3 people 1966eb2615 quantize : add '--keep-split' to quantize model into shards (#6688) ...

* Implement '--keep-split' to quantize model into several shards

* Add test script

* Update examples/quantize/quantize.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

* Split model correctly even if tensor id is out-of-order

* Update llama_model_quantize_params

* Fix preci failures

---------

Co-authored-by: z5269887 <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>

2024-04-25 13:29:35 +03:00

..

baby-llama

code : normalize enum names (#5697)

2024-02-25 12:09:09 +02:00

batched

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

batched-bench

bench : make n_batch and n_ubatch configurable in Batched bench (#6500)

2024-04-05 21:34:53 +03:00

batched.swift

llama : add option to render special/control tokens (#6807)

2024-04-21 18:36:45 +03:00

beam-search

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

benchmark

ggml : remove old quantization functions (#5942)

2024-03-09 15:53:59 +02:00

convert-llama2c-to-ggml

llama2c : open file as binary (#6332)

2024-03-27 09:16:02 +02:00

embedding

BERT tokenizer fixes (#6498)

2024-04-09 13:44:08 -04:00

eval-callback

model: support arch DbrxForCausalLM (#6515)

2024-04-13 11:33:52 +02:00

export-lora

ci : add an option to fail on compile warning (#3952)

2024-02-17 23:03:14 +02:00

finetune

code : normalize enum names (#5697)

2024-02-25 12:09:09 +02:00

gbnf-validator

grammars: 1.5x faster inference w/ complex grammars (vector reserves / reuses) (#6609)

2024-04-11 19:47:34 +01:00

gguf

gguf : add option to not check tensor data (#6582)

2024-04-10 21:16:48 +03:00

gguf-split

Fix --split-max-size (#6655)

2024-04-14 13:12:59 +02:00

gritlm

gritlm : add --outdir option to hf.sh script (#6699)

2024-04-16 09:34:06 +03:00

imatrix

ggml : group all experts in a single ggml_mul_mat_id (#6505)

2024-04-18 15:18:48 +02:00

infill

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

jeopardy

parallel : add option to load external prompt file (#3416)

2023-10-06 16:16:38 +03:00

llama-bench

ggml : add llamafile sgemm (#6414)

2024-04-16 21:55:30 +03:00

llama.android

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

llama.swiftui

llama : add option to render special/control tokens (#6807)

2024-04-21 18:36:45 +03:00

llava

llava : use logger in llava-cli (#6797)

2024-04-21 15:19:04 +03:00

lookahead

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

lookup

Server: fix seed for multiple slots (#6835)

2024-04-24 11:08:36 +02:00

main

Server: fix seed for multiple slots (#6835)

2024-04-24 11:08:36 +02:00

main-cmake-pkg

cuda : rename build flag to LLAMA_CUDA (#6299)

2024-03-26 01:16:01 +01:00

parallel

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

passkey

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

perplexity

perplexity : require positive --ctx-size arg (#6695)

2024-04-16 09:28:33 +03:00

quantize

quantize : add '--keep-split' to quantize model into shards (#6688)

2024-04-25 13:29:35 +03:00

quantize-stats

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

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

retrieval

examples : add "retrieval" (#6193)

2024-03-25 09:38:22 +02:00

save-load-state

llama : save and restore kv cache for single seq id (#6341)

2024-04-08 15:43:30 +03:00

server

server : do not apply Markdown formatting in code sections (#6850)

2024-04-24 13:54:24 +03:00

simple

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

speculative

llama : support Llama 3 HF conversion (#6745)

2024-04-21 14:50:41 +03:00

sycl

fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)

2024-04-14 10:42:29 +08:00

tokenize

BERT tokenizer fixes (#6498)

2024-04-09 13:44:08 -04:00

train-text-from-scratch

train : add general name (#6752)

2024-04-19 10:16:45 +03:00

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

llama : fix session saving/loading (#3400)

2023-10-03 21:04:01 +03:00

chat-vicuna.sh

…

chat.sh

main : log file (#2748)

2023-08-30 09:29:32 +03:00

CMakeLists.txt

eval-callback: Example how to use eval callback for debugging (#6576)

2024-04-11 14:51:07 +02:00

gpt4all.sh

…

json_schema_to_grammar.py

JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)

2024-04-12 19:43:38 +01:00

json-schema-pydantic-example.py

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

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

llama2-13b.sh

…

llama2.sh

…

llama.vim

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

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

llm.vim

llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)

2023-08-30 09:50:55 +03:00

make-ggml.py

make-ggml.py : compatibility with more models and GGUF (#3290)

2023-09-27 19:25:12 +03:00

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

…

regex-to-grammar.py

JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)

2024-04-12 19:43:38 +01:00

server-embd.py

server : refactor (#5882)

2024-03-07 11:41:53 +02:00

server-llama2-13B.sh

…

ts-type-to-grammar.sh

JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)

2024-04-12 19:43:38 +01:00