θΏ™ζ˜―indexlocζδΎ›ηš„ζœεŠ‘οΌŒδΈθ¦θΎ“ε…₯任何密码
Skip to content

Bump TogetherAI models #2645

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

Merged
merged 2 commits into from
Nov 18, 2024
Merged

Bump TogetherAI models #2645

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
ecd8ada
bump together ai models
shatfield4 Nov 18, 2024
8f5f5dc
Run post-bump command
timothycarambat Nov 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
108 changes: 36 additions & 72 deletions server/utils/AiProviders/togetherAi/models.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,82 +1,10 @@
const MODELS = {
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
organization: "Meta",
name: "Llama 3.1 8B Instruct Turbo",
maxLength: 128000,
},
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
organization: "Meta",
name: "Llama 3.1 70B Instruct Turbo",
maxLength: 128000,
},
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
organization: "Meta",
name: "Llama 3.1 405B Instruct Turbo",
maxLength: 4096,
},
"meta-llama/Meta-Llama-3-8B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
organization: "Meta",
name: "Llama 3 8B Instruct Turbo",
maxLength: 8192,
},
"meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
organization: "Meta",
name: "Llama 3 70B Instruct Turbo",
maxLength: 8192,
},
"meta-llama/Meta-Llama-3-8B-Instruct-Lite": {
id: "meta-llama/Meta-Llama-3-8B-Instruct-Lite",
organization: "Meta",
name: "Llama 3 8B Instruct Lite",
maxLength: 8192,
},
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
id: "meta-llama/Meta-Llama-3-70B-Instruct-Lite",
organization: "Meta",
name: "Llama 3 70B Instruct Lite",
maxLength: 8192,
},
"google/gemma-2-27b-it": {
id: "google/gemma-2-27b-it",
organization: "Google",
name: "Gemma 2 27B",
maxLength: 8192,
},
"google/gemma-2-9b-it": {
id: "google/gemma-2-9b-it",
organization: "Google",
name: "Gemma 2 9B",
maxLength: 8192,
},
"allenai/OLMo-7B-Instruct": {
id: "allenai/OLMo-7B-Instruct",
organization: "Allen AI",
name: "OLMo Instruct (7B)",
maxLength: 2048,
},
"zero-one-ai/Yi-34B-Chat": {
id: "zero-one-ai/Yi-34B-Chat",
organization: "01.AI",
name: "01-ai Yi Chat (34B)",
maxLength: 4096,
},
"allenai/OLMo-7B-Twin-2T": {
id: "allenai/OLMo-7B-Twin-2T",
organization: "Allen AI",
name: "OLMo Twin-2T (7B)",
maxLength: 2048,
},
"allenai/OLMo-7B": {
id: "allenai/OLMo-7B",
organization: "Allen AI",
name: "OLMo (7B)",
maxLength: 2048,
},
"Austism/chronos-hermes-13b": {
id: "Austism/chronos-hermes-13b",
organization: "Austism",
Expand Down Expand Up @@ -131,6 +59,12 @@ const MODELS = {
name: "MythoMax-L2 (13B)",
maxLength: 4096,
},
"Gryphe/MythoMax-L2-13b-Lite": {
id: "Gryphe/MythoMax-L2-13b-Lite",
organization: "Gryphe",
name: "MythoMax-L2 Lite (13B)",
maxLength: 4096,
},
"lmsys/vicuna-13b-v1.5": {
id: "lmsys/vicuna-13b-v1.5",
organization: "LM Sys",
Expand Down Expand Up @@ -197,6 +131,36 @@ const MODELS = {
name: "LLaMA-3 Chat (70B)",
maxLength: 8192,
},
"meta-llama/Meta-Llama-3-8B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
organization: "Meta",
name: "LLaMA-3 Chat (8B) Turbo",
maxLength: 8192,
},
"meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
organization: "Meta",
name: "LLaMA-3 Chat (70B) Turbo",
maxLength: 8192,
},
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
organization: "Meta",
name: "Llama 3.1 8B Instruct Turbo",
maxLength: 8192,
},
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
organization: "Meta",
name: "Llama 3.1 70B Instruct Turbo",
maxLength: 8192,
},
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
id: "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
organization: "Meta",
name: "Llama 3.1 405B Instruct Turbo",
maxLength: 4096,
},
"mistralai/Mistral-7B-Instruct-v0.1": {
id: "mistralai/Mistral-7B-Instruct-v0.1",
organization: "mistralai",
Expand Down
136 changes: 65 additions & 71 deletions server/utils/AiProviders/togetherAi/scripts/chat_models.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,71 +1,65 @@
| Organization | Model Name | Model String for API | Context length |
|--------------|------------|----------------------|----------------|
| Meta | Llama 3.1 8B Instruct Turbo | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | 128000 |
| Meta | Llama 3.1 70B Instruct Turbo | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 128000 |
| Meta | Llama 3.1 405B Instruct Turbo | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 4096 |
| Meta | Llama 3 8B Instruct Turbo | meta-llama/Meta-Llama-3-8B-Instruct-Turbo | 8192 |
| Meta | Llama 3 70B Instruct Turbo | meta-llama/Meta-Llama-3-70B-Instruct-Turbo | 8192 |
| Meta | Llama 3 8B Instruct Lite | meta-llama/Meta-Llama-3-8B-Instruct-Lite | 8192 |
| Meta | Llama 3 70B Instruct Lite | meta-llama/Meta-Llama-3-70B-Instruct-Lite | 8192 |
| Google | Gemma 2 27B | google/gemma-2-27b-it | 8192 |
| Google | Gemma 2 9B | google/gemma-2-9b-it | 8192 |
| Allen AI | OLMo Instruct (7B) | allenai/OLMo-7B-Instruct | 2048 |
| 01.AI | 01-ai Yi Chat (34B) | zero-one-ai/Yi-34B-Chat | 4096 |
| Allen AI | OLMo Twin-2T (7B) | allenai/OLMo-7B-Twin-2T | 2048 |
| Allen AI | OLMo (7B) | allenai/OLMo-7B | 2048 |
| Austism | Chronos Hermes (13B) | Austism/chronos-hermes-13b | 2048 |
| cognitivecomputations | Dolphin 2.5 Mixtral 8x7b | cognitivecomputations/dolphin-2.5-mixtral-8x7b | 32768 |
| databricks | DBRX Instruct | databricks/dbrx-instruct | 32768 |
| DeepSeek | Deepseek Coder Instruct (33B) | deepseek-ai/deepseek-coder-33b-instruct | 16384 |
| DeepSeek | DeepSeek LLM Chat (67B) | deepseek-ai/deepseek-llm-67b-chat | 4096 |
| garage-bAInd | Platypus2 Instruct (70B) | garage-bAInd/Platypus2-70B-instruct | 4096 |
| Google | Gemma Instruct (2B) | google/gemma-2b-it | 8192 |
| Google | Gemma Instruct (7B) | google/gemma-7b-it | 8192 |
| Gryphe | MythoMax-L2 (13B) | Gryphe/MythoMax-L2-13b | 4096 |
| LM Sys | Vicuna v1.5 (13B) | lmsys/vicuna-13b-v1.5 | 4096 |
| LM Sys | Vicuna v1.5 (7B) | lmsys/vicuna-7b-v1.5 | 4096 |
| Meta | Code Llama Instruct (13B) | codellama/CodeLlama-13b-Instruct-hf | 16384 |
| Meta | Code Llama Instruct (34B) | codellama/CodeLlama-34b-Instruct-hf | 16384 |
| Meta | Code Llama Instruct (70B) | codellama/CodeLlama-70b-Instruct-hf | 4096 |
