technillogue / mistral-instruct-webrtc-triton

  • Public
  • 13 runs

Run technillogue/mistral-instruct-webrtc-triton with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
prompt
string
None
system_prompt
string
You are a very helpful, respectful and honest assistant.
None
max_new_tokens
integer
250
None
min_length
integer
None
top_k
integer
0
None
top_p
number
0
None
temperature
number
1
None
length_penalty
number
1
None
presence_penalty
number
0
None
frequency_penalty
number
0
None
stop_words
string
None
prompt_template
string
<s>[INST] {system_prompt} {prompt} [/INST]
None
webrtc_offer
string
instead of a single prediction, handle a WebRTC offer as json, optionally with an ice_server key of ICE servers to use for connecting

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "string"
  },
  "title": "Output",
  "x-cog-array-type": "iterator",
  "x-cog-array-display": "concatenate"
}