mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Wizard Mega, Ziya, KoAlpaca, OpenBuddy, Chinese-Vicuna, Vigogne, Bactrian, H2O support, fix Baize (#2159)

Browse source
This commit is contained in:
Carl Kenner 2023-05-20 00:12:41 +09:30 • committed by GitHub
parent c98d6ad27f
commit c86231377b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
16 changed files with 127 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

59
models/config.yaml
View file

@ -1,9 +1,17 @@
.*(llama|alpac|vicuna|guanaco|koala|llava|wizardlm|metharme|pygmalion-7b):
.*(llama|alpac|vicuna|guanaco|koala|llava|wizardlm|metharme|pygmalion-7b|wizard-mega|openbuddy|vigogne|h2ogpt-research|manticore):
model_type: 'llama'
.*(opt-|opt_|opt1|opt3|optfor|galactica|galpaca|pygmalion-350m):
model_type: 'opt'
.*(gpt-j|gptj|gpt4all-j|malion-6b|pygway|pygmalion-6b):
.*(gpt-j|gptj|gpt4all-j|malion-6b|pygway|pygmalion-6b|dolly-v1):
model_type: 'gptj'
.*(gpt-neox|koalpaca-polyglot|polyglot.*koalpaca|polyglot-ko|polyglot_ko|pythia|stablelm|incite|dolly-v2|polycoder|h2ogpt-oig|h2ogpt-oasst1|h2ogpt-gm):
model_type: 'gpt_neox'
.*llama:
model_type: 'llama'
.*bloom:
model_type: 'bloom'
llama-65b-gptq-3bit:
groupsize: 'None'
.*(4bit|int4):
wbits: 4
.*(3bit|int3):
@ -28,11 +36,15 @@
groupsize: 128
.*(gr1024|1024g|groupsize1024):
groupsize: 1024
.*(oasst|stablelm-7b-sft-v7-epoch-3):
.*(oasst|openassistant-|stablelm-7b-sft-v7-epoch-3):
mode: 'instruct'
instruction_template: 'Open Assistant'
skip_special_tokens: false
(?!.*v0)(?!.*1.1)(?!.*1_1)(?!.*stable).*vicuna:
(?!.*galactica)(?!.*reward).*openassistant:
mode: 'instruct'
instruction_template: 'Open Assistant'
skip_special_tokens: false
(?!.*v0)(?!.*1.1)(?!.*1_1)(?!.*stable)(?!.*chinese).*vicuna:
mode: 'instruct'
instruction_template: 'Vicuna-v0'
.*vicuna.*v0:
@ -47,6 +59,12 @@
.*stable.*vicuna:
mode: 'instruct'
instruction_template: 'StableVicuna'
(?!.*chat).*chinese-vicuna:
mode: 'instruct'
instruction_template: 'Alpaca'
.*chinese-vicuna.*chat:
mode: 'instruct'
instruction_template: 'Chinese-Vicuna-Chat'
.*alpaca:
mode: 'instruct'
instruction_template: 'Alpaca'
@ -126,3 +144,36 @@
.*incite.*instruct:
mode: 'instruct'
instruction_template: 'INCITE-Instruct'
.*wizard.*mega:
mode: 'instruct'
instruction_template: 'Wizard-Mega'
.*ziya-:
mode: 'instruct'
instruction_template: 'Ziya'
.*koalpaca:
mode: 'instruct'
instruction_template: 'KoAlpaca'
.*openbuddy:
mode: 'instruct'
instruction_template: 'OpenBuddy'
(?!.*chat).*vigogne:
mode: 'instruct'
instruction_template: 'Vigogne-Instruct'
.*vigogne.*chat:
mode: 'instruct'
instruction_template: 'Vigogne-Chat'
.*(llama-deus|supercot|llama-natural-instructions|open-llama-0.3t-7b-instruct-dolly-hhrlhf|open-llama-0.3t-7b-open-instruct):
mode: 'instruct'
instruction_template: 'Alpaca'
.*bactrian:
mode: 'instruct'
instruction_template: 'Bactrian'
.*(h2ogpt-oig-|h2ogpt-oasst1-|h2ogpt-research-oasst1-):
mode: 'instruct'
instruction_template: 'H2O-human_bot'
.*h2ogpt-gm-:
mode: 'instruct'
instruction_template: 'H2O-prompt_answer'
.*manticore:
mode: 'instruct'
instruction_template: 'Manticore Chat'