Instructions to use AdnanRiaz107/CodeBert-finetuned-the-stack-bash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdnanRiaz107/CodeBert-finetuned-the-stack-bash with Transformers:

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

pipe = pipeline("text-generation", model="AdnanRiaz107/CodeBert-finetuned-the-stack-bash")

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

tokenizer = AutoTokenizer.from_pretrained("AdnanRiaz107/CodeBert-finetuned-the-stack-bash")
model = AutoModelForCausalLM.from_pretrained("AdnanRiaz107/CodeBert-finetuned-the-stack-bash", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AdnanRiaz107/CodeBert-finetuned-the-stack-bash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AdnanRiaz107/CodeBert-finetuned-the-stack-bash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdnanRiaz107/CodeBert-finetuned-the-stack-bash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AdnanRiaz107/CodeBert-finetuned-the-stack-bash

SGLang

How to use AdnanRiaz107/CodeBert-finetuned-the-stack-bash 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 "AdnanRiaz107/CodeBert-finetuned-the-stack-bash" \
    --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": "AdnanRiaz107/CodeBert-finetuned-the-stack-bash",
		"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 "AdnanRiaz107/CodeBert-finetuned-the-stack-bash" \
        --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": "AdnanRiaz107/CodeBert-finetuned-the-stack-bash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AdnanRiaz107/CodeBert-finetuned-the-stack-bash with Docker Model Runner:
```
docker model run hf.co/AdnanRiaz107/CodeBert-finetuned-the-stack-bash
```

CodeBert-finetuned-the-stack-bash / README.md

AdnanRiaz107

End of training

4e90b16 almost 3 years ago

preview code

Raw History Blame Contribute Delete

2.41 kB

---
base_model: microsoft/codebert-base
tags:
- generated_from_trainer
model-index:
- name: CodeBert-finetuned-the-stack-bash
  results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# CodeBert-finetuned-the-stack-bash

This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.6895

## 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 10000

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 8.1473        | 0.05  | 500   | 7.4270          |
| 6.9372        | 0.1   | 1000  | 6.9409          |
| 6.167         | 0.15  | 1500  | 6.6749          |
| 7.9745        | 0.2   | 2000  | 6.4053          |
| 7.2576        | 0.25  | 2500  | 6.2217          |
| 6.451         | 0.3   | 3000  | 6.0992          |
| 6.3218        | 0.35  | 3500  | 6.0231          |
| 6.3115        | 0.4   | 4000  | 6.0302          |
| 6.6343        | 0.45  | 4500  | 5.8745          |
| 6.1515        | 0.5   | 5000  | 5.8281          |
| 6.3992        | 0.55  | 5500  | 5.7614          |
| 6.8421        | 0.6   | 6000  | 5.8745          |
| 6.0542        | 0.65  | 6500  | 5.7452          |
| 5.3206        | 0.7   | 7000  | 5.7668          |
| 6.121         | 0.75  | 7500  | 5.6950          |
| 6.5956        | 0.8   | 8000  | 5.6926          |
| 5.8667        | 0.85  | 8500  | 5.6904          |
| 6.0287        | 0.9   | 9000  | 5.6803          |
| 5.8417        | 0.95  | 9500  | 5.6747          |
| 6.9719        | 1.0   | 10000 | 5.6895          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0

	---
	base_model: microsoft/codebert-base
	tags:
	- generated_from_trainer
	model-index:
	- name: CodeBert-finetuned-the-stack-bash
	results: []
	---

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

	# CodeBert-finetuned-the-stack-bash

	This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 5.6895

	## 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: 5e-05
	- train_batch_size: 1
	- eval_batch_size: 1
	- seed: 42
	- gradient_accumulation_steps: 4
	- total_train_batch_size: 4
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_steps: 100
	- training_steps: 10000

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:-----:\|:-----:\|:---------------:\|
	\| 8.1473 \| 0.05 \| 500 \| 7.4270 \|
	\| 6.9372 \| 0.1 \| 1000 \| 6.9409 \|
	\| 6.167 \| 0.15 \| 1500 \| 6.6749 \|
	\| 7.9745 \| 0.2 \| 2000 \| 6.4053 \|
	\| 7.2576 \| 0.25 \| 2500 \| 6.2217 \|
	\| 6.451 \| 0.3 \| 3000 \| 6.0992 \|
	\| 6.3218 \| 0.35 \| 3500 \| 6.0231 \|
	\| 6.3115 \| 0.4 \| 4000 \| 6.0302 \|
	\| 6.6343 \| 0.45 \| 4500 \| 5.8745 \|
	\| 6.1515 \| 0.5 \| 5000 \| 5.8281 \|
	\| 6.3992 \| 0.55 \| 5500 \| 5.7614 \|
	\| 6.8421 \| 0.6 \| 6000 \| 5.8745 \|
	\| 6.0542 \| 0.65 \| 6500 \| 5.7452 \|
	\| 5.3206 \| 0.7 \| 7000 \| 5.7668 \|
	\| 6.121 \| 0.75 \| 7500 \| 5.6950 \|
	\| 6.5956 \| 0.8 \| 8000 \| 5.6926 \|
	\| 5.8667 \| 0.85 \| 8500 \| 5.6904 \|
	\| 6.0287 \| 0.9 \| 9000 \| 5.6803 \|
	\| 5.8417 \| 0.95 \| 9500 \| 5.6747 \|
	\| 6.9719 \| 1.0 \| 10000 \| 5.6895 \|


	### Framework versions

	- Transformers 4.36.0.dev0
	- Pytorch 2.1.0+cu118
	- Datasets 2.15.0
	- Tokenizers 0.15.0