| Meta | Code Llama Instruct (7B) | codellama/CodeLlama-7b-Instruct-hf | 16384 |
| Meta | LLaMA-2 Chat (70B) | meta-llama/Llama-2-70b-chat-hf | 4096 |
| Meta | LLaMA-2 Chat (13B) | meta-llama/Llama-2-13b-chat-hf | 4096 |
| Meta | LLaMA-2 Chat (7B) | meta-llama/Llama-2-7b-chat-hf | 4096 |
| Meta | LLaMA-3 Chat (8B) | meta-llama/Llama-3-8b-chat-hf | 8192 |
| Meta | LLaMA-3 Chat (70B) | meta-llama/Llama-3-70b-chat-hf | 8192 |
| mistralai | Mistral (7B) Instruct | mistralai/Mistral-7B-Instruct-v0.1 | 8192 |
| mistralai | Mistral (7B) Instruct v0.2 | mistralai/Mistral-7B-Instruct-v0.2 | 32768 |
| mistralai | Mistral (7B) Instruct v0.3 | mistralai/Mistral-7B-Instruct-v0.3 | 32768 |
| mistralai | Mixtral-8x7B Instruct (46.7B) | mistralai/Mixtral-8x7B-Instruct-v0.1 | 32768 |
| mistralai | Mixtral-8x22B Instruct (141B) | mistralai/Mixtral-8x22B-Instruct-v0.1 | 65536 |
| NousResearch | Nous Capybara v1.9 (7B) | NousResearch/Nous-Capybara-7B-V1p9 | 8192 |
| NousResearch | Nous Hermes 2 - Mistral DPO (7B) | NousResearch/Nous-Hermes-2-Mistral-7B-DPO | 32768 |
| NousResearch | Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) | NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO | 32768 |
| NousResearch | Nous Hermes 2 - Mixtral 8x7B-SFT (46.7B) | NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT | 32768 |
| NousResearch | Nous Hermes LLaMA-2 (7B) | NousResearch/Nous-Hermes-llama-2-7b | 4096 |
| NousResearch | Nous Hermes Llama-2 (13B) | NousResearch/Nous-Hermes-Llama2-13b | 4096 |
| NousResearch | Nous Hermes-2 Yi (34B) | NousResearch/Nous-Hermes-2-Yi-34B | 4096 |
| OpenChat | OpenChat 3.5 (7B) | openchat/openchat-3.5-1210 | 8192 |
| OpenOrca | OpenOrca Mistral (7B) 8K | Open-Orca/Mistral-7B-OpenOrca | 8192 |
| Qwen | Qwen 1.5 Chat (0.5B) | Qwen/Qwen1.5-0.5B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (1.8B) | Qwen/Qwen1.5-1.8B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (4B) | Qwen/Qwen1.5-4B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (7B) | Qwen/Qwen1.5-7B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (14B) | Qwen/Qwen1.5-14B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (32B) | Qwen/Qwen1.5-32B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (72B) | Qwen/Qwen1.5-72B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (110B) | Qwen/Qwen1.5-110B-Chat | 32768 |
| Qwen | Qwen 2 Instruct (72B) | Qwen/Qwen2-72B-Instruct | 32768 |
| Snorkel AI | Snorkel Mistral PairRM DPO (7B) | snorkelai/Snorkel-Mistral-PairRM-DPO | 32768 |
| Snowflake | Snowflake Arctic Instruct | Snowflake/snowflake-arctic-instruct | 4096 |
| Stanford | Alpaca (7B) | togethercomputer/alpaca-7b | 2048 |
| Teknium | OpenHermes-2-Mistral (7B) | teknium/OpenHermes-2-Mistral-7B | 8192 |
| Teknium | OpenHermes-2.5-Mistral (7B) | teknium/OpenHermes-2p5-Mistral-7B | 8192 |
| Together | LLaMA-2-7B-32K-Instruct (7B) | togethercomputer/Llama-2-7B-32K-Instruct | 32768 |
| Together | RedPajama-INCITE Chat (3B) | togethercomputer/RedPajama-INCITE-Chat-3B-v1 | 2048 |
| Together | RedPajama-INCITE Chat (7B) | togethercomputer/RedPajama-INCITE-7B-Chat | 2048 |
| Together | StripedHyena Nous (7B) | togethercomputer/StripedHyena-Nous-7B | 32768 |
| Undi95 | ReMM SLERP L2 (13B) | Undi95/ReMM-SLERP-L2-13B | 4096 |
| Undi95 | Toppy M (7B) | Undi95/Toppy-M-7B | 4096 |
| WizardLM | WizardLM v1.2 (13B) | WizardLM/WizardLM-13B-V1.2 | 4096 |
| upstage | Upstage SOLAR Instruct v1 (11B) | upstage/SOLAR-10.7B-Instruct-v1.0 | 4096 |
| Organization | Model Name | Model String for API | Context length |
| :-------------------- | :--------------------------------------- | :--------------------------------------------- | :------------- |
| 01.AI | 01-ai Yi Chat (34B) | zero-one-ai/Yi-34B-Chat | 4096 |
| Austism | Chronos Hermes (13B) | Austism/chronos-hermes-13b | 2048 |
| cognitivecomputations | Dolphin 2.5 Mixtral 8x7b | cognitivecomputations/dolphin-2.5-mixtral-8x7b | 32768 |
| databricks | DBRX Instruct | databricks/dbrx-instruct | 32768 |
| DeepSeek | Deepseek Coder Instruct (33B) | deepseek-ai/deepseek-coder-33b-instruct | 16384 |
| DeepSeek | DeepSeek LLM Chat (67B) | deepseek-ai/deepseek-llm-67b-chat | 4096 |
| garage-bAInd | Platypus2 Instruct (70B) | garage-bAInd/Platypus2-70B-instruct | 4096 |
| Google | Gemma Instruct (2B) | google/gemma-2b-it | 8192 |
| Google | Gemma Instruct (7B) | google/gemma-7b-it | 8192 |
| Gryphe | MythoMax-L2 (13B) | Gryphe/MythoMax-L2-13b | 4096 |
| Gryphe | MythoMax-L2 Lite (13B) | Gryphe/MythoMax-L2-13b-Lite | 4096 |
| LM Sys | Vicuna v1.5 (13B) | lmsys/vicuna-13b-v1.5 | 4096 |
| LM Sys | Vicuna v1.5 (7B) | lmsys/vicuna-7b-v1.5 | 4096 |
| Meta | Code Llama Instruct (13B) | codellama/CodeLlama-13b-Instruct-hf | 16384 |
| Meta | Code Llama Instruct (34B) | codellama/CodeLlama-34b-Instruct-hf | 16384 |
| Meta | Code Llama Instruct (70B) | codellama/CodeLlama-70b-Instruct-hf | 4096 |
| Meta | Code Llama Instruct (7B) | codellama/CodeLlama-7b-Instruct-hf | 16384 |
| Meta | LLaMA-2 Chat (70B) | meta-llama/Llama-2-70b-chat-hf | 4096 |
| Meta | LLaMA-2 Chat (13B) | meta-llama/Llama-2-13b-chat-hf | 4096 |
| Meta | LLaMA-2 Chat (7B) | meta-llama/Llama-2-7b-chat-hf | 4096 |
| Meta | LLaMA-3 Chat (8B) | meta-llama/Llama-3-8b-chat-hf | 8192 |
| Meta | LLaMA-3 Chat (70B) | meta-llama/Llama-3-70b-chat-hf | 8192 |
| Meta | LLaMA-3 Chat (8B) Turbo | meta-llama/Meta-Llama-3-8B-Instruct-Turbo | 8192 |
| Meta | LLaMA-3 Chat (70B) Turbo | meta-llama/Meta-Llama-3-70B-Instruct-Turbo | 8192 |
| Meta | Llama 3.1 8B Instruct Turbo | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | 8192 |
| Meta | Llama 3.1 70B Instruct Turbo | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 8192 |
| Meta | Llama 3.1 405B Instruct Turbo | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 4096 |
| mistralai | Mistral (7B) Instruct | mistralai/Mistral-7B-Instruct-v0.1 | 8192 |
| mistralai | Mistral (7B) Instruct v0.2 | mistralai/Mistral-7B-Instruct-v0.2 | 32768 |
| mistralai | Mistral (7B) Instruct v0.3 | mistralai/Mistral-7B-Instruct-v0.3 | 32768 |
| mistralai | Mixtral-8x7B Instruct (46.7B) | mistralai/Mixtral-8x7B-Instruct-v0.1 | 32768 |
| mistralai | Mixtral-8x22B Instruct (141B) | mistralai/Mixtral-8x22B-Instruct-v0.1 | 65536 |
