Instructions to use craa/exceptions_exp2_swap_0.3_last_to_drop_40817 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use craa/exceptions_exp2_swap_0.3_last_to_drop_40817 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="craa/exceptions_exp2_swap_0.3_last_to_drop_40817")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("craa/exceptions_exp2_swap_0.3_last_to_drop_40817")
model = AutoModelForCausalLM.from_pretrained("craa/exceptions_exp2_swap_0.3_last_to_drop_40817", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use craa/exceptions_exp2_swap_0.3_last_to_drop_40817 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "craa/exceptions_exp2_swap_0.3_last_to_drop_40817"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "craa/exceptions_exp2_swap_0.3_last_to_drop_40817",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/craa/exceptions_exp2_swap_0.3_last_to_drop_40817

SGLang

How to use craa/exceptions_exp2_swap_0.3_last_to_drop_40817 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "craa/exceptions_exp2_swap_0.3_last_to_drop_40817" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "craa/exceptions_exp2_swap_0.3_last_to_drop_40817",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "craa/exceptions_exp2_swap_0.3_last_to_drop_40817" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "craa/exceptions_exp2_swap_0.3_last_to_drop_40817",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use craa/exceptions_exp2_swap_0.3_last_to_drop_40817 with Docker Model Runner:
```
docker model run hf.co/craa/exceptions_exp2_swap_0.3_last_to_drop_40817
```

exceptions_exp2_swap_0.3_last_to_drop_40817

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.5678
Accuracy: 0.3684

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0006
train_batch_size: 16
eval_batch_size: 16
seed: 40817
gradient_accumulation_steps: 5
total_train_batch_size: 80
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 50.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.8289	0.2915	1000	4.7681	0.2530
4.3459	0.5830	2000	4.2902	0.2986
4.1533	0.8745	3000	4.1042	0.3142
3.9994	1.1659	4000	4.0041	0.3235
3.9458	1.4574	5000	3.9249	0.3300
3.9017	1.7488	6000	3.8669	0.3357
3.7609	2.0402	7000	3.8242	0.3401
3.7621	2.3317	8000	3.7923	0.3431
3.7635	2.6232	9000	3.7652	0.3456
3.7326	2.9147	10000	3.7371	0.3484
3.6462	3.2061	11000	3.7242	0.3503
3.6613	3.4976	12000	3.7090	0.3519
3.6538	3.7891	13000	3.6884	0.3540
3.5588	4.0805	14000	3.6824	0.3547
3.6013	4.3719	15000	3.6706	0.3558
3.5855	4.6634	16000	3.6573	0.3567
3.5977	4.9549	17000	3.6431	0.3584
3.5171	5.2463	18000	3.6458	0.3588
3.5245	5.5378	19000	3.6333	0.3596
3.5389	5.8293	20000	3.6240	0.3604
3.4536	6.1207	21000	3.6288	0.3608
3.4858	6.4122	22000	3.6211	0.3616
3.497	6.7037	23000	3.6087	0.3624
3.5044	6.9952	24000	3.5998	0.3631
3.4306	7.2865	25000	3.6104	0.3634
3.455	7.5780	26000	3.5997	0.3641
3.466	7.8695	27000	3.5896	0.3646
3.3832	8.1609	28000	3.5999	0.3645
3.4281	8.4524	29000	3.5926	0.3649
3.4374	8.7439	30000	3.5849	0.3656
3.3393	9.0353	31000	3.5889	0.3655
3.3868	9.3268	32000	3.5871	0.3661
3.4096	9.6183	33000	3.5812	0.3664
3.4232	9.9098	34000	3.5709	0.3670
3.3558	10.2011	35000	3.5849	0.3667
3.3822	10.4926	36000	3.5760	0.3672
3.3904	10.7841	37000	3.5686	0.3679
3.3149	11.0755	38000	3.5773	0.3678
3.3528	11.3670	39000	3.5727	0.3680
3.3584	11.6585	40000	3.5678	0.3684
3.3889	11.9500	41000	3.5576	0.3691
3.3032	12.2414	42000	3.5727	0.3685
3.3375	12.5329	43000	3.5674	0.3688
3.3663	12.8243	44000	3.5583	0.3696
3.2764	13.1157	45000	3.5738	0.3688
3.322	13.4072	46000	3.5673	0.3694
3.3434	13.6987	47000	3.5593	0.3696
3.3469	13.9902	48000	3.5515	0.3704
3.2903	14.2816	49000	3.5656	0.3696
3.3158	14.5731	50000	3.5593	0.3702
3.3283	14.8646	51000	3.5513	0.3707
3.2427	15.1559	52000	3.5663	0.3700
3.2774	15.4474	53000	3.5601	0.3704
3.3089	15.7389	54000	3.5547	0.3707
3.2189	16.0303	55000	3.5624	0.3704
3.2783	16.3218	56000	3.5618	0.3707
3.2849	16.6133	57000	3.5524	0.3711
3.306	16.9048	58000	3.5462	0.3713
3.2308	17.1962	59000	3.5605	0.3707
3.255	17.4877	60000	3.5595	0.3709
3.2922	17.7792	61000	3.5478	0.3718
3.2152	18.0705	62000	3.5608	0.3709
3.2411	18.3620	63000	3.5558	0.3714
3.2605	18.6535	64000	3.5531	0.3717
3.2802	18.9450	65000	3.5414	0.3722
3.2072	19.2364	66000	3.5636	0.3713
3.2536	19.5279	67000	3.5526	0.3718
3.2671	19.8194	68000	3.5456	0.3721
3.1897	20.1108	69000	3.5613	0.3716
3.2141	20.4023	70000	3.5561	0.3715
3.2671	20.6938	71000	3.5469	0.3724
3.2552	20.9853	72000	3.5446	0.3726
3.209	21.2766	73000	3.5609	0.3719
3.235	21.5681	74000	3.5493	0.3725
3.25	21.8596	75000	3.5425	0.3730
3.1737	22.1510	76000	3.5614	0.3722
3.2054	22.4425	77000	3.5519	0.3725
3.245	22.7340	78000	3.5471	0.3727
3.136	23.0254	79000	3.5589	0.3723
3.1843	23.3169	80000	3.5529	0.3726
3.219	23.6083	81000	3.5493	0.3726
3.2168	23.8998	82000	3.5415	0.3732
3.1599	24.1912	83000	3.5613	0.3722
3.1827	24.4827	84000	3.5522	0.3732
3.2161	24.7742	85000	3.5460	0.3734

Framework versions

Transformers 4.55.2
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 8

Safetensors

Model size

0.1B params

Tensor type

F32