Gasby supports chat with models provided by NVIDIA. To connect NVIDIA with Gasby, you'll need to signup and get access API Key, then add it to Gasby.
Get NVIDIA API key
- Visit build.nvidia.com, then signup an account and login
- Open NVIDIA NIM > nvidia/llama-3.1-nemotron-70b-instruct, or any model on NVIDIA NIM
- On the right side, find and click on "Get API key". Select "Generate key" to get an API Key
Copy this API key to use on Gasby
Connect to NVIDIA on Gasby
- On the GasbyAI.com site, click on the settings icon (on the top right) to open the Settings popup
- Under the Settings section, select NVIDIA as the Provider
- Paste the key above into API Key, and select your chat model (or manually enter the model name)
- Click
Test settings
to ensure the settings are correct. Then click Save
Now, you've completed connecting Gasby with your custom API service and should be ready to start using Gasby
Supported models
Gasby supports getting latest models from NVIDIA. To get the latest list of models, open the NVIDIA provider settings (as above), click "Refresh model list" to get an updated list of models.
Current NVIDA chat models:
- 01-ai/yi-large
- abacusai/dracarys-llama-3.1-70b-instruct
- adept/fuyu-8b
- ai21labs/jamba-1.5-large-instruct
- ai21labs/jamba-1.5-mini-instruct
- aisingapore/sea-lion-7b-instruct
- baai/bge-m3
- baichuan-inc/baichuan2-13b-chat
- bigcode/starcoder2-15b
- bigcode/starcoder2-7b
- databricks/dbrx-instruct
- deepseek-ai/deepseek-coder-6.7b-instruct
- google/codegemma-1.1-7b
- google/codegemma-7b
- google/deplot
- google/gemma-2-27b-it
- google/gemma-2-2b-it
- google/gemma-2-9b-it
- google/gemma-2b
- google/gemma-7b
- google/paligemma
- google/recurrentgemma-2b
- google/shieldgemma-9b
- ibm/granite-3.0-3b-a800m-instruct
- ibm/granite-3.0-8b-instruct
- ibm/granite-34b-code-instruct
- ibm/granite-8b-code-instruct
- ibm/granite-guardian-3.0-8b
- institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1
- institute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1
- mediatek/breeze-7b-instruct
- meta/codellama-70b
- meta/llama-3.1-405b-instruct
- meta/llama-3.1-405b-instruct-turbo
- meta/llama-3.1-70b-instruct
- meta/llama-3.1-70b-instruct-turbo
- meta/llama-3.1-8b-instruct
- meta/llama-3.1-8b-instruct-turbo
- meta/llama-3.2-1b-instruct
- meta/llama-3.2-3b-instruct
- meta/llama2-70b
- meta/llama3-70b-instruct
- meta/llama3-8b-instruct
- microsoft/kosmos-2
- microsoft/phi-3-medium-128k-instruct
- microsoft/phi-3-medium-4k-instruct
- microsoft/phi-3-mini-128k-instruct
- microsoft/phi-3-mini-4k-instruct
- microsoft/phi-3-small-128k-instruct
- microsoft/phi-3-small-8k-instruct
- microsoft/phi-3-vision-128k-instruct
- microsoft/phi-3.5-mini-instruct
- microsoft/phi-3.5-moe-instruct
- microsoft/phi-3.5-vision-instruct
- mistralai/codestral-22b-instruct-v0.1
- mistralai/mamba-codestral-7b-v0.1
- mistralai/mathstral-7b-v0.1
- mistralai/mistral-7b-instruct-v0.2
- mistralai/mistral-7b-instruct-v0.3
- mistralai/mistral-large
- mistralai/mistral-large-2-instruct
- mistralai/mixtral-8x22b-instruct-v0.1
- mistralai/mixtral-8x22b-v0.1
- mistralai/mixtral-8x7b-instruct-v0.1
- mistralai/mixtral-8x7b-instruct-v0.1-turbo
- nv-mistralai/mistral-nemo-12b-instruct
- nvidia/embed-qa-4
- nvidia/llama-3.1-nemotron-51b-instruct
- nvidia/llama-3.1-nemotron-70b-instruct
- nvidia/llama-3.1-nemotron-70b-reward
- nvidia/llama3-chatqa-1.5-70b
- nvidia/llama3-chatqa-1.5-8b
- nvidia/mistral-nemo-minitron-8b-8k-instruct
- nvidia/mistral-nemo-minitron-8b-base
- nvidia/nemotron-4-340b-instruct
- nvidia/nemotron-4-340b-reward
- nvidia/nemotron-4-mini-hindi-4b-instruct
- nvidia/nemotron-mini-4b-instruct
- nvidia/neva-22b
- nvidia/nv-embed-v1
- nvidia/nv-embedqa-e5-v5
- nvidia/nv-embedqa-mistral-7b-v2
- nvidia/nvclip
- nvidia/usdcode-llama3-70b-instruct
- nvidia/vila
- qwen/qwen2-7b-instruct
- rakuten/rakutenai-7b-chat
- rakuten/rakutenai-7b-instruct
- snowflake/arctic-embed-l
- thudm/chatglm3-6b
- tokyotech-llm/llama-3-swallow-70b-instruct-v0.1
- upstage/solar-10.7b-instruct
- writer/palmyra-fin-70b-32k
- writer/palmyra-med-70b
- writer/palmyra-med-70b-32k
- yentinglin/llama-3-taiwan-70b-instruct
- zyphra/zamba2-7b-instruct