AIDC-AI

/

Ovis2-4B

like 41

Follow

AIDC-AI 414

Is there any way to convert Ovis to GGUF format?
I have tried to use llama.ccp by adding Ovis in the convert_hf_to_gguf_update.py script, and it seems to add it successfully.

(venv) J:\llama.cpp>python convert_hf_to_gguf_update.py [MY_HF_TOKEN]
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): huggingface.co:443
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /AIDC-AI/Ovis2-4B/resolve/main/config.json HTTP/1.1" 200 7176
INFO:convert_hf_to_gguf_update:File models/tokenizers/ovis2/config.json downloaded successfully
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /AIDC-AI/Ovis2-4B/resolve/main/tokenizer.json HTTP/1.1" 302 1179
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): cdn-lfs-us-1.hf.co:443
DEBUG:urllib3.connectionpool:https://cdn-lfs-us-1.hf.co:443 "GET /repos/3c/8e/3c8e885c4a8b5bf176bcfbc47e67b1fcd79e23dce3b282ecd062fa5d13c0516b/9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27tokenizer.json%3B+filename%3D%22tokenizer.json%22%3B&response-content-type=application%2Fjson&Expires=1740427710&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTc0MDQyNzcxMH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzNjLzhlLzNjOGU4ODVjNGE4YjViZjE3NmJjZmJjNDdlNjdiMWZjZDc5ZTIzZGNlM2IyODJlY2QwNjJmYTVkMTNjMDUxNmIvOWM1YWUwMGU2MDJiODg2MGNiZDc4NGJhODJhOGFhMTRlOGZlZWNlYzY5MmU3MDc2NTkwZDAxNGQ3YjdmZGFmYT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=CTwJTh-ImLIfR0giBDMUHfHO4sA4kej7KFF19WhI4DAjsjO~WO975TIb5aiBgZ8CJ4kumZbobxYk8rKGHXZrxOt7INvRW1KU7TggB6~0~Ozn4EBH571DyNuFDAohBwHAmMbGZ56npZ5ceNLEqOqcdX0tv0z7vF1q-8hWLSO-YqAdg-BOfQqyPCLOZ3jHlFHEphcMx~KwC8GAQtTMz7bBlWs0G-O302QoJm33l8Bh37sBjas9pP00Ie12j5YLR9Tn8BIroV5XVa4liLbds2prFYbvtmk7E7bkLCpf97n4YVvzO4gIEM2sIgCa61F8TRYJU7fjBQ5CozahUHjydgxugA__&Key-Pair-Id=K24J24Z295AEI9 HTTP/1.1" 200 11421896
INFO:convert_hf_to_gguf_update:File models/tokenizers/ovis2/tokenizer.json downloaded successfully
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /AIDC-AI/Ovis2-4B/resolve/main/tokenizer_config.json HTTP/1.1" 200 7306
INFO:convert_hf_to_gguf_update:File models/tokenizers/ovis2/tokenizer_config.json downloaded successfully
INFO:convert_hf_to_gguf_update:model: ovis2
INFO:convert_hf_to_gguf_update:tokt: 2
INFO:convert_hf_to_gguf_update:repo: https://huggingface.co/AIDC-AI/Ovis2-4B
INFO:convert_hf_to_gguf_update:chktok: [198, 4710, 14731, 65497, 7847, 1572, 2303, 78672, 10947, 145836, 320, 8252, 8, 26525, 114, 378, 235, 149921, 30543, 320, 35673, 99066, 97534, 8, 25521, 227, 11162, 99, 247, 149955, 220, 18, 220, 18, 18, 220, 18, 18, 18, 220, 18, 18, 18, 18, 220, 18, 18, 18, 18, 18, 220, 18, 18, 18, 18, 18, 18, 220, 18, 18, 18, 18, 18, 18, 18, 220, 18, 18, 18, 18, 18, 18, 18, 18, 220, 18, 13, 18, 220, 18, 496, 18, 220, 18, 1112, 18, 220, 146394, 97529, 241, 44258, 233, 146568, 44258, 224, 147603, 20879, 115, 146280, 44258, 223, 146280, 147272, 97529, 227, 144534, 937, 104100, 18493, 22377, 99257, 16, 18, 16, 19, 16, 20, 16, 35727, 21216, 55460, 53237, 18658, 14144, 1456, 13073, 63471, 33594, 3038, 133178, 79012, 3355, 4605, 4605, 13874, 13874, 73594, 3014, 3014, 28149, 17085, 2928, 26610, 7646, 358, 3003, 1012, 364, 83, 813, 566, 594, 1052, 11, 364, 787, 498, 2704, 30, 364, 44, 537, 2704, 358, 3278, 1281, 432, 11, 364, 35, 498, 1075, 1045, 15243, 30, 1205, 6, 42612, 264, 63866, 43]
INFO:convert_hf_to_gguf_update:chkhsh: e636dc30a262dcc0d8c323492e32ae2b70728f4df7dfe9737d9f920a282b8aea
INFO:convert_hf_to_gguf_update:normalizer: {
    "type": "NFC"
}
INFO:convert_hf_to_gguf_update:pre_tokenizer: {
    "type": "Sequence",
    "pretokenizers": [
        {
            "type": "Split",
            "pattern": {
                "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
            },
            "behavior": "Isolated",
            "invert": false
        },
        {
            "type": "ByteLevel",
            "add_prefix_space": false,
            "trim_offsets": false,
            "use_regex": false
        }
    ]
}
INFO:convert_hf_to_gguf_update:ignore_merges: false
INFO:convert_hf_to_gguf_update:
INFO:convert_hf_to_gguf_update:+++ convert_hf_to_gguf.py was updated
INFO:convert_hf_to_gguf_update:Tests for ovis2 written in ./models/ggml-vocab-ovis2.gguf.*
INFO:convert_hf_to_gguf_update:
Run the following commands to generate the vocab files for testing:

python3 convert_hf_to_gguf.py models/tokenizers/ovis2/ --outfile models/ggml-vocab-ovis2.gguf --vocab-only
INFO:convert_hf_to_gguf_update:

but then when I run the convert_hf_to_gguf.py script I get the following error:

INFO:hf-to-gguf:Loading model: ovis2
ERROR:hf-to-gguf:Model Ovis is not supported

This is how Ovis was added to the update script: