add orca model and change config.yaml

models/config.yaml

@@ -1,206 +1,279 @@
-.*(llama|alpac|vicuna|guanaco|koala|llava|wizardlm|metharme|pygmalion-7b|pygmalion-2|mythalion|wizard-mega|openbuddy|vigogne|h2ogpt-research|manticore):
+.*(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|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: 'gptneox'
+  model_type: 'gpt_neox'
+.*llama:
+  model_type: 'llama'
 .*bloom:
   model_type: 'bloom'
-.*gpt2:
-  model_type: 'gpt2'
-.*falcon:
-  model_type: 'falcon'
-.*mpt:
-  model_type: 'mpt'
-.*(starcoder|starchat):
-  model_type: 'starcoder'
-.*dolly-v2:
-  model_type: 'dollyv2'
-.*replit:
-  model_type: 'replit'
+llama-65b-gptq-3bit:
+  groupsize: 'None'
+.*(4bit|int4):
+  wbits: 4
+.*(3bit|int3):
+  wbits: 3
+.*(-2bit|_2bit|int2-):
+  wbits: 2
+.*(-1bit|_1bit|int1-):
+  wbits: 1
+.*(8bit|int8):
+  wbits: 8
+.*(-7bit|_7bit|int7-):
+  wbits: 7
+.*(-6bit|_6bit|int6-):
+  wbits: 6
+.*(-5bit|_5bit|int5-):
+  wbits: 5
+.*(-gr32-|-32g-|groupsize32|-32g$):
+  groupsize: 32
+.*(-gr64-|-64g-|groupsize64|-64g$):
+  groupsize: 64
+.*(gr128|128g|groupsize128):
+  groupsize: 128
+.*(gr1024|1024g|groupsize1024):
+  groupsize: 1024
 .*(oasst|openassistant-|stablelm-7b-sft-v7-epoch-3):
+  mode: 'instruct'
   instruction_template: 'Open Assistant'
   skip_special_tokens: false
 (?!.*galactica)(?!.*reward).*openassistant:
+  mode: 'instruct'
   instruction_template: 'Open Assistant'
   skip_special_tokens: false
-.*galactica:
-  skip_special_tokens: false
-.*dolly-v[0-9]-[0-9]*b:
-  instruction_template: 'Alpaca'
-  skip_special_tokens: false
-.*alpaca-native-4bit:
-  instruction_template: 'Alpaca'
-  custom_stopping_strings: '"### End"'
-.*llava:
-  instruction_template: 'LLaVA'
-  custom_stopping_strings: '"\n###"'
-.*llava.*1.5:
-  instruction_template: 'Vicuna-v1.1'
-.*wizard.*mega:
-  instruction_template: 'Wizard-Mega'
-  custom_stopping_strings: '"</s>"'
-.*starchat-beta:
-  instruction_template: 'Starchat-Beta'
-  custom_stopping_strings: '"<|end|>"'
 (?!.*v0)(?!.*1.1)(?!.*1_1)(?!.*stable)(?!.*chinese).*vicuna:
+  mode: 'instruct'
   instruction_template: 'Vicuna-v0'
 .*vicuna.*v0:
+  mode: 'instruct'
   instruction_template: 'Vicuna-v0'
 .*vicuna.*(1.1|1_1|1.3|1_3):
+  mode: 'instruct'
   instruction_template: 'Vicuna-v1.1'
-.*vicuna.*(1.5|1_5):
+.*wizard.*vicuna:
+  mode: 'instruct'
   instruction_template: 'Vicuna-v1.1'
 .*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'
+.*alpaca-native-4bit:
+  mode: 'instruct'
+  instruction_template: 'Alpaca'
+  wbits: 4
+  groupsize: 128
+.*galactica:
+  skip_special_tokens: false
+.*dolly-v[0-9]-[0-9]*b:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
+  skip_special_tokens: false
+  custom_stopping_strings: '"### End"'
 .*koala:
+  mode: 'instruct'
   instruction_template: 'Koala'
 .*chatglm:
+  mode: 'instruct'
   instruction_template: 'ChatGLM'
-.*(metharme|pygmalion|mythalion):
+.*metharme:
+  mode: 'instruct'
   instruction_template: 'Metharme'
+.*llava:
+  mode: 'instruct'
+  model_type: 'llama'
+  instruction_template: 'LLaVA'
+  custom_stopping_strings: '"\n###"'
 .*raven:
+  mode: 'instruct'
   instruction_template: 'RWKV-Raven'
+.*ctx8192:
+  truncation_length: 8192
 .*moss-moon.*sft:
+  mode: 'instruct'
   instruction_template: 'MOSS'
 .*stablelm-tuned:
+  mode: 'instruct'
   instruction_template: 'StableLM'
+  truncation_length: 4096
+.*stablelm-base:
+  truncation_length: 4096
+.*wizardlm:
+  mode: 'instruct'
+  model_type: 'llama'
+  instruction_template: 'WizardLM'
 .*galactica.*finetuned:
+  mode: 'instruct'
   instruction_template: 'Galactica Finetuned'
 .*galactica.*-v2:
+  mode: 'instruct'
   instruction_template: 'Galactica v2'
 (?!.*finetuned)(?!.*-v2).*galactica:
+  mode: 'instruct'
   instruction_template: 'Galactica'
 .*guanaco:
+  mode: 'instruct'
   instruction_template: 'Guanaco non-chat'
 .*baize:
+  mode: 'instruct'
   instruction_template: 'Baize'
 .*mpt-.*instruct:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*mpt-.*chat:
-  instruction_template: 'ChatML'
+  mode: 'instruct'
+  instruction_template: 'MPT-Chat'
 (?!.*-flan-)(?!.*-t5-).*lamini-:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*incite.*chat:
+  mode: 'instruct'
   instruction_template: 'INCITE-Chat'
 .*incite.*instruct:
+  mode: 'instruct'
   instruction_template: 'INCITE-Instruct'
+.*wizard.*mega:
+  mode: 'instruct'
