# How to deploy models trained here

**URL:** <https://discuss.huggingface.co/t/how-to-deploy-models-trained-here/55123>\
**Category:** Beginners\
**Created:** [September 15, 2023, 10:03am UTC](https://discuss.huggingface.co/t/how-to-deploy-models-trained-here/55123 "2023-09-15T10:03:30Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![BadDotNetDev](https://avatars.discourse-cdn.com/v4/letter/b/e0b2c6/32.png) [@BadDotNetDev](https://discuss.huggingface.co/u/BadDotNetDev)\
**Post date:** [September 15, 2023, 10:03am UTC](https://discuss.huggingface.co/t/how-to-deploy-models-trained-here/55123/1 "2023-09-15T10:03:30Z")

</div>

So i fine tuned the falcon 7b for my specific use case, how can i now use the model locally, i have the following:

Config directory - contains only some config.json  
Model directory - contains config.json and adapter\_model.bin  
Tokenizer directory - Contains special\_tokens\_map.json, tokenizer\_config.json and tokenizer.json

I tried to load the model locally with this code:  
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Load the tokenizer and model

tokenizer = AutoTokenizer.from\_pretrained(r"C:\Users\josip\git\AII\tokenizer")

model = AutoModelForSequenceClassification.from\_pretrained(r"C:\Users\josip\git\AII\model")

text = “Tell me something about linux”

inputs = tokenizer(text, return\_tensors=“pt”, padding=True, truncation=True)

outputs = model(\*\*inputs)

predictions = outputs.logits.argmax(1)

print(predictions);

but i got this error:  
Traceback (most recent call last):  
File “C:\Users\josip\git\AII\model.py”, line 5, in   
model = AutoModelForSequenceClassification.from\_pretrained(r"C:\Users\josip\git\AII\model")  
File “C:\Users\josip\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\auto\auto\_factory.py”, line 566, in from\_pretrained  
raise ValueError(  
ValueError: Unrecognized configuration class \<class ‘transformers.models.git.configuration\_git.GitConfig’\> for this kind of AutoModel: AutoModelForSequenceClassification.  
Model type should be one of AlbertConfig, BartConfig, BertConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BloomConfig, CamembertConfig, CanineConfig, LlamaConfig, ConvBertConfig, CTRLConfig, Data2VecTextConfig, DebertaConfig,  
DebertaV2Config, DistilBertConfig, ElectraConfig, ErnieConfig, ErnieMConfig, EsmConfig, FalconConfig, FlaubertConfig, FNetConfig, FunnelConfig, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTJConfig, IBertConfig, LayoutLMConfig, LayoutLMv2Config, LayoutLMv3Config, LEDConfig, LiltConfig, LlamaConfig, LongformerConfig, LukeConfig, MarkupLMConfig, MBartConfig, MegaConfig, MegatronBertConfig, MobileBertConfig, MPNetConfig, MptConfig, MraConfig, MT5Config, MvpConfig, NezhaConfig, NystromformerConfig, OpenLlamaConfig, OpenAIGPTConfig, OPTConfig, PerceiverConfig, PLBartConfig, QDQBertConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, SqueezeBertConfig, T5Config, TapasConfig, TransfoXLConfig, UMT5Config, XLMConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, XmodConfig, YosoConfig.