Skip to content

Commit

Permalink
Merge branch 'master' into light-mode-1
Browse files Browse the repository at this point in the history
  • Loading branch information
@timothycarambat
timothycarambat authored Nov 18, 2024
2 parents 8d591f5 + e29f054 commit 999dd30
Show file tree
Hide file tree
Showing 3 changed files with 102 additions and 144 deletions.
108 changes: 36 additions & 72 deletions server/utils/AiProviders/togetherAi/models.js
View file
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
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
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

0 comments on commit 999dd30

Please sign in to comment.