| NousResearch | Nous Capybara v1.9 (7B) | NousResearch/Nous-Capybara-7B-V1p9 | 8192 |
| NousResearch | Nous Hermes 2 - Mistral DPO (7B) | NousResearch/Nous-Hermes-2-Mistral-7B-DPO | 32768 |
| NousResearch | Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) | NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO | 32768 |
| NousResearch | Nous Hermes 2 - Mixtral 8x7B-SFT (46.7B) | NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT | 32768 |
| NousResearch | Nous Hermes LLaMA-2 (7B) | NousResearch/Nous-Hermes-llama-2-7b | 4096 |
| NousResearch | Nous Hermes Llama-2 (13B) | NousResearch/Nous-Hermes-Llama2-13b | 4096 |
| NousResearch | Nous Hermes-2 Yi (34B) | NousResearch/Nous-Hermes-2-Yi-34B | 4096 |
| OpenChat | OpenChat 3.5 (7B) | openchat/openchat-3.5-1210 | 8192 |
| OpenOrca | OpenOrca Mistral (7B) 8K | Open-Orca/Mistral-7B-OpenOrca | 8192 |
| Qwen | Qwen 1.5 Chat (0.5B) | Qwen/Qwen1.5-0.5B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (1.8B) | Qwen/Qwen1.5-1.8B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (4B) | Qwen/Qwen1.5-4B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (7B) | Qwen/Qwen1.5-7B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (14B) | Qwen/Qwen1.5-14B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (32B) | Qwen/Qwen1.5-32B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (72B) | Qwen/Qwen1.5-72B-Chat | 32768 |
| Qwen | Qwen 1.5 Chat (110B) | Qwen/Qwen1.5-110B-Chat | 32768 |
| Qwen | Qwen 2 Instruct (72B) | Qwen/Qwen2-72B-Instruct | 32768 |
| Snorkel AI | Snorkel Mistral PairRM DPO (7B) | snorkelai/Snorkel-Mistral-PairRM-DPO | 32768 |
| Snowflake | Snowflake Arctic Instruct | Snowflake/snowflake-arctic-instruct | 4096 |
| Stanford | Alpaca (7B) | togethercomputer/alpaca-7b | 2048 |
| Teknium | OpenHermes-2-Mistral (7B) | teknium/OpenHermes-2-Mistral-7B | 8192 |
| Teknium | OpenHermes-2.5-Mistral (7B) | teknium/OpenHermes-2p5-Mistral-7B | 8192 |
| Together | LLaMA-2-7B-32K-Instruct (7B) | togethercomputer/Llama-2-7B-32K-Instruct | 32768 |
| Together | RedPajama-INCITE Chat (3B) | togethercomputer/RedPajama-INCITE-Chat-3B-v1 | 2048 |
| Together | RedPajama-INCITE Chat (7B) | togethercomputer/RedPajama-INCITE-7B-Chat | 2048 |
| Together | StripedHyena Nous (7B) | togethercomputer/StripedHyena-Nous-7B | 32768 |
| Undi95 | ReMM SLERP L2 (13B) | Undi95/ReMM-SLERP-L2-13B | 4096 |
| Undi95 | Toppy M (7B) | Undi95/Toppy-M-7B | 4096 |
| WizardLM | WizardLM v1.2 (13B) | WizardLM/WizardLM-13B-V1.2 | 4096 |
| upstage | Upstage SOLAR Instruct v1 (11B) | upstage/SOLAR-10.7B-Instruct-v1.0 | 4096 |
2 changes: 1 addition & 1 deletion server/utils/AiProviders/togetherAi/scripts/parse.mjs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
// copy outputs into the export in ../models.js

// Update the date below if you run this again because TogetherAI added new models.
// Last Collected: Jul 31, 2024
// Last Collected: Nov 18, 2024
// Since last collection Together's docs are broken. I just copied the HTML table
// and had claude3 convert to markdown and it works well enough.

Expand Down