Douglas Hanley 03bf161eb6 llama : support batched embeddings (#5466) ...

* batched embedding: pool outputs by sequence id. updated embedding example

* bring back non-causal attention

* embd : minor improvements

* llama : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2024-02-13 14:06:58 +02:00

..

baby-llama

…

batched

examples : add passkey test (#3856)

2024-01-08 11:14:04 +02:00

batched-bench

llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)

2024-01-31 17:30:17 +02:00

batched.swift

…

beam-search

…

benchmark

2-bit quantizations (#4897)

2024-01-14 09:45:56 +02:00

convert-llama2c-to-ggml

…

embedding

llama : support batched embeddings (#5466)

2024-02-13 14:06:58 +02:00

export-lora

sync : ggml (#5452)

2024-02-12 09:16:06 +02:00

finetune

sync : ggml (#5452)

2024-02-12 09:16:06 +02:00

gguf

…

imatrix

Adding some imatrix tools (#5302)

2024-02-04 10:39:58 +02:00

infill

Remove unused data and add fixes (#5154)

2024-01-27 15:25:55 +01:00

jeopardy

…

llama-bench

refactor : switch to emplace_back to avoid extra object (#5291)

2024-02-03 13:23:37 +02:00

llama.android

android : use release cmake build type by default (#5123)

2024-01-25 19:05:51 +02:00

llama.swiftui

llama.swiftui : update models layout (#4826)

2024-01-12 14:48:00 +02:00

llava

llava : remove prog parameter from ArgumentParser (#5457)

2024-02-12 10:38:44 +02:00

lookahead

…

lookup

lookup: add print for drafting performance (#5450)

2024-02-11 12:44:51 +01:00

main

main : ctrl+C print timing in non-interactive mode (#3873)

2024-02-11 15:35:50 +02:00

main-cmake-pkg

…

parallel

…

passkey

examples : add passkey test (#3856)

2024-01-08 11:14:04 +02:00

perplexity

refactor : switch to emplace_back to avoid extra object (#5291)

2024-02-03 13:23:37 +02:00

quantize

refactor : switch to emplace_back to avoid extra object (#5291)

2024-02-03 13:23:37 +02:00

quantize-stats

refactor : switch to emplace_back to avoid extra object (#5291)

2024-02-03 13:23:37 +02:00

save-load-state

llama : minimize size used for state save/load (#4820)

2024-01-13 18:29:43 +02:00

server

server : allow to specify tokens as strings in logit_bias (#5003)

2024-02-11 15:38:14 +02:00

simple

…

speculative

speculative : threading options (#4959)

2024-01-16 13:04:32 +02:00

sycl

[SYCL] update guide of SYCL backend (#5254)

2024-02-02 15:53:27 +08:00

tokenize

…

train-text-from-scratch

sync : ggml (#5452)

2024-02-12 09:16:06 +02:00

alpaca.sh

…

base-translate.sh

examples : improve base-translate.sh script (#4783)

2024-01-06 11:40:24 +02:00

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

ggml : add unified SYCL backend for Intel GPUs (#2690)

2024-01-28 17:56:23 +02:00

gpt4all.sh

…

json-schema-to-grammar.py

…

llama2-13b.sh

…

llama2.sh

…

llama.vim

llama.vim : added api key support (#5090)

2024-01-23 08:51:27 +02:00

llm.vim

…

make-ggml.py

…

Miku.sh

…

pydantic_models_to_grammar.py

examples : make pydantic scripts pass mypy and support py3.8 (#5099)

2024-01-25 14:51:24 -05:00

pydantic-models-to-grammar-examples.py

examples : make pydantic scripts pass mypy and support py3.8 (#5099)

2024-01-25 14:51:24 -05:00

reason-act.sh

…

server-llama2-13B.sh

…