AI on demand: opendatalab/MinerU2.5-2509-1.2B: Difference between revisions

From MediaWiki
Jump to navigation Jump to search
No edit summary
No edit summary
 
(2 intermediate revisions by the same user not shown)
Line 5: Line 5:


# Set the desired model:
# Set the desired model:
MODEL_ID=MinerU2.5-2509-1.2B
MODEL=MinerU2.5-2509-1.2B


# Set your prompt:
# Set the desired document to run OCR against:
PROMPT='Describe an imaginary document.'
FILE_PATH=document.png


# Set maximum amount of tokens:
# Encode document contents with Base64 and detect MIME type:
MAX_TOKENS=2000
FILE_CONTENT_BASE64=$(base64 -w 0 < "$FILE_PATH")
FILE_MIME_TYPE=$(file --brief --mime-type "$FILE_PATH")


curl -s https://llm.stoney-cloud.com/v1/chat/completions \
curl https://llm.stoney-cloud.com/v1/chat/completions \
  -H "Authorization: Bearer $STONEY_KEY" \
        --silent --fail --show-error \
  -H "Content-Type: application/json" \
        --header "Authorization: Bearer $STONEY_KEY" \
  -d '{
        --header 'Content-Type: application/json' \
    "model": "'"$MODEL_ID"'",
        --data '{
    "messages": [
                "model": "'"$MODEL"'",
      {"role": "user", "content": "'"$PROMPT"'"}
                "messages": [{
    ],
                        "role": "user",
    "max_tokens": '"$MAX_TOKENS"'
                        "content": [{
  }' \
                                "type": "image_url",
  | jq .
                                "image_url": {
                                        "url": "data:'"$FILE_MIME_TYPE"';base64,'"$FILE_CONTENT_BASE64"'"
                                }
                        }]
                }],
                "max_tokens": 4096,
                "temperature": 0.2,
                "top_p": 0.9
        }' \
        | jq
</syntaxhighlight>
</syntaxhighlight>


Line 29: Line 39:
<syntaxhighlight lang="json">
<syntaxhighlight lang="json">
{
{
   "id": "chatcmpl-8e804087bd0f6e64",
   "id": "chatcmpl-928cc308fa758fc8",
   "object": "chat.completion",
   "object": "chat.completion",
   "created": 1774862972,
   "created": 1778491655,
   "model": "MinerU2.5-2509-1.2B",
   "model": "MinerU2.5-2509-1.2B",
   "choices": [
   "choices": [
Line 38: Line 48:
       "message": {
       "message": {
         "role": "assistant",
         "role": "assistant",
         "content": "Describe an imaginary document.",
         "content": "This is a lot of 12 point text to test theOCR code and see if it works on all types of file format. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox.",
         "refusal": null,
         "refusal": null,
         "annotations": null,
         "annotations": null,
Line 56: Line 66:
   "system_fingerprint": null,
   "system_fingerprint": null,
   "usage": {
   "usage": {
     "prompt_tokens": 24,
     "prompt_tokens": 412,
     "total_tokens": 30,
     "total_tokens": 480,
     "completion_tokens": 6,
     "completion_tokens": 68,
     "prompt_tokens_details": null
     "prompt_tokens_details": null
   },
   },

Latest revision as of 11:28, 11 May 2026

Calling the model

# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=MinerU2.5-2509-1.2B

# Set the desired document to run OCR against:
FILE_PATH=document.png

# Encode document contents with Base64 and detect MIME type:
FILE_CONTENT_BASE64=$(base64 -w 0 < "$FILE_PATH")
FILE_MIME_TYPE=$(file --brief --mime-type "$FILE_PATH")

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": [{
                                "type": "image_url",
                                "image_url": {
                                        "url": "data:'"$FILE_MIME_TYPE"';base64,'"$FILE_CONTENT_BASE64"'"
                                }
                        }]
                }],
                "max_tokens": 4096,
                "temperature": 0.2,
                "top_p": 0.9
        }' \
        | jq

Example output:

{
  "id": "chatcmpl-928cc308fa758fc8",
  "object": "chat.completion",
  "created": 1778491655,
  "model": "MinerU2.5-2509-1.2B",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "This is a lot of 12 point text to test theOCR code and see if it works on all types of file format. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox.",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "function_call": null,
        "tool_calls": [],
        "reasoning": null,
        "reasoning_content": null
      },
      "logprobs": null,
      "finish_reason": "stop",
      "stop_reason": null,
      "token_ids": null
    }
  ],
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "prompt_tokens": 412,
    "total_tokens": 480,
    "completion_tokens": 68,
    "prompt_tokens_details": null
  },
  "prompt_logprobs": null,
  "prompt_token_ids": null,
  "kv_transfer_params": null
}