Instructions to use adpretko/ml815-model5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adpretko/ml815-model5 with Transformers:

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

pipe = pipeline("text-generation", model="adpretko/ml815-model5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adpretko/ml815-model5")
model = AutoModelForCausalLM.from_pretrained("adpretko/ml815-model5", device_map="auto")
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/ml815-model5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adpretko/ml815-model5"
# 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/ml815-model5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adpretko/ml815-model5

SGLang

How to use adpretko/ml815-model5 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/ml815-model5" \
    --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/ml815-model5",
		"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/ml815-model5" \
        --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/ml815-model5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adpretko/ml815-model5 with Docker Model Runner:
```
docker model run hf.co/adpretko/ml815-model5
```

adpretko commited on Nov 23, 2025

Commit

b8219b7

verified ·

1 Parent(s): fadcd0f

Training in progress, step 155

Browse files

Files changed (2) hide show

model.safetensors +1 -1
trainer_log.jsonl +6 -0

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee72412094e2170c61162f3c0b4519bc3f89beaac4b88fa4db0c13a953a2777
 size 3554214752

 version https://git-lfs.github.com/spec/v1
+oid sha256:26dae8524b9145f16740987311006f4f4ff5d742b0703aaa41446c233101cf49
 size 3554214752

trainer_log.jsonl CHANGED Viewed

@@ -8,3 +8,9 @@
 {"current_steps": 80, "total_steps": 155, "loss": 0.0511, "lr": 1.1463811409361667e-05, "epoch": 0.517799352750809, "percentage": 51.61, "elapsed_time": "0:16:36", "remaining_time": "0:15:33"}
 {"current_steps": 90, "total_steps": 155, "loss": 0.0515, "lr": 9.209776239900453e-06, "epoch": 0.5825242718446602, "percentage": 58.06, "elapsed_time": "0:18:42", "remaining_time": "0:13:30"}
 {"current_steps": 100, "total_steps": 155, "loss": 0.0483, "lr": 6.995935948193294e-06, "epoch": 0.6472491909385113, "percentage": 64.52, "elapsed_time": "0:20:45", "remaining_time": "0:11:24"}

 {"current_steps": 80, "total_steps": 155, "loss": 0.0511, "lr": 1.1463811409361667e-05, "epoch": 0.517799352750809, "percentage": 51.61, "elapsed_time": "0:16:36", "remaining_time": "0:15:33"}
 {"current_steps": 90, "total_steps": 155, "loss": 0.0515, "lr": 9.209776239900453e-06, "epoch": 0.5825242718446602, "percentage": 58.06, "elapsed_time": "0:18:42", "remaining_time": "0:13:30"}
 {"current_steps": 100, "total_steps": 155, "loss": 0.0483, "lr": 6.995935948193294e-06, "epoch": 0.6472491909385113, "percentage": 64.52, "elapsed_time": "0:20:45", "remaining_time": "0:11:24"}
+{"current_steps": 110, "total_steps": 155, "loss": 0.0442, "lr": 4.934897930252887e-06, "epoch": 0.7119741100323624, "percentage": 70.97, "elapsed_time": "0:23:14", "remaining_time": "0:09:30"}
+{"current_steps": 120, "total_steps": 155, "loss": 0.0456, "lr": 3.1314972661673572e-06, "epoch": 0.7766990291262136, "percentage": 77.42, "elapsed_time": "0:25:24", "remaining_time": "0:07:24"}
+{"current_steps": 130, "total_steps": 155, "loss": 0.0476, "lr": 1.6774642643563955e-06, "epoch": 0.8414239482200647, "percentage": 83.87, "elapsed_time": "0:27:27", "remaining_time": "0:05:16"}
+{"current_steps": 140, "total_steps": 155, "loss": 0.043, "lr": 6.467585824627886e-07, "epoch": 0.9061488673139159, "percentage": 90.32, "elapsed_time": "0:29:39", "remaining_time": "0:03:10"}
+{"current_steps": 150, "total_steps": 155, "loss": 0.0447, "lr": 9.180725568338045e-08, "epoch": 0.970873786407767, "percentage": 96.77, "elapsed_time": "0:31:52", "remaining_time": "0:01:03"}
+{"current_steps": 155, "total_steps": 155, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:33:16", "remaining_time": "0:00:00"}