* match image resize behavior
* fix fullatt_block calculation
* vision model works
* remove logs
* add more qwen vl presets
* fix some clippy lints
* fix clippy
* Fix ToChatMessage
* expose image processing hints
* remove unwraps
* fix unwraps in tests
* fix more examples | 11 个月前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Remove anyhow (#313)
* Remove anyhow from llama source and cache
Partial fix for: https://github.com/floneum/floneum/issues/186
* remove anyhow where possible in kalosm-* libraries
* Update examples with breaking changes
* fix formatting
* Fix clippy
* Fix floneum build
---------
Co-authored-by: Josh McKinney <joshka@users.noreply.github.com> | 1 年前 |
| Use a chat model in the custom llama example
| 1 年前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Add support for Gemma3 and codestral (#378)
* add gemma 3 support
* fix gemma example
* add a warning about system prompts
* fix codestral chat template
* fix md_get
* remove extra file
* fix formatting
* remove commented out code
* fix kalosm llama example | 1 年前 |
| Remove anyhow (#313)
* Remove anyhow from llama source and cache
Partial fix for: https://github.com/floneum/floneum/issues/186
* remove anyhow where possible in kalosm-* libraries
* Update examples with breaking changes
* fix formatting
* Fix clippy
* Fix floneum build
---------
Co-authored-by: Josh McKinney <joshka@users.noreply.github.com> | 1 年前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Add support for Qwen 2.5 Vision (#382)
* implement qwen vision embed and patch merger
* implement qwen vision block
* calculate the rope index of images and videos
* add get_window_index
* fix get window index
* unwrap less
* Create media source api
* integrate the new media support into the language model trait
* Create QwenVisionTransformer
* implement QwenVisionTransformer::forward
* fix formatting
* fix loading qwen 2.5 vl
* fix rot_pos_emb
* add image preprocessing utilities
* fix vision rope
* fix mask
* Fix feed forward
* qwen vision forward working
* unwrap less
* clean up
* create tensor tools cli
* fix cli
* fix fuse tokenizer
* move parse into its own module
* Use llama.cpp compatible tensor names
* add preset
* load qwen vision metadata from the gguf file
* fix loading the vision encoder
* test process image
* forward eps and add more tests
* fix image processing
* implement image chat templating
* full pipeline running
* fix formatting
* use 3d rope index
* fix dimension_sections decoding
* qwen vl rope working
* remove logs
* fix rope tests
* fix rope size
* fix rope index to tensor conversion
* Fix rope updates
* normalize image input
* match image resize behavior
* fix fullatt_block calculation
* vision model works
* remove logs
* add more qwen vl presets
* fix some clippy lints
* fix clippy
* Fix ToChatMessage
* expose image processing hints
* remove unwraps
* fix unwraps in tests
* fix more examples | 11 个月前 |
| feat(SurrealDB Integration): Hybrid Search Support (#415)
* Added hybrid search setup
* Refactored for more testable code
* Added unit test for score normalization function
* Added unit tests for distance to similarity calculation
* Added tests for weighted score calculation
* Added tests for rrf
* Added tests for results merging
* Finished units, with rrf and weighted pipeline test
* Refactored for builder pattern
* Completed hybrid search api
* Created integration tests
* Updated surrealdb version and queries
* Added conditional materialized fild
* Fixed query definitions for both semantic and keyword
* Fixed normalization issues with weighted search
* Fixed ranking issues in rrf
* Finalized queries for materialized fields and index rebuilding
* Created default value for rrf
* Completed integration tests
* Simplified hybrid search with default field
* Removed unused code and added comments
* Making sure search parameters are clamped and adjusted
* Completed example
* tighten test assertions, make more functions private to avoid semvar breaking changes in the future and clean up the error type
* Returning original example back
* Clippy fixes
* fixed doc tests
* fixed fmt checks
---------
Co-authored-by: Evan Almloff <evanalmloff@gmail.com> | 4 个月前 |
| reorganize packages
| 2 年前 |
| Make kalosm-sound usable in wasm (#407)
* make kalosm-sound usable in wasm
* smaller default tiny en model
* fix cargo check
* forward input features
* fix examples | 6 个月前 |
| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Generalize task chunker and add more logging (#423)
* generalize task chunker and add more logging
* Fix misleading variable name in chunking example (#429)
* Initial plan
* Fix variable name: rename hypothetical to summarizer in chunking.rs example
Co-authored-by: ealmloff <66571940+ealmloff@users.noreply.github.com>
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ealmloff <66571940+ealmloff@users.noreply.github.com>
* fix formatting
---------
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> | 2 个月前 |
| reorganize packages
| 2 年前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| add phi 4 support (#323)
| 1 年前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Add support for Qwen 2.5 Vision (#382)
* implement qwen vision embed and patch merger
* implement qwen vision block
* calculate the rope index of images and videos
* add get_window_index
* fix get window index
* unwrap less
* Create media source api
* integrate the new media support into the language model trait
* Create QwenVisionTransformer
* implement QwenVisionTransformer::forward
* fix formatting
* fix loading qwen 2.5 vl
* fix rot_pos_emb
* add image preprocessing utilities
* fix vision rope
* fix mask
* Fix feed forward
* qwen vision forward working
* unwrap less
* clean up
* create tensor tools cli
* fix cli
* fix fuse tokenizer
* move parse into its own module
* Use llama.cpp compatible tensor names
* add preset
* load qwen vision metadata from the gguf file
* fix loading the vision encoder
* test process image
* forward eps and add more tests
* fix image processing
* implement image chat templating
* full pipeline running
* fix formatting
* use 3d rope index
* fix dimension_sections decoding
* qwen vl rope working
* remove logs
* fix rope tests
* fix rope size
* fix rope index to tensor conversion
* Fix rope updates
* normalize image input
* match image resize behavior
* fix fullatt_block calculation
* vision model works
* remove logs
* add more qwen vl presets
* fix some clippy lints
* fix clippy
* Fix ToChatMessage
* expose image processing hints
* remove unwraps
* fix unwraps in tests
* fix more examples | 11 个月前 |
| Remove anyhow (#313)
* Remove anyhow from llama source and cache
Partial fix for: https://github.com/floneum/floneum/issues/186
* remove anyhow where possible in kalosm-* libraries
* Update examples with breaking changes
* fix formatting
* Fix clippy
* Fix floneum build
---------
Co-authored-by: Josh McKinney <joshka@users.noreply.github.com> | 1 年前 |
| Remote chat, remote structured generation models, and single file gguf chat model loading (#319)
* add chat template support and remove the VectorSpace trait
* move sampling and chat templates to kalosm llama
* update kalosm-llama unstructured generation to the new interface
* restore structured generation module
* Restore llama implementation of structured generation
* clean up kalosm-llama clippy lints
* restore llama chat and structured chat implementation
* improve infer chat example
* add support for remote chat models
* support constraints for openai remote models
* load the tokenizer from the gguf file if a huggingface tokenizer is not present
* Fix tokenizer conversion
* restore chat struct
* Fix chat implementation with llama
* remove tokio from language model
* Create chat and text completion extension traits
* add task helper to the chat extension trait
* update kalosm-language to new task interface
* make llama callable
* add with_constraints method to task
* fix task example
* update examples to new chat and task api
* set tools to none to fix llama chat template
* Add helpers for the default parser for a specific type and model combo
* simplify constrained rust type example
* restore prompt annealing
* fix structured example
* document text completion model
* document new chat api
* update task documentation
* Fix tokenizer gguf
* fix custom llama source example
* fix remaining tests
* add logging to remote examples
* Clippy fixes
* More clippy fixes
* use function call in docs more constantly
* fix remaining doc tests | 1 年前 |
| Add a separate method for embedding queries
| 1 年前 |
| Fix clippy lints (#381)
| 11 个月前 |
| Add support for Qwen 2.5 Vision (#382)
* implement qwen vision embed and patch merger
* implement qwen vision block
* calculate the rope index of images and videos
* add get_window_index
* fix get window index
* unwrap less
* Create media source api
