Instructions to use Heejindo/rationale_model_e3_save5000_f4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Heejindo/rationale_model_e3_save5000_f4 with Transformers:

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

pipe = pipeline("text-generation", model="Heejindo/rationale_model_e3_save5000_f4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Heejindo/rationale_model_e3_save5000_f4")
model = AutoModelForCausalLM.from_pretrained("Heejindo/rationale_model_e3_save5000_f4")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Heejindo/rationale_model_e3_save5000_f4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Heejindo/rationale_model_e3_save5000_f4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heejindo/rationale_model_e3_save5000_f4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Heejindo/rationale_model_e3_save5000_f4

SGLang

How to use Heejindo/rationale_model_e3_save5000_f4 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 "Heejindo/rationale_model_e3_save5000_f4" \
    --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": "Heejindo/rationale_model_e3_save5000_f4",
		"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 "Heejindo/rationale_model_e3_save5000_f4" \
        --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": "Heejindo/rationale_model_e3_save5000_f4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Heejindo/rationale_model_e3_save5000_f4 with Docker Model Runner:
```
docker model run hf.co/Heejindo/rationale_model_e3_save5000_f4
```

rationale_model_e3_save5000_f4

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.9369

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: 1e-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

Training results

Training Loss	Epoch	Step	Validation Loss
1.7536	0.1907	1000	1.9369
1.3797	0.3813	2000	2.0320
1.0216	0.5720	3000	2.1529
0.6624	0.7626	4000	2.3760
0.3893	0.9533	5000	2.7429
0.1995	1.1439	6000	2.9766
0.1703	1.3346	7000	3.0843
0.1489	1.5253	8000	3.1774
0.1249	1.7159	9000	3.3298
0.1168	1.9066	10000	3.4572
0.0977	2.0972	11000	3.5885
0.0951	2.2879	12000	3.6941
0.092	2.4786	13000	3.7847
0.0894	2.6692	14000	3.9039
0.086	2.8599	15000	3.9903

Framework versions

Transformers 4.45.0
Pytorch 2.3.0
Datasets 2.14.4
Tokenizers 0.20.3

Downloads last month: 3

Safetensors

Model size

1B params

Tensor type

F32

Model tree for Heejindo/rationale_model_e3_save5000_f4

Base model

meta-llama/Llama-3.2-1B

Finetuned

(908)

this model