Instructions to use DedeProGames/mini-chennus-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DedeProGames/mini-chennus-2 with Transformers:

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

pipe = pipeline("text-generation", model="DedeProGames/mini-chennus-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DedeProGames/mini-chennus-2")
model = AutoModelForCausalLM.from_pretrained("DedeProGames/mini-chennus-2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DedeProGames/mini-chennus-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DedeProGames/mini-chennus-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/mini-chennus-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DedeProGames/mini-chennus-2

SGLang

How to use DedeProGames/mini-chennus-2 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 "DedeProGames/mini-chennus-2" \
    --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": "DedeProGames/mini-chennus-2",
		"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 "DedeProGames/mini-chennus-2" \
        --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": "DedeProGames/mini-chennus-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DedeProGames/mini-chennus-2 with Docker Model Runner:
```
docker model run hf.co/DedeProGames/mini-chennus-2
```

mini-chennus-2 / README.md

DedeProGames

Update README.md

13afcf8 verified 2 months ago

preview code

raw

history blame contribute delete

3.76 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: EleutherAI/pythia-14m-deduped
	tags:
	- generated_from_trainer
	metrics:
	- accuracy
	model-index:
	- name: chennus-mini-2
	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. -->

	# mini-chennus-2

	This model is a fine-tuned version of [EleutherAI/pythia-14m-deduped](https://huggingface.co/EleutherAI/pythia-14m-deduped) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: nan
	- Accuracy: 0.0

	## 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:
	- learning_rate: 5e-05
	- train_batch_size: 8
	- eval_batch_size: 8
	- seed: 42
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- num_epochs: 6

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|:--------:\|
	\| 0.0 \| 0.1616 \| 200 \| nan \| 0.0 \|
	\| 0.0 \| 0.3231 \| 400 \| nan \| 0.0 \|
	\| 0.0 \| 0.4847 \| 600 \| nan \| 0.0 \|
	\| 0.0 \| 0.6462 \| 800 \| nan \| 0.0 \|
	\| 0.0 \| 0.8078 \| 1000 \| nan \| 0.0 \|
	\| 0.0 \| 0.9693 \| 1200 \| nan \| 0.0 \|
	\| 0.0 \| 1.1309 \| 1400 \| nan \| 0.0 \|
	\| 0.0 \| 1.2924 \| 1600 \| nan \| 0.0 \|
	\| 0.0 \| 1.4540 \| 1800 \| nan \| 0.0 \|
	\| 0.0 \| 1.6155 \| 2000 \| nan \| 0.0 \|
	\| 0.0 \| 1.7771 \| 2200 \| nan \| 0.0 \|
	\| 0.0 \| 1.9386 \| 2400 \| nan \| 0.0 \|
	\| 0.0 \| 2.1002 \| 2600 \| nan \| 0.0 \|
	\| 0.0 \| 2.2617 \| 2800 \| nan \| 0.0 \|
	\| 0.0 \| 2.4233 \| 3000 \| nan \| 0.0 \|
	\| 0.0 \| 2.5848 \| 3200 \| nan \| 0.0 \|
	\| 0.0 \| 2.7464 \| 3400 \| nan \| 0.0 \|
	\| 0.0 \| 2.9079 \| 3600 \| nan \| 0.0 \|
	\| 0.0 \| 3.0695 \| 3800 \| nan \| 0.0 \|
	\| 0.0 \| 3.2310 \| 4000 \| nan \| 0.0 \|
	\| 0.0 \| 3.3926 \| 4200 \| nan \| 0.0 \|
	\| 0.0 \| 3.5541 \| 4400 \| nan \| 0.0 \|
	\| 0.0 \| 3.7157 \| 4600 \| nan \| 0.0 \|
	\| 0.0 \| 3.8772 \| 4800 \| nan \| 0.0 \|
	\| 0.0 \| 4.0388 \| 5000 \| nan \| 0.0 \|
	\| 0.0 \| 4.2003 \| 5200 \| nan \| 0.0 \|
	\| 0.0 \| 4.3619 \| 5400 \| nan \| 0.0 \|
	\| 0.0 \| 4.5234 \| 5600 \| nan \| 0.0 \|
	\| 0.0 \| 4.6850 \| 5800 \| nan \| 0.0 \|
	\| 0.0 \| 4.8465 \| 6000 \| nan \| 0.0 \|
	\| 0.0 \| 5.0081 \| 6200 \| nan \| 0.0 \|
	\| 0.0 \| 5.1696 \| 6400 \| nan \| 0.0 \|
	\| 0.0 \| 5.3312 \| 6600 \| nan \| 0.0 \|
	\| 0.0 \| 5.4927 \| 6800 \| nan \| 0.0 \|
	\| 0.0 \| 5.6543 \| 7000 \| nan \| 0.0 \|
	\| 0.0 \| 5.8158 \| 7200 \| nan \| 0.0 \|
	\| 0.0 \| 5.9774 \| 7400 \| nan \| 0.0 \|


	### Framework versions

	- Transformers 5.0.0
	- Pytorch 2.10.0+cu128
	- Datasets 4.0.0
	- Tokenizers 0.22.2