* integrate the new media support into the language model trait
* Create QwenVisionTransformer
* implement QwenVisionTransformer::forward
* fix formatting
* fix loading qwen 2.5 vl
* fix rot_pos_emb
* add image preprocessing utilities
* fix vision rope
* fix mask
* Fix feed forward
* qwen vision forward working
* unwrap less
* clean up
* create tensor tools cli
* fix cli
* fix fuse tokenizer
* move parse into its own module
* Use llama.cpp compatible tensor names
* add preset
* load qwen vision metadata from the gguf file
* fix loading the vision encoder
* test process image
* forward eps and add more tests
* fix image processing
* implement image chat templating
* full pipeline running
* fix formatting
* use 3d rope index
* fix dimension_sections decoding
* qwen vl rope working
* remove logs
* fix rope tests
* fix rope size
* fix rope index to tensor conversion
* Fix rope updates
* normalize image input
* match image resize behavior
* fix fullatt_block calculation
* vision model works
* remove logs
* add more qwen vl presets
* fix some clippy lints
* fix clippy
* Fix ToChatMessage
* expose image processing hints
* remove unwraps
* fix unwraps in tests
* fix more examples | 11 个月前 |
| Add support for Qwen 2.5 Vision (#382)
* implement qwen vision embed and patch merger
* implement qwen vision block
* calculate the rope index of images and videos
* add get_window_index
* fix get window index
* unwrap less
* Create media source api
* integrate the new media support into the language model trait
* Create QwenVisionTransformer
* implement QwenVisionTransformer::forward
* fix formatting
* fix loading qwen 2.5 vl
* fix rot_pos_emb
* add image preprocessing utilities
* fix vision rope
* fix mask
* Fix feed forward
* qwen vision forward working
* unwrap less
* clean up
* create tensor tools cli
* fix cli
* fix fuse tokenizer
* move parse into its own module
* Use llama.cpp compatible tensor names
* add preset
* load qwen vision metadata from the gguf file
* fix loading the vision encoder
* test process image
* forward eps and add more tests
* fix image processing
* implement image chat templating
* full pipeline running
* fix formatting
* use 3d rope index
* fix dimension_sections decoding
* qwen vl rope working
* remove logs
* fix rope tests
* fix rope size
* fix rope index to tensor conversion
* Fix rope updates
* normalize image input
* match image resize behavior
* fix fullatt_block calculation
* vision model works
* remove logs
* add more qwen vl presets
* fix some clippy lints
* fix clippy
* Fix ToChatMessage
* expose image processing hints
* remove unwraps
* fix unwraps in tests
* fix more examples | 11 个月前 |
| Remove anyhow (#313)
* Remove anyhow from llama source and cache
Partial fix for: https://github.com/floneum/floneum/issues/186
* remove anyhow where possible in kalosm-* libraries
* Update examples with breaking changes
* fix formatting
* Fix clippy
* Fix floneum build
---------
Co-authored-by: Josh McKinney <joshka@users.noreply.github.com> | 1 年前 |
| Add support for Qwen 2.5 Vision (#382)
* implement qwen vision embed and patch merger
* implement qwen vision block
* calculate the rope index of images and videos
* add get_window_index
* fix get window index
* unwrap less
* Create media source api
* integrate the new media support into the language model trait
* Create QwenVisionTransformer
* implement QwenVisionTransformer::forward
* fix formatting
* fix loading qwen 2.5 vl
* fix rot_pos_emb
* add image preprocessing utilities
* fix vision rope
* fix mask
* Fix feed forward
* qwen vision forward working
* unwrap less
* clean up
* create tensor tools cli
* fix cli
* fix fuse tokenizer
* move parse into its own module
* Use llama.cpp compatible tensor names
* add preset
* load qwen vision metadata from the gguf file
* fix loading the vision encoder
* test process image
* forward eps and add more tests
* fix image processing
* implement image chat templating
* full pipeline running
* fix formatting
* use 3d rope index
* fix dimension_sections decoding
* qwen vl rope working
* remove logs
* fix rope tests
* fix rope size
* fix rope index to tensor conversion
* Fix rope updates
* normalize image input
* match image resize behavior
* fix fullatt_block calculation
* vision model works
* remove logs
* add more qwen vl presets
* fix some clippy lints
* fix clippy
* Fix ToChatMessage
* expose image processing hints
* remove unwraps
* fix unwraps in tests
* fix more examples | 11 个月前 |
