Instructions to use lmnglzd/az-asr-postedit-gemma4-e2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmnglzd/az-asr-postedit-gemma4-e2b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-E2B-it")
model = PeftModel.from_pretrained(base_model, "lmnglzd/az-asr-postedit-gemma4-e2b")

Transformers

How to use lmnglzd/az-asr-postedit-gemma4-e2b with Transformers:

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

pipe = pipeline("text-generation", model="lmnglzd/az-asr-postedit-gemma4-e2b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lmnglzd/az-asr-postedit-gemma4-e2b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lmnglzd/az-asr-postedit-gemma4-e2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmnglzd/az-asr-postedit-gemma4-e2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmnglzd/az-asr-postedit-gemma4-e2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lmnglzd/az-asr-postedit-gemma4-e2b

SGLang

How to use lmnglzd/az-asr-postedit-gemma4-e2b 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 "lmnglzd/az-asr-postedit-gemma4-e2b" \
    --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": "lmnglzd/az-asr-postedit-gemma4-e2b",
		"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 "lmnglzd/az-asr-postedit-gemma4-e2b" \
        --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": "lmnglzd/az-asr-postedit-gemma4-e2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lmnglzd/az-asr-postedit-gemma4-e2b with Docker Model Runner:
```
docker model run hf.co/lmnglzd/az-asr-postedit-gemma4-e2b
```

az-asr-postedit-gemma4-e2b

This model is a fine-tuned version of google/gemma-4-E2B-it on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1453

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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 481
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.2498	0.1868	1000	0.2027
0.2288	0.3735	2000	0.1797
0.2151	0.5603	3000	0.1663
0.2112	0.7471	4000	0.1647
0.2072	0.9338	5000	0.1546
0.1850	1.1205	6000	0.1520
0.1643	1.3072	7000	0.1552
0.1607	1.4940	8000	0.1490
0.1607	1.6808	9000	0.1461
0.1653	1.8675	10000	0.1453
0.1320	2.0542	11000	0.1480
0.1265	2.2409	12000	0.1509
0.1248	2.4277	13000	0.1521

Framework versions

PEFT 0.20.0
Transformers 5.15.0
Pytorch 2.8.0+cu128
Datasets 5.0.1
Tokenizers 0.22.2

Downloads last month: 4

Model tree for lmnglzd/az-asr-postedit-gemma4-e2b

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Adapter

(210)

this model