Instructions to use TheNateTCY/fulltrain_optmodel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheNateTCY/fulltrain_optmodel with Transformers:

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

pipe = pipeline("text-generation", model="TheNateTCY/fulltrain_optmodel")

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

tokenizer = AutoTokenizer.from_pretrained("TheNateTCY/fulltrain_optmodel")
model = AutoModelForCausalLM.from_pretrained("TheNateTCY/fulltrain_optmodel", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheNateTCY/fulltrain_optmodel with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TheNateTCY/fulltrain_optmodel

SGLang

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

Docker Model Runner
How to use TheNateTCY/fulltrain_optmodel with Docker Model Runner:
```
docker model run hf.co/TheNateTCY/fulltrain_optmodel
```

fulltrain_optmodel / README.md

TheNateTCY

Training in progress epoch 0

04053aa almost 4 years ago

preview code

Raw History Blame Contribute Delete

1.65 kB

---
license: other
tags:
- generated_from_keras_callback
model-index:
- name: TheNateTCY/fulltrain_optmodel
  results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->

# TheNateTCY/fulltrain_optmodel
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.8560
- Validation Loss: 1.2171
- Epoch: 0
## 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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 8375, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 1.8560     | 1.2171          | 0     |
### Framework versions
- Transformers 4.25.1
- TensorFlow 2.10.1
- Datasets 2.7.1
- Tokenizers 0.13.2

	---
	license: other
	tags:
	- generated_from_keras_callback
	model-index:
	- name: TheNateTCY/fulltrain_optmodel
	results: []
	---

	<!-- This model card has been generated automatically according to the information Keras had access to. You should
	probably proofread and complete it, then remove this comment. -->

	# TheNateTCY/fulltrain_optmodel

	This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Train Loss: 1.8560
	- Validation Loss: 1.2171
	- Epoch: 0

	## 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:
	- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 8375, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
	- training_precision: float32

	### Training results

	\| Train Loss \| Validation Loss \| Epoch \|
	\|:----------:\|:---------------:\|:-----:\|
	\| 1.8560 \| 1.2171 \| 0 \|


	### Framework versions

	- Transformers 4.25.1
	- TensorFlow 2.10.1
	- Datasets 2.7.1
	- Tokenizers 0.13.2