Georgi Gerganov faf69d4237 llama : sanitize invalid tokens (#9357) ...

* common : do not add null tokens during warmup

ggml-ci

* llama : check that the input tokens are valid

ggml-ci

* tests : fix batch size of bert model

ggml-ci

2024-09-08 00:33:13 +03:00

..

baby-llama

Threadpool: take 2 (#8672)

2024-08-30 01:20:53 +02:00

batched

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

batched-bench

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

batched.swift

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

benchmark

Threadpool: take 2 (#8672)

2024-08-30 01:20:53 +02:00

convert-llama2c-to-ggml

…

cvector-generator

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

deprecation-warning

examples : remove finetune and train-text-from-scratch (#8669)

2024-07-25 10:39:04 +02:00

embedding

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

eval-callback

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

export-lora

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

gbnf-validator

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

gen-docs

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

gguf

…

gguf-hash

…

gguf-split

…

gritlm

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

imatrix

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

infill

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

jeopardy

…

llama-bench

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

llama.android

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

llama.swiftui

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

llava

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

lookahead

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

lookup

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

main

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

main-cmake-pkg

…

parallel

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

passkey

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

perplexity

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

quantize

ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)

2024-09-05 21:48:47 -04:00

quantize-stats

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

retrieval

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

rpc

Merge commit from fork

2024-08-09 23:03:21 +03:00

save-load-state

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

server

llama : sanitize invalid tokens (#9357)

2024-09-08 00:33:13 +03:00

simple

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

speculative

common : refactor arg parser (#9308)

2024-09-07 20:43:51 +02:00

sycl

[SYCL] Updated SYCL device filtering (#8901)

2024-08-07 11:25:36 +01:00

tokenize

common : remove duplicate function llama_should_add_bos_token (#8778)

2024-08-15 10:23:23 +03:00

base-translate.sh

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

examples : remove finetune and train-text-from-scratch (#8669)

2024-07-25 10:39:04 +02:00

convert_legacy_llama.py

…

json_schema_pydantic_example.py

…

json_schema_to_grammar.py

…

llama.vim

…

llm.vim

…

Miku.sh

…

pydantic_models_to_grammar_examples.py

examples : Rewrite pydantic_models_to_grammar_examples.py (#8493)

2024-07-20 22:09:17 -04:00

pydantic_models_to_grammar.py

…

reason-act.sh

…

regex_to_grammar.py

…

server_embd.py

…

server-llama2-13B.sh

…

ts-type-to-grammar.sh

…