( ! ) Deprecated: mysql_pconnect(): The mysql extension is deprecated and will be removed in the future: use mysqli or PDO instead in /home/users/2/daiskip/web/sites_applog/userlib/class/adodb/drivers/adodb-mysql.inc.php on line 381
Call Stack
#TimeMemoryFunctionLocation
10.0004274768{main}( ).../app.php:0
20.00821559808MyDB->MyDB( ).../app.php:4
30.00941828128ADOConnection->PConnect( ).../MyDB.php:42
40.00941828360ADODB_mysql->_pconnect( ).../adodb.inc.php:484
50.00941828408mysql_pconnect ( ).../adodb-mysql.inc.php:381
( ! ) Deprecated: mysql_pconnect(): The mysql extension is deprecated and will be removed in the future: use mysqli or PDO instead in /home/users/2/daiskip/web/sites_applog/userlib/class/adodb/drivers/adodb-mysql.inc.php on line 381
Call Stack
#TimeMemoryFunctionLocation
10.0004274768{main}( ).../app.php:0
20.01081839224getInstallCount( ).../app.php:17
30.01081839400MyDB->MyDB( ).../common.php:109
40.01081840320ADOConnection->PConnect( ).../MyDB.php:42
50.01081840368ADODB_mysql->_pconnect( ).../adodb.inc.php:484
60.01081840416mysql_pconnect ( ).../adodb-mysql.inc.php:381
( ! ) Warning: Cannot modify header information - headers already sent by (output started at /home/users/2/daiskip/web/sites_applog/userlib/class/adodb/drivers/adodb-mysql.inc.php:381) in /home/users/2/daiskip/web/sites_applog/app.php on line 76
Call Stack
#TimeMemoryFunctionLocation
10.0004274768{main}( ).../app.php:0
20.26891890440header ( ).../app.php:76
 LLM Farm

LLM Farm

開発ツール
Artem Savkin
☆

LLMFarm is an iOS and MacOS app to work with large language models (LLM). It allows you to load different LLMs with certain parameters.

# Features
* Various inferences
* Various sampling methods
* Metal
* Model setting templates
* LoRA adapters support
* LoRA FineTune and Export

# Inferences
* LLaMA
* GPTNeoX
* Replit
* GPT2 + Cerebras
* Starcoder(Santacoder)
* RWKV (20B tokenizer)
* Falcon
* MPT
* Bloom
* StableLM-3b-4e1t
* Qwen
* Gemma
* Phi
* Mamba
* Others

# Multimodal
* LLaVA 1.5 models
* Obsidian
* MobileVLM 1.7B/3B models

Note: For Falcon, Alpaca, GPT4All, Chinese LLaMA / Alpaca and Chinese LLaMA-2 / Alpaca-2, Vigogne (French), Vicuna, Koala, OpenBuddy (Multilingual), Pygmalion/Metharme, WizardLM, Baichuan 1 & 2 + derivations, Aquila 1 & 2, Mistral AI v0.1, Refact, Persimmon 8B, MPT, Bloom select llama inferece in model settings.

Sampling methods
* Temperature (temp, tok-k, top-p)
* Tail Free Sampling (TFS)
* Locally Typical Sampling
* Mirostat
* Greedy
* Grammar (dont work with GGJTv3)