Fix missing model name in tokenize requests for llama.cpp (fixes #4962) (#5344) * Fix missing model name in tokenize requests for llama.cpp (fixes #4962) The new router mode of llama.cpp allows to switch models on the fly, what is already supported by SillyTavern. The call to the `/tokenize` endpoint did not contain the model name, and failed in router mode. This patch adds the `model` parameter similar to the implementation for other backends. * fix: migrate vllm and aphrodite to new payload field --------- Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>

d306194c5171a6885ec1cb615ab266c89d054f56

allo- <allo@laxu.de>

Signed

public/scripts/tokenizers.js+1 -2 Viewed

         text: str,
         api_type: textgen_settings.type,
         url: getTextGenServer(),
         vllm_modelmodel: textgen_settings.vllm_modelgetTextGenModel(),
 -        aphrodite_model: textgen_settings.aphrodite_model,
     };
+}

src/endpoints/tokenizers.js+4 -5 Viewed

+    }
     const text = String(request.body.text) || '';
     const baseUrl = String(request.body.url);
     const vllmModelmodel = String(request.body.vllm_modelmodel) || '';
 -    const aphroditeModel = String(request.body.aphrodite_model) || '';
     try {
         const args = {

                 break;
             case TEXTGEN_TYPES.LLAMACPP:
                 url += '/tokenize';
                 args.body = JSON.stringify({ 'model': model, 'content': text });
                 break;
             case TEXTGEN_TYPES.VLLM:
                 url += '/tokenize';
                 args.body = JSON.stringify({ 'model': vllmModelmodel, 'prompt': text });
                 break;
             case TEXTGEN_TYPES.APHRODITE:
                 url += '/v1/tokenize';
                 args.body = JSON.stringify({ 'model': aphroditeModelmodel, 'prompt': text });
                 break;
             default:
                 url += '/v1/internal/encode';