Instructions to use Yanjo/datamix-treatment-12l with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yanjo/datamix-treatment-12l with Transformers:

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

pipe = pipeline("text-generation", model="Yanjo/datamix-treatment-12l")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yanjo/datamix-treatment-12l")
model = AutoModelForCausalLM.from_pretrained("Yanjo/datamix-treatment-12l")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Yanjo/datamix-treatment-12l with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yanjo/datamix-treatment-12l"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yanjo/datamix-treatment-12l",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Yanjo/datamix-treatment-12l

SGLang

How to use Yanjo/datamix-treatment-12l 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 "Yanjo/datamix-treatment-12l" \
    --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": "Yanjo/datamix-treatment-12l",
		"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 "Yanjo/datamix-treatment-12l" \
        --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": "Yanjo/datamix-treatment-12l",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Yanjo/datamix-treatment-12l with Docker Model Runner:
```
docker model run hf.co/Yanjo/datamix-treatment-12l
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

datamix-treatment-12l

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

Loss: 6.6002

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: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
7.3611	0.1010	500	7.2894
7.1006	0.2020	1000	7.0496
6.8657	0.3030	1500	6.9105
6.9066	0.4040	2000	6.8204
6.7658	0.5051	2500	6.7608
6.8033	0.6061	3000	6.6947
6.6107	0.7071	3500	6.6542
6.6699	0.8081	4000	6.6237
6.6169	0.9091	4500	6.6002

Framework versions

Transformers 4.44.2
Pytorch 2.0.1
Datasets 3.0.0
Tokenizers 0.19.1

Downloads last month: 4

Safetensors

Model size

0.2B params

Tensor type

F32

Model tree for Yanjo/datamix-treatment-12l

Quantizations

2 models