Main Page

Sst-yde — Thu, 09 Jul 2026 14:20:16 GMT

Overview

← Older revision		Revision as of 16:20, 9 July 2026
(One intermediate revision by the same user not shown)
Line 39:		Line 39:
	[[:Category:AI on demand\|AI on demand]]		[[:Category:AI on demand\|AI on demand]]
	* [[AI on demand: Usage]] (list models, show usage, ...)		* [[AI on demand: Usage]] (list models, show usage, ...)
			* [[AI on demand: apertus-ai/Apertus-v1.5-8B-Prerelease-2607]]
			* <s>[[AI on demand: swiss-ai/Apertus-70B-Instruct-2509]]</s> (discontinued since the 7th of May 2026!)
	* [[AI on demand: BAAI/bge-m3]]		* [[AI on demand: BAAI/bge-m3]]
	* [[AI on demand: BAAI/bge-reranker-v2-m3]]		* [[AI on demand: BAAI/bge-reranker-v2-m3]]
Line 50:		Line 52:
	* [[AI on demand: openai/whisper-large-v3]]		* [[AI on demand: openai/whisper-large-v3]]
	* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]		* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]
	* <s>[[AI on demand: swiss-ai/Apertus-70B-Instruct-2509]]</s> (discontinued since the 7th of May 2026!)

	[[:Category:Backup\|Backup]]		[[:Category:Backup\|Backup]]

AI on demand: apertus-ai/Apertus-v1.5-8B-Prerelease-2607

Sst-yde — Thu, 09 Jul 2026 14:19:13 GMT

Created page with "== Calling the model == <syntaxhighlight lang="bash"> # Set your personal key: STONEY_KEY=sk-... # Set the desired model: MODEL=apertus-ai/Apertus-v1.5-8B-Prerelease-2607 # Set your prompt: PROMPT='Hello.' # Set maximum amount of tokens: MAX_TOKENS=100 curl https://llm.stoney-cloud.com/v1/chat/completions \ --silent --fail --show-error \ --header "Authorization: Bearer $STONEY_KEY" \ --header 'Content-Type: application/json' \ --data..."

New page

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=apertus-ai/Apertus-v1.5-8B-Prerelease-2607

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=100

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-8c1d87941fc8fa7d",
"object": "chat.completion",
"created": 1783606728,
"model": "apertus-ai/Apertus-v1.5-8B-Prerelease-2607",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null,
"routed_experts": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.24.0-28f19b20",
"usage": {
"prompt_tokens": 64,
"total_tokens": 74,
"completion_tokens": 10,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"prompt_text": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category:AI on demand]]

MediaWiki - Recent changes [en]

Main Page

AI on demand: apertus-ai/Apertus-v1.5-8B-Prerelease-2607