Instructions to use Gan1108/electraForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gan1108/electraForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="Gan1108/electraForCausalLM")

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

tokenizer = AutoTokenizer.from_pretrained("Gan1108/electraForCausalLM")
model = AutoModelForCausalLM.from_pretrained("Gan1108/electraForCausalLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gan1108/electraForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gan1108/electraForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gan1108/electraForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Gan1108/electraForCausalLM

SGLang

How to use Gan1108/electraForCausalLM 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 "Gan1108/electraForCausalLM" \
    --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": "Gan1108/electraForCausalLM",
		"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 "Gan1108/electraForCausalLM" \
        --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": "Gan1108/electraForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gan1108/electraForCausalLM with Docker Model Runner:
```
docker model run hf.co/Gan1108/electraForCausalLM
```

electraForCausalLM / README.md

Gan1108

Update README.md

ad1eae2 verified over 2 years ago

preview code

Raw History Blame Contribute Delete

1.41 kB

---
license: mit
base_model: lang-uk/electra-base-ukrainian-cased-generator
tags:
- generated_from_trainer
model-index:
- name: electraForCausalLM
  results: []
language:
- uk
widget:
- text: "0007347852 - 734785.0 - Підшипник кульковий закритий спеціальний "
---
# electraForCausalLM

This model is a fine-tuned version of [lang-uk/electra-base-ukrainian-cased-generator](https://huggingface.co/lang-uk/electra-base-ukrainian-cased-generator) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3302

## Model description

The model is trained to generate a text description in Ukrainian of spare parts for agricultural machinery based on their name.


## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7321        | 1.0   | 2354 | 1.5172          |
| 1.4763        | 2.0   | 4708 | 1.3670          |
| 1.4006        | 3.0   | 7062 | 1.3302          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2

	---
	license: mit
	base_model: lang-uk/electra-base-ukrainian-cased-generator
	tags:
	- generated_from_trainer
	model-index:
	- name: electraForCausalLM
	results: []
	language:
	- uk
	widget:
	- text: "0007347852 - 734785.0 - Підшипник кульковий закритий спеціальний "
	---

	# electraForCausalLM

	This model is a fine-tuned version of [lang-uk/electra-base-ukrainian-cased-generator](https://huggingface.co/lang-uk/electra-base-ukrainian-cased-generator) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 1.3302

	## Model description

	The model is trained to generate a text description in Ukrainian of spare parts for agricultural machinery based on their name.


	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 2e-05
	- train_batch_size: 8
	- eval_batch_size: 8
	- seed: 42
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: linear
	- num_epochs: 3.0

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:-----:\|:----:\|:---------------:\|
	\| 1.7321 \| 1.0 \| 2354 \| 1.5172 \|
	\| 1.4763 \| 2.0 \| 4708 \| 1.3670 \|
	\| 1.4006 \| 3.0 \| 7062 \| 1.3302 \|


	### Framework versions

	- Transformers 4.38.2
	- Pytorch 2.2.1+cu121
	- Datasets 2.18.0
	- Tokenizers 0.15.2