"Finetune not found" after uploading LoRA adapter via wrangler and REST API #23272
Description
Existing documentation URL(s)
https://developers.cloudflare.com/workers-ai/fine-tunes/loras/
#14757
What changes are you suggesting?
tl;dr
I'm encountering a near-identical problem as this prev Github issue closed (#14757)
Trying both a custom Gemma, Mistral adapter and the public Predibase LoRA demo. Here's the response I receive:
{"errors":[{"message":"AiError: AiError: Finetune 3dd75f75-0e0c-425b-b19e-6fbd2fb84cde not found (63371b53-4237-44f1-baec-b690284ac214)","code":3037}],"success":false,"result":{},"messages":[]}%
Here’s my adapter_config.json for reference:
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 8,
"rank_pattern": {},
"revision": null,
"target_modules": [
"q_proj",
"v_proj"
],
"task_type": "CAUSAL_LM",
"model_type": "mistral"
}
Also tried via both wrangler and REST API method listed in docs - with upload successfully created, but the finetune is not recognized at inference time. Any insight would be appreciated!
Additional information
No response