Instructions to use 3N3G/e3-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 3N3G/e3-sft with Transformers:

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

pipe = pipeline("text-generation", model="3N3G/e3-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("3N3G/e3-sft")
model = AutoModelForCausalLM.from_pretrained("3N3G/e3-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 3N3G/e3-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "3N3G/e3-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "3N3G/e3-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/3N3G/e3-sft

SGLang

How to use 3N3G/e3-sft 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 "3N3G/e3-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "3N3G/e3-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "3N3G/e3-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "3N3G/e3-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 3N3G/e3-sft with Docker Model Runner:
```
docker model run hf.co/3N3G/e3-sft
```

e3-sft

This model is a fine-tuned version of CMU-AIRe/e3-1.7B on the hardmath_sft_2 dataset. It achieves the following results on the evaluation set:

Loss: 0.6364

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-07
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_min_lr
lr_scheduler_warmup_ratio: 0.1
num_epochs: 100.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7025	4.0	16	0.7606
0.9105	8.0	32	0.7590
0.8193	12.0	48	0.7550
0.6939	16.0	64	0.7460
0.6623	20.0	80	0.7418
0.8112	24.0	96	0.7389
0.708	28.0	112	0.7154
0.6471	32.0	128	0.7097
0.9019	36.0	144	0.7050
0.7328	40.0	160	0.7007
0.8191	44.0	176	0.6938
0.6327	48.0	192	0.6752
0.6903	52.0	208	0.6604
0.7467	56.0	224	0.6533
0.7364	60.0	240	0.6489
0.7706	64.0	256	0.6460
0.7777	68.0	272	0.6441
0.6391	72.0	288	0.6419
0.648	76.0	304	0.6408
0.704	80.0	320	0.6398
0.6316	84.0	336	0.6387
0.6232	88.0	352	0.6380
0.6545	92.0	368	0.6372
0.7126	96.0	384	0.6364
0.6465	100.0	400	0.6364

Framework versions

Transformers 4.55.0
Pytorch 2.5.1
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 6

Safetensors

Model size

2B params

Tensor type

F32

Model tree for 3N3G/e3-sft

Base model

CMU-AIRe/e3-1.7B

Finetuned

(1)

this model