Instructions to use carlesoctav/e4b-it-simple-lora-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use carlesoctav/e4b-it-simple-lora-sft with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-E4B-it")
model = PeftModel.from_pretrained(base_model, "carlesoctav/e4b-it-simple-lora-sft")

Transformers

How to use carlesoctav/e4b-it-simple-lora-sft with Transformers:

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

pipe = pipeline("text-generation", model="carlesoctav/e4b-it-simple-lora-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("carlesoctav/e4b-it-simple-lora-sft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use carlesoctav/e4b-it-simple-lora-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "carlesoctav/e4b-it-simple-lora-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": "carlesoctav/e4b-it-simple-lora-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/carlesoctav/e4b-it-simple-lora-sft

SGLang

How to use carlesoctav/e4b-it-simple-lora-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 "carlesoctav/e4b-it-simple-lora-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": "carlesoctav/e4b-it-simple-lora-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 "carlesoctav/e4b-it-simple-lora-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": "carlesoctav/e4b-it-simple-lora-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use carlesoctav/e4b-it-simple-lora-sft with Docker Model Runner:
```
docker model run hf.co/carlesoctav/e4b-it-simple-lora-sft
```

Gemma 4 E4B-it Simple LoRA SFT

Direct Supervised Fine-Tuning (SFT) LoRA adapter trained directly on google/gemma-4-E4B-it using termgrade_train_sft_32k.jsonl (32k sequence length).

Base Model: google/gemma-4-E4B-it
Method: Direct LoRA SFT ($r=16$, $\alpha=16$)
Dataset: termgrade_train_sft_32k.jsonl

Usage

import torch
from transformers import AutoModelForCausalLM
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-4-E4B-it",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(
    base_model,
    "carlesoctav/e4b-it-simple-lora-sft",
)

Downloads last month: 18

Model tree for carlesoctav/e4b-it-simple-lora-sft

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Adapter

(486)

this model