Douglas Hanley 80ea089d77 llama : allow pooled embeddings on any model (#7477) ...

* create append_pooling operation; allow to specify attention_type; add last token pooling; update examples

* find result_norm/result_embd tensors properly; update output allocation logic

* only use embd output for pooling_type NONE

* get rid of old causal_attn accessor

* take out attention_type; add in llama_set_embeddings

* bypass logits when doing non-NONE pooling

2024-06-21 08:38:22 +03:00

..

base64.hpp

…

build-info.cpp.in

…

CMakeLists.txt

cmake : fix BUILD_SHARED_LIBS=ON build (#7784)

2024-06-07 15:15:07 +03:00

common.cpp

llama : allow pooled embeddings on any model (#7477)

2024-06-21 08:38:22 +03:00

common.h

chore: clean useless beam search param (#7985)

2024-06-18 10:11:40 +03:00

console.cpp

…

console.h

…

grammar-parser.cpp

Added support for . (any character) token in grammar engine. (#6467)

2024-06-06 06:08:52 -07:00

grammar-parser.h

…

json-schema-to-grammar.cpp

json: refine constraint for whitespace to avoid runaways yet allow pretty print (#7866)

2024-06-11 02:22:57 +01:00

json-schema-to-grammar.h

JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

2024-05-08 21:53:08 +02:00

json.hpp

json-schema-to-grammar improvements (+ added to server) (#5978)

2024-03-21 11:50:43 +00:00

log.h

Add support for properly optimized Windows ARM64 builds with LLVM and MSVC (#7191)

2024-05-16 12:47:36 +10:00

ngram-cache.cpp

Fixed lookup compilation issues on Windows (#6273)

2024-03-24 14:21:17 +01:00

ngram-cache.h

lookup: complement data from context with general text statistics (#5479)

2024-03-23 01:24:36 +01:00

sampling.cpp

common : normalize naming style (#7462)

2024-05-22 20:04:20 +03:00

sampling.h

common : normalize naming style (#7462)

2024-05-22 20:04:20 +03:00

stb_image.h

…

train.cpp

train : change default FA argument (#7528)

2024-05-25 15:22:35 +03:00

train.h

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00