Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

💄 style: add mistral provider new models #4014

Merged
merged 2 commits into from
Sep 19, 2024
Merged

💄 style: add mistral provider new models #4014

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
58b1796
Update mistral.ts
LovelyGuYiMeng Sep 18, 2024
39e2f33
Update upstage.ts
LovelyGuYiMeng Sep 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 38 additions & 21 deletions src/config/modelProviders/mistral.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,33 +6,20 @@ const Mistral: ModelProviderCard = {
chatModels: [
{
description:
'Mistral 7B是一款紧凑但高性能的模型，擅长批量处理和简单任务，如分类和文本生成，具有良好的推理能力。',
displayName: 'Mistral 7B',
id: 'open-mistral-7b',
tokens: 32_768,
},
{
description:
'Mixtral 8x7B是一个稀疏专家模型，利用多个参数提高推理速度，适合处理多语言和代码生成任务。',
displayName: 'Mixtral 8x7B',
id: 'open-mixtral-8x7b',
tokens: 32_768,
},
{
description:
'Mixtral 8x22B是一个更大的专家模型，专注于复杂任务，提供出色的推理能力和更高的吞吐量。',
displayName: 'Mixtral 8x22B',
'Mistral Nemo是一个与Nvidia合作开发的12B模型，提供出色的推理和编码性能，易于集成和替换。',
displayName: 'Mistral Nemo',
enabled: true,
functionCall: true,
id: 'open-mixtral-8x22b',
tokens: 65_536,
id: 'open-mistral-nemo',
tokens: 128_000,
},
{
description:
'Mistral Nemo是一个与Nvidia合作开发的12B模型，提供出色的推理和编码性能，易于集成和替换。',
displayName: 'Mistral Nemo',
'Mistral Small是成本效益高、快速且可靠的选项，适用于翻译、摘要和情感分析等用例。',
displayName: 'Mistral Small',
enabled: true,
functionCall: true,
id: 'open-mistral-nemo',
id: 'mistral-small-latest',
tokens: 128_000,
},
{
Expand All @@ -51,6 +38,36 @@ const Mistral: ModelProviderCard = {
id: 'codestral-latest',
tokens: 32_768,
},
{
description: 'Pixtral 模型在图表和图理解、文档问答、多模态推理和指令遵循等任务上表现出强大的能力，能够以自然分辨率和宽高比摄入图像，还能够在长达 128K 令牌的长上下文窗口中处理任意数量的图像。',
displayName: 'Pixtral 12B',
enabled: true,
id: 'pixtral-12b-2409',
tokens: 128_000,
vision: true,
},
{
description:
'Mistral 7B是一款紧凑但高性能的模型，擅长批量处理和简单任务，如分类和文本生成，具有良好的推理能力。',
displayName: 'Mistral 7B',
id: 'open-mistral-7b',
tokens: 32_768,
},
{
description:
'Mixtral 8x7B是一个稀疏专家模型，利用多个参数提高推理速度，适合处理多语言和代码生成任务。',
displayName: 'Mixtral 8x7B',
id: 'open-mixtral-8x7b',
tokens: 32_768,
},
{
description:
'Mixtral 8x22B是一个更大的专家模型，专注于复杂任务，提供出色的推理能力和更高的吞吐量。',
displayName: 'Mixtral 8x22B',
functionCall: true,
id: 'open-mixtral-8x22b',
tokens: 65_536,
},
{
description:
'Codestral Mamba是专注于代码生成的Mamba 2语言模型，为先进的代码和推理任务提供强力支持。',
Expand Down
18 changes: 9 additions & 9 deletions src/config/modelProviders/upstage.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,15 +3,6 @@ import { ModelProviderCard } from '@/types/llm';
// ref :https://developers.upstage.ai/docs/getting-started/models
const Upstage: ModelProviderCard = {
chatModels: [
{
description:
'Solar Pro 是 Upstage 推出的一款高智能LLM，专注于单GPU的指令跟随能力，IFEval得分80以上。目前支持英语，正式版本计划于2024年11月推出，将扩展语言支持和上下文长度。',
displayName: 'Solar Pro',
enabled: true,
functionCall: false,
id: 'solar-pro',
tokens: 4096,
},
{
description:
'Solar Mini 是一种紧凑型 LLM，性能优于 GPT-3.5，具备强大的多语言能力，支持英语和韩语，提供高效小巧的解决方案。',
Expand All @@ -29,6 +20,15 @@ const Upstage: ModelProviderCard = {
id: 'solar-1-mini-chat-ja',
tokens: 32_768,
},
{
description:
'Solar Pro 是 Upstage 推出的一款高智能LLM，专注于单GPU的指令跟随能力，IFEval得分80以上。目前支持英语，正式版本计划于2024年11月推出，将扩展语言支持和上下文长度。',
displayName: 'Solar Pro',
enabled: true,
functionCall: false,
id: 'solar-pro',
tokens: 4096,
},
],
checkModel: 'solar-1-mini-chat',
description:
Expand Down
Loading