bug: tinyllama - loading non existent model file: mmproj.gguf

[sefgit]

Cortex version

v1.0.12

Describe the issue and expected behaviour

cortex tries to load non existent file: /tinyllama/1b/mmproj.gguf

`
0250603 05:47:37.925506 UTC 93693 DEBUG [ReadYamlFile] mmproj: /home/user/cortexcpp/models/cortex.so/tinyllama/1b/mmproj.gguf - yaml_config.cc:51
20250603 05:47:37.996366 UTC 93693 ERROR HTTP request failed with status code: 400 - curl_utils.cc:170
20250603 05:47:37.996404 UTC 93693 ERROR Failed to get JSON from http://127.0.0.1:39281/v1/models/status/tinyllama:1b: {"message":"Engine is not loaded yet"} - curl_utils.cc:265
20250603 05:47:37.996445 UTC 93693 WARN Engine is not loaded yet - model_status_cmd.cc:28
20250603 05:47:39.879004 UTC 93693 ERROR CURL request failed: Server returned nothing (no headers, no data) - curl_utils.cc:232
20250603 05:47:39.879070 UTC 93693 INFO url: http://127.0.0.1:39281/v1/models/start - curl_utils.cc:322
20250603 05:47:39.879082 UTC 93693 INFO body: {
"model" : "tinyllama:1b"
}

• curl_utils.cc:323
  20250603 05:47:39.879093 UTC 93693 ERROR Failed to get JSON from http://127.0.0.1:39281/v1/models/start: CURL request failed: Server returned nothing (no headers, no data) - curl_utils.cc:324
  20250603 05:47:39.879168 UTC 93693 INFO - model_start_cmd.cc:67
  20250603 05:47:39.879207 UTC 93693 INFO Error: Failed to start model - run_cmd.cc:133
  20250603 05:47:39.884693 UTC 93719 INFO Will not check for new update, return the cache latest: v1.0.12 - cortex_upd_cmd.cc:149
  `

Steps to Reproduce

Under Linux:

install cortex
cortex start
cortex run tinyllama:1b

Screenshots / Logs

`
ser@dev:~/cortexcpp/models/cortex.so/tinyllama/1b$ ls -l
total 763732
-rw-rw-r-- 1 user user 58 Jun 3 12:38 metadata.yml
-rw-rw-r-- 1 user user 782045248 Jun 3 12:38 model.gguf
-rw-rw-r-- 1 user user 1419 Jun 3 12:46 model.yml

`

What is your OS?

• Windows
• Mac Silicon
• Mac Intel
• Linux / Ubuntu

What engine are you running?

• cortex.llamacpp (default)
• cortex.tensorrt-llm (Nvidia GPUs)
• cortex.onnx (NPUs, DirectML)

Hardware Specs eg OS version, GPU

Intel(R) Xeon(R) CPU E5-2640 0 @ 2.50GHz Linux Mint 22.1 NVIDIA GeForce GT 1030

[sefgit]

side note:
I'm absolute beginner in using this cortex.cpp, I might have missed a step or two to get it running.
Trying to compare cortex.cpp with ollama and llamafile, which I've managed to get them running on my modest hardware.