Instructions to use adpretko/train-armv8-O2_epoch3_AMD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adpretko/train-armv8-O2_epoch3_AMD with Transformers:

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

pipe = pipeline("text-generation", model="adpretko/train-armv8-O2_epoch3_AMD")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("adpretko/train-armv8-O2_epoch3_AMD")
model = AutoModelForMultimodalLM.from_pretrained("adpretko/train-armv8-O2_epoch3_AMD")
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 Settings

vLLM

How to use adpretko/train-armv8-O2_epoch3_AMD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adpretko/train-armv8-O2_epoch3_AMD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adpretko/train-armv8-O2_epoch3_AMD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adpretko/train-armv8-O2_epoch3_AMD

SGLang

How to use adpretko/train-armv8-O2_epoch3_AMD 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 "adpretko/train-armv8-O2_epoch3_AMD" \
    --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": "adpretko/train-armv8-O2_epoch3_AMD",
		"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 "adpretko/train-armv8-O2_epoch3_AMD" \
        --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": "adpretko/train-armv8-O2_epoch3_AMD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adpretko/train-armv8-O2_epoch3_AMD with Docker Model Runner:
```
docker model run hf.co/adpretko/train-armv8-O2_epoch3_AMD
```

adpretko commited on Oct 30, 2025

Commit

23a79ce

verified ·

1 Parent(s): d19f62d

Training in progress, step 2300

Browse files

Files changed (2) hide show

model.safetensors +1 -1
trainer_log.jsonl +10 -0

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0002f6144519d5911d11a754c1d52b2c4a9e895d1876e02b0f667ed1c3eef780
 size 3554214752

 version https://git-lfs.github.com/spec/v1
+oid sha256:771ed3b1e1c35dedf39e1cb9c8be10ea06dd6f56a814375a60026e97a0d7cde8
 size 3554214752

trainer_log.jsonl CHANGED Viewed

@@ -218,3 +218,13 @@
 {"current_steps": 2180, "total_steps": 3236, "loss": 0.0053, "lr": 5.827123817457631e-06, "epoch": 1.3475034781264492, "percentage": 67.37, "elapsed_time": "1 day, 15:37:18", "remaining_time": "19:11:34"}
 {"current_steps": 2190, "total_steps": 3236, "loss": 0.0057, "lr": 5.729326002958889e-06, "epoch": 1.3536868140361724, "percentage": 67.68, "elapsed_time": "1 day, 15:48:01", "remaining_time": "19:00:34"}
 {"current_steps": 2200, "total_steps": 3236, "loss": 0.0054, "lr": 5.632025248914546e-06, "epoch": 1.3598701499458958, "percentage": 67.99, "elapsed_time": "1 day, 15:58:46", "remaining_time": "18:49:36"}

 {"current_steps": 2180, "total_steps": 3236, "loss": 0.0053, "lr": 5.827123817457631e-06, "epoch": 1.3475034781264492, "percentage": 67.37, "elapsed_time": "1 day, 15:37:18", "remaining_time": "19:11:34"}
 {"current_steps": 2190, "total_steps": 3236, "loss": 0.0057, "lr": 5.729326002958889e-06, "epoch": 1.3536868140361724, "percentage": 67.68, "elapsed_time": "1 day, 15:48:01", "remaining_time": "19:00:34"}
 {"current_steps": 2200, "total_steps": 3236, "loss": 0.0054, "lr": 5.632025248914546e-06, "epoch": 1.3598701499458958, "percentage": 67.99, "elapsed_time": "1 day, 15:58:46", "remaining_time": "18:49:36"}
+{"current_steps": 2210, "total_steps": 3236, "loss": 0.0057, "lr": 5.535232880084373e-06, "epoch": 1.366053485855619, "percentage": 68.29, "elapsed_time": "1 day, 16:11:17", "remaining_time": "18:39:27"}
+{"current_steps": 2220, "total_steps": 3236, "loss": 0.0054, "lr": 5.438960162057548e-06, "epoch": 1.3722368217653425, "percentage": 68.6, "elapsed_time": "1 day, 16:21:56", "remaining_time": "18:28:25"}
+{"current_steps": 2230, "total_steps": 3236, "loss": 0.0055, "lr": 5.343218299941517e-06, "epoch": 1.3784201576750656, "percentage": 68.91, "elapsed_time": "1 day, 16:32:45", "remaining_time": "18:17:28"}
+{"current_steps": 2240, "total_steps": 3236, "loss": 0.0055, "lr": 5.248018437057807e-06, "epoch": 1.384603493584789, "percentage": 69.22, "elapsed_time": "1 day, 16:43:33", "remaining_time": "18:06:30"}
+{"current_steps": 2250, "total_steps": 3236, "loss": 0.0054, "lr": 5.15337165364507e-06, "epoch": 1.3907868294945123, "percentage": 69.53, "elapsed_time": "1 day, 16:54:14", "remaining_time": "17:55:30"}
+{"current_steps": 2260, "total_steps": 3236, "loss": 0.0054, "lr": 5.059288965569471e-06, "epoch": 1.3969701654042357, "percentage": 69.84, "elapsed_time": "1 day, 17:04:59", "remaining_time": "17:44:31"}
+{"current_steps": 2270, "total_steps": 3236, "loss": 0.0054, "lr": 4.965781323042547e-06, "epoch": 1.4031535013139589, "percentage": 70.15, "elapsed_time": "1 day, 17:15:41", "remaining_time": "17:33:31"}
+{"current_steps": 2280, "total_steps": 3236, "loss": 0.0053, "lr": 4.872859609346733e-06, "epoch": 1.409336837223682, "percentage": 70.46, "elapsed_time": "1 day, 17:26:24", "remaining_time": "17:22:32"}
+{"current_steps": 2290, "total_steps": 3236, "loss": 0.0053, "lr": 4.780534639568651e-06, "epoch": 1.4155201731334055, "percentage": 70.77, "elapsed_time": "1 day, 17:37:06", "remaining_time": "17:11:33"}
+{"current_steps": 2300, "total_steps": 3236, "loss": 0.0055, "lr": 4.68881715934037e-06, "epoch": 1.4217035090431287, "percentage": 71.08, "elapsed_time": "1 day, 17:47:49", "remaining_time": "17:00:34"}