Instructions to use MikeMpapa/4_bar_lmd_clean_custom_test3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MikeMpapa/4_bar_lmd_clean_custom_test3 with Transformers:

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

pipe = pipeline("text-generation", model="MikeMpapa/4_bar_lmd_clean_custom_test3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MikeMpapa/4_bar_lmd_clean_custom_test3")
model = AutoModelForCausalLM.from_pretrained("MikeMpapa/4_bar_lmd_clean_custom_test3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MikeMpapa/4_bar_lmd_clean_custom_test3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MikeMpapa/4_bar_lmd_clean_custom_test3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MikeMpapa/4_bar_lmd_clean_custom_test3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MikeMpapa/4_bar_lmd_clean_custom_test3

SGLang

How to use MikeMpapa/4_bar_lmd_clean_custom_test3 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 "MikeMpapa/4_bar_lmd_clean_custom_test3" \
    --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": "MikeMpapa/4_bar_lmd_clean_custom_test3",
		"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 "MikeMpapa/4_bar_lmd_clean_custom_test3" \
        --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": "MikeMpapa/4_bar_lmd_clean_custom_test3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MikeMpapa/4_bar_lmd_clean_custom_test3 with Docker Model Runner:
```
docker model run hf.co/MikeMpapa/4_bar_lmd_clean_custom_test3
```

4_bar_lmd_clean_custom_test3

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 4.4912

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: 0.005
train_batch_size: 48
eval_batch_size: 32
seed: 1
gradient_accumulation_steps: 2
total_train_batch_size: 96
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
6.8709	1.82	10	5.7363
5.6849	3.64	20	5.4321
5.4501	5.45	30	5.3610
5.359	7.27	40	5.2833
5.278	9.09	50	5.1274
5.1335	10.91	60	5.0075
5.0548	12.73	70	4.9488
4.958	14.55	80	4.8213
4.8511	16.36	90	4.7643
4.8158	18.18	100	4.7202
4.7548	20.0	110	4.6591
4.7269	21.82	120	4.6380
4.6823	23.64	130	4.6200
4.6757	25.45	140	4.6081
4.629	27.27	150	4.6285
4.6398	29.09	160	4.6024
4.6111	30.91	170	4.6235
4.6028	32.73	180	4.5945
4.577	34.55	190	4.5932
4.5812	36.36	200	4.5689
4.5583	38.18	210	4.5713
4.5567	40.0	220	4.5731
4.55	41.82	230	4.5619
4.5338	43.64	240	4.5656
4.5245	45.45	250	4.5494
4.5143	47.27	260	4.5578
4.5339	49.09	270	4.5489
4.4948	50.91	280	4.5746
4.5	52.73	290	4.5407
4.4755	54.55	300	4.5448
4.4736	56.36	310	4.5311
4.4584	58.18	320	4.5279
4.465	60.0	330	4.5339
4.4511	61.82	340	4.5326
4.4408	63.64	350	4.5163
4.4314	65.45	360	4.5193
4.417	67.27	370	4.5161
4.424	69.09	380	4.5027
4.4147	70.91	390	4.5044
4.3938	72.73	400	4.5012
4.4001	74.55	410	4.5037
4.3821	76.36	420	4.5006
4.383	78.18	430	4.4981
4.3893	80.0	440	4.4942
4.3684	81.82	450	4.4927
4.3788	83.64	460	4.4933
4.3836	85.45	470	4.4929
4.3766	87.27	480	4.4917
4.3871	89.09	490	4.4912
4.3725	90.91	500	4.4912

Framework versions

Transformers 4.36.0
Pytorch 2.1.0
Datasets 2.15.0
Tokenizers 0.15.1

Downloads last month: 2

Safetensors

Model size

27.3M params

Tensor type

F32

Model tree for MikeMpapa/4_bar_lmd_clean_custom_test3

Base model

openai-community/gpt2

Finetuned

(2208)

this model