+  instruction_template: 'Wizard-Mega'
+  custom_stopping_strings: '"</s>"'
 .*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-):
-  instruction_template: 'INCITE-Chat'
+  mode: 'instruct'
+  instruction_template: 'H2O-human_bot'
 .*h2ogpt-gm-:
+  mode: 'instruct'
   instruction_template: 'H2O-prompt_answer'
 .*manticore:
+  mode: 'instruct'
   instruction_template: 'Manticore Chat'
 .*bluemoonrp-(30|13)b:
+  mode: 'instruct'
   instruction_template: 'Bluemoon'
+  truncation_length: 4096
 .*Nous-Hermes-13b:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*airoboros:
+  mode: 'instruct'
   instruction_template: 'Vicuna-v1.1'
 .*airoboros.*1.2:
+  mode: 'instruct'
   instruction_template: 'Airoboros-v1.2'
+.*WizardLM-30B-V1.0:
+  mode: 'instruct'
+  instruction_template: 'Vicuna-v1.1'
+TheBloke_WizardLM-30B-GPTQ:
+  mode: 'instruct'
+  instruction_template: 'Vicuna-v1.1'
 .*alpa(cino|sta):
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*hippogriff:
+  mode: 'instruct'
   instruction_template: 'Hippogriff'
+.*gpt4all-.*-snoozy:
+  mode: 'instruct'
+  instruction_template: 'WizardLM'
 .*lazarus:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*guanaco-.*(7|13|33|65)b:
-  instruction_template: 'Vicuna-v0'
+  mode: 'instruct'
+  instruction_template: 'Guanaco'
 .*hypermantis:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*open-llama-.*-open-instruct:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*starcoder-gpteacher-code-instruct:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*tulu:
+  mode: 'instruct'
   instruction_template: 'Tulu'
 .*chronos:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
 .*samantha:
+  mode: 'instruct'
   instruction_template: 'Samantha'
 .*wizardcoder:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
+.*starchat-beta:
+  mode: 'instruct'
+  instruction_template: 'Starchat-Beta'
 .*minotaur:
-  instruction_template: 'Manticore Chat'
+  mode: 'instruct'
+  instruction_template: 'Minotaur'
+.*minotaur-15b:
+  truncation_length: 8192
 .*orca_mini:
+  mode: 'instruct'
   instruction_template: 'Orca Mini'
+.*landmark:
+  truncation_length: 8192
+.*superhot-8k:
+  truncation_length: 8192
+.*xgen.*-inst:
+  truncation_length: 8192
+  instruction_template: 'Vicuna-v0'
 .*(platypus|gplatty|superplatty):
+  mode: 'instruct'
   instruction_template: 'Alpaca'
-.*(openorca-platypus2):
-  instruction_template: 'OpenOrca-Platypus2'
-  custom_stopping_strings: '"### Instruction:", "### Response:"'
 .*longchat:
+  mode: 'instruct'
   instruction_template: 'Vicuna-v1.1'
 .*vicuna-33b:
+  mode: 'instruct'
   instruction_template: 'Vicuna-v1.1'
 .*redmond-hermes-coder:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
+  truncation_length: 8192
 .*wizardcoder-15b:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
-.*wizardlm:
+  truncation_length: 8192
+.*wizardlm-.*-v1.1:
+  mode: 'instruct'
   instruction_template: 'Vicuna-v1.1'
 .*godzilla:
+  mode: 'instruct'
   instruction_template: 'Alpaca'
-.*llama(-?)(2|v2).*chat:
-  instruction_template: 'Llama-v2'
-.*newhope:
-  instruction_template: 'NewHope'
-.*stablebeluga2:
-  instruction_template: 'StableBeluga2'
-.*openchat:
-  instruction_template: 'OpenChat'
-.*codellama.*instruct:
-  instruction_template: 'Llama-v2'
-.*(mistral|mixtral).*instruct:
-  instruction_template: 'Mistral'
-.*mistral.*openorca:
-  instruction_template: 'ChatML'
-.*(WizardCoder-Python-34B-V1.0|Phind-CodeLlama-34B-v2|CodeBooga-34B-v0.1):
-  instruction_template: 'Alpaca'
-.*orca-2-(13|7)b:
-  instruction_template: 'ChatML'
-.*openhermes.*mistral:
-  instruction_template: 'ChatML'
-.*Yi-34B-Chat:
-  instruction_template: 'ChatML'
-(dolphin).*:
-  instruction_template: 'ChatML'
-.*synthia:
-  instruction_template: 'Synthia'
-.*(hercules|hyperion):
-  instruction_template: 'ChatML'
-.*command-r:
-  instruction_template: 'Command-R'
-.*xwin-lm-70b-v0.1:
-  instruction_template: 'Vicuna-v1.1'
-.*platypus-yi-34b:
-  instruction_template: 'Vicuna-v1.1'
-.*CausalLM-RP-34B:
-  instruction_template: 'ChatML'
-34b-beta:
-  instruction_template: 'ChatML'
-.*airoboros-3_1-yi-34b-200k:
+.*llama-(2|v2):
+  truncation_length: 4096
+.*llama-(2|v2).*chat:
+  mode: 'instruct'
   instruction_template: 'Llama-v2'

models/orca-mini-3b.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84705205f71dd55be7b24a778f248f0eda9999a125d313358c087e092d83148
+size 1928446208