A continuation of OpenHermes 2 model, trained on additional code datasets.
Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.
Uptime stats for OpenHermes 2.5 Mistral 7B across all providers
Sample code and API for OpenHermes 2.5 Mistral 7B
OpenRouter normalizes requests and responses across providers for you.
To get started, you can use OpenHermes 2.5 Mistral 7B via API like this:
fetch("https://openrouter.ai/api/v1/chat/completions",{ method:"POST", headers:{"Authorization":`Bearer ${OPENROUTER_API_KEY}`,"HTTP-Referer":`${YOUR_SITE_URL}`,// Optional, for including your app on openrouter.ai rankings."X-Title":`${YOUR_SITE_NAME}`,// Optional. Shows in rankings on openrouter.ai."Content-Type":"application/json"}, body:JSON.stringify({"model":"teknium/openhermes-2.5-mistral-7b","messages":[{"role":"user","content":"What is the meaning of life?"}]})});
You can also use OpenRouter with OpenAI's client API:
import OpenAI from"openai"const openai =newOpenAI({ baseURL:"https://openrouter.ai/api/v1", apiKey: $OPENROUTER_API_KEY, defaultHeaders:{"HTTP-Referer": $YOUR_SITE_URL,// Optional, for including your app on openrouter.ai rankings."X-Title": $YOUR_SITE_NAME,// Optional. Shows in rankings on openrouter.ai.}})asyncfunctionmain(){const completion =await openai.chat.completions.create({ model:"teknium/openhermes-2.5-mistral-7b", messages:[{"role":"user","content":"What is the meaning of life?"}]})console.log(completion.choices[0].message)}main()
See the Request docs for all possible parameters, and Parameters for recommended values.