zack3d/big-agi
1
0
Fork 0
mirror of https://github.com/enricoros/big-AGI.git synced 2026-05-10 21:50:14 -07:00
Code Issues Packages Projects Releases Wiki Activity

Groq: update models

Browse Source
This commit is contained in:
Enrico Ros
2024-04-22 02:52:19 -07:00
parent ad56e3165c
commit 3eef03b303
2 changed files with 47 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/modules/llms/server/openai/models.data.ts
+44 -10
View File
@@ -842,23 +842,48 @@ export function perplexityAIModelSort(a: ModelDescriptionSchema, b: ModelDescrip
return b.label.localeCompare(a.label);
}
// Groq
// Groq - https://console.groq.com/docs/models
const _knownGroqModels: ManualMappings = [
// {
// id: 'lama2-70b-4096',
// label: 'Llama 2 70B Chat',
// description: 'Llama 2 is a collection of pretrained and fine-tuned generative text models.',
// contextWindow: 4096,
// interfaces: [LLM_IF_OAI_Chat],
// },
{
isLatest: true,
idPrefix: 'llama3-70b-8192',
label: 'Llama 3 · 70B',
description: 'LLaMA3 70b developed by Meta with a context window of 8,192 tokens.',
contextWindow: 8192,
interfaces: [LLM_IF_OAI_Chat],
},
{
// isLatest: true,
idPrefix: 'llama3-8b-8192',
label: 'Llama 3 · 8B',
description: 'LLaMA3 8b developed by Meta with a context window of 8,192 tokens.',
contextWindow: 8192,
interfaces: [LLM_IF_OAI_Chat],
},
{
idPrefix: 'llama2-70b-4096',
label: 'Llama 2 · 70B',
description: 'LLaMA2 70b developed by Meta with a context window of 4,096 tokens.',
contextWindow: 4096,
interfaces: [LLM_IF_OAI_Chat],
hidden: true,
},
{
idPrefix: 'mixtral-8x7b-32768',
label: 'Mixtral 8x7B Instruct v0.1',
description: 'The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.',
label: 'Mixtral 8x7B',
description: 'Mixtral 8x7b developed by Mistral with a context window of 32,768 tokens.',
contextWindow: 32768,
interfaces: [LLM_IF_OAI_Chat],
},
{
idPrefix: 'gemma-7b-it',
label: 'Gemma 1.1 · 7B Instruct',
description: 'Gemma 7b developed by Google with a context window of 8,192 tokens.',
contextWindow: 8192,
interfaces: [LLM_IF_OAI_Chat],
},
];
export function groqModelToModelDescription(_model: unknown): ModelDescriptionSchema {
@@ -873,6 +898,15 @@ export function groqModelToModelDescription(_model: unknown): ModelDescriptionSc
});
}
export function groqModelSortFn(a: ModelDescriptionSchema, b: ModelDescriptionSchema): number {
// sort as per their order in the known models
const aIndex = _knownGroqModels.findIndex(base => a.id.startsWith(base.idPrefix));
const bIndex = _knownGroqModels.findIndex(base => b.id.startsWith(base.idPrefix));
if (aIndex !== -1 && bIndex !== -1)
return aIndex - bIndex;
return a.id.localeCompare(b.id);
}
// Helpers
src/modules/llms/server/openai/openai.router.ts
+3 -2
View File
@@ -11,7 +11,7 @@ import { Brand } from '~/common/app.config';
import { fixupHost } from '~/common/util/urlUtils';
import { OpenAIWire, WireOpenAICreateImageOutput, wireOpenAICreateImageOutputSchema, WireOpenAICreateImageRequest } from './openai.wiretypes';
import { azureModelToModelDescription, groqModelToModelDescription, lmStudioModelToModelDescription, localAIModelToModelDescription, mistralModelsSort, mistralModelToModelDescription, oobaboogaModelToModelDescription, openAIModelFilter, openAIModelToModelDescription, openRouterModelFamilySortFn, openRouterModelToModelDescription, perplexityAIModelDescriptions, perplexityAIModelSort, togetherAIModelsToModelDescriptions } from './models.data';
import { azureModelToModelDescription, groqModelSortFn, groqModelToModelDescription, lmStudioModelToModelDescription, localAIModelToModelDescription, mistralModelsSort, mistralModelToModelDescription, oobaboogaModelToModelDescription, openAIModelFilter, openAIModelToModelDescription, openRouterModelFamilySortFn, openRouterModelToModelDescription, perplexityAIModelDescriptions, perplexityAIModelSort, togetherAIModelsToModelDescriptions } from './models.data';
import { llmsChatGenerateWithFunctionsOutputSchema, llmsListModelsOutputSchema, ModelDescriptionSchema } from '../llm.server.types';
import { wilreLocalAIModelsApplyOutputSchema, wireLocalAIModelsAvailableOutputSchema, wireLocalAIModelsListOutputSchema } from './localai.wiretypes';
@@ -168,7 +168,8 @@ export const llmOpenAIRouter = createTRPCRouter({
case 'groq':
models = openAIModels
.map(groqModelToModelDescription);
.map(groqModelToModelDescription)
.sort(groqModelSortFn);
break;
case 'lmstudio':