Instructions to use Heejindo/rationale_model_e15 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Heejindo/rationale_model_e15 with Transformers:

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

pipe = pipeline("text-generation", model="Heejindo/rationale_model_e15")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Heejindo/rationale_model_e15")
model = AutoModelForCausalLM.from_pretrained("Heejindo/rationale_model_e15")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Heejindo/rationale_model_e15 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Heejindo/rationale_model_e15"
# 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_e15",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Heejindo/rationale_model_e15

SGLang

How to use Heejindo/rationale_model_e15 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_e15" \
    --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_e15",
		"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_e15" \
        --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_e15",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Heejindo/rationale_model_e15 with Docker Model Runner:
```
docker model run hf.co/Heejindo/rationale_model_e15
```

rationale_model_e15

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: 2.1070

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 adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
2.1363	0.0954	500	2.1185
1.7868	0.1908	1000	2.1070
1.5132	0.2862	1500	2.1743
1.238	0.3815	2000	2.2694
0.9723	0.4769	2500	2.3214
0.7249	0.5723	3000	2.4423
0.5657	0.6677	3500	2.5636
0.4404	0.7631	4000	2.6851
0.3192	0.8585	4500	2.8630
0.2676	0.9538	5000	2.9741
0.2057	1.0492	5500	3.0958
0.1792	1.1446	6000	3.1219
0.1691	1.2400	6500	3.1735
0.1597	1.3354	7000	3.2299
0.1516	1.4308	7500	3.2997
0.1422	1.5261	8000	3.2759
0.1372	1.6215	8500	3.3557
0.1301	1.7169	9000	3.4023
0.1229	1.8123	9500	3.4617
0.1183	1.9077	10000	3.4668
0.1119	2.0031	10500	3.5609
0.0924	2.0984	11000	3.5975
0.0926	2.1938	11500	3.6429
0.089	2.2892	12000	3.6586
0.0881	2.3846	12500	3.6920
0.0861	2.4800	13000	3.7656
0.0835	2.5754	13500	3.7939
0.0803	2.6707	14000	3.8398
0.0797	2.7661	14500	3.8909
0.0774	2.8615	15000	3.9238
0.0759	2.9569	15500	3.9394

Framework versions

Transformers 4.46.3
Pytorch 2.3.0
Datasets 2.14.4
Tokenizers 0.20.3

Downloads last month: 2

Safetensors

Model size

1B params

Tensor type

F32

Model tree for Heejindo/rationale_model_e15

Base model

meta-llama/Llama-3.2-1B

Finetuned

(908)

this model