Xenova

/

nanoLLaVA

like 12

Applied Quantizations

❌ Based on embed_tokens.onnx with slimming

None

↳ ❌ q4f16: embed_tokens_q4f16.onnx (added but JS-based E2E test failed)

file:///home/ubuntu/src/tjsmigration/node_modules/.pnpm/@huggingface+transformers@3.5.2/node_modules/@huggingface/transformers/dist/transformers.node.mjs:23781
        throw Error(`Unsupported pipeline: ${task}. Must be one of [${Object.keys(SUPPORTED_TASKS)}]`)
              ^

Error: Unsupported pipeline: image-text-to-text. Must be one of [text-classification,token-classification,question-answering,fill-mask,summarization,translation,text2text-generation,text-generation,zero-shot-classification,audio-classification,zero-shot-audio-classification,automatic-speech-recognition,text-to-audio,image-to-text,image-classification,image-segmentation,background-removal,zero-shot-image-classification,object-detection,zero-shot-object-detection,document-question-answering,image-to-image,depth-estimation,feature-extraction,image-feature-extraction]
    at pipeline (file:///home/ubuntu/src/tjsmigration/node_modules/.pnpm/@huggingface+transformers@3.5.2/node_modules/@huggingface/transformers/dist/transformers.node.mjs:23781:15)
    at file:///home/ubuntu/src/tjsmigration/src/[eval1]:8:21
    at ModuleJob.run (node:internal/modules/esm/module_job:274:25)
    at async onImport.tracePromise.__proto__ (node:internal/modules/esm/loader:268:26)
    at async ModuleLoader.executeModuleJob (node:internal/modules/esm/loader:264:20)
    at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:117:5)

Node.js v22.16.0

❌ Based on vision_encoder.onnx with slimming

None

↳ ❌ q4f16: vision_encoder_q4f16.onnx (added but JS-based E2E test failed)

file:///home/ubuntu/src/tjsmigration/node_modules/.pnpm/@huggingface+transformers@3.5.2/node_modules/@huggingface/transformers/dist/transformers.node.mjs:23781
        throw Error(`Unsupported pipeline: ${task}. Must be one of [${Object.keys(SUPPORTED_TASKS)}]`)
              ^

Error: Unsupported pipeline: image-text-to-text. Must be one of [text-classification,token-classification,question-answering,fill-mask,summarization,translation,text2text-generation,text-generation,zero-shot-classification,audio-classification,zero-shot-audio-classification,automatic-speech-recognition,text-to-audio,image-to-text,image-classification,image-segmentation,background-removal,zero-shot-image-classification,object-detection,zero-shot-object-detection,document-question-answering,image-to-image,depth-estimation,feature-extraction,image-feature-extraction]
    at pipeline (file:///home/ubuntu/src/tjsmigration/node_modules/.pnpm/@huggingface+transformers@3.5.2/node_modules/@huggingface/transformers/dist/transformers.node.mjs:23781:15)
    at file:///home/ubuntu/src/tjsmigration/src/[eval1]:8:21
    at ModuleJob.run (node:internal/modules/esm/module_job:274:25)
    at async onImport.tracePromise.__proto__ (node:internal/modules/esm/loader:268:26)
    at async ModuleLoader.executeModuleJob (node:internal/modules/esm/loader:264:20)
    at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:117:5)

Node.js v22.16.0