Skip to main content
Glama

import_model

Transfer models from S3 to Tuning Engines cloud storage for use as base models in fine-tuning jobs.

Instructions

Import a model from S3 into Tuning Engines cloud storage so it can be used as a base for future fine-tuning jobs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesName for the imported model
source_s3_urlYesS3 URL of the model to import (e.g. s3://bucket/path/to/model)
base_modelYesHuggingFace model ID that this model was fine-tuned from
s3_access_key_idYesAWS access key ID
s3_secret_access_keyYesAWS secret access key
s3_regionYesAWS region (e.g. us-east-1)

Implementation Reference

  • src/mcp.ts:308-329 (registration)
    The 'import_model' tool is defined here in the tools list for the MCP server.
      name: "import_model",
      description:
        "Import a model from S3 into Tuning Engines cloud storage so it can be used as a base for future fine-tuning jobs.",
      inputSchema: {
        type: "object" as const,
        properties: {
          name: { type: "string", description: "Name for the imported model" },
          source_s3_url: {
            type: "string",
            description: "S3 URL of the model to import (e.g. s3://bucket/path/to/model)",
          },
          base_model: {
            type: "string",
            description: "HuggingFace model ID that this model was fine-tuned from",
          },
          s3_access_key_id: { type: "string", description: "AWS access key ID" },
          s3_secret_access_key: { type: "string", description: "AWS secret access key" },
          s3_region: { type: "string", description: "AWS region (e.g. us-east-1)" },
        },
        required: ["name", "source_s3_url", "base_model", "s3_access_key_id", "s3_secret_access_key", "s3_region"],
      },
    },
  • The MCP request handler for 'import_model' calls the client's importModel method.
    case "import_model":
      result = await client.importModel({
        name: args!.name as string,
        source_s3_url: args!.source_s3_url as string,
        base_model: args!.base_model as string,
        s3_access_key_id: args!.s3_access_key_id as string,
        s3_secret_access_key: args!.s3_secret_access_key as string,
        s3_region: args!.s3_region as string,
      });
      break;
  • The 'importModel' method in the TuningEnginesClient, which executes the API request for importing a model.
    async importModel(params: {
      name: string;
      source_s3_url: string;
      base_model: string;
      s3_access_key_id: string;
      s3_secret_access_key: string;
      s3_region: string;
    }): Promise<any> {
      return this.request("POST", "/api/v1/user_models/import", params);
    }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cerebrixos-org/tuning-engines-cli'

If you have feedback or need assistance with the MCP directory API, please join our Discord server