tiiuae

/

falcon-40b-instruct

like 1.17k

Hi there

I'm totally new to the falcon-40b-instruct-model AND the using of HuggingFace-inference-endpoints.

What I am trying to do is:

• having an endpoint, that I can invoke with a "prompt" and "instructions", as I can when trying the "falcon-chat-demo"
• sending multiple requests with the same - I guess - "session_hash" (?), so the bot knows, what "we were talking about so far" ..

--code--
What I did:

• I've successfully set up an inference endpoint with falcon-40b-instruct
• I also can reach the endpoint via postman-post-request like so:

const axios = require('axios');
let data = JSON.stringify([
"Hi"
]);

let config = {
method: 'post',
maxBodyLength: Infinity,
url: 'ENDPOINT',
headers: {
'Content-Type': 'application/json'
},
data : data
};

axios.request(config)
.then((response) => {
console.log(JSON.stringify(response.data));
})
.catch((error) => {
console.log(error);
});
--code--

What I am NOT able to do is:

• setting "instructions"
• setting some kind of "session"-id/-hash or whatever, so the bot remembers the conversation like it does in the "falcon-chat-demo".

Can anyone help me out here? I did not find any documentation on this ..

Cheers
Philip