Instructions to use adpretko/ml815-model4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adpretko/ml815-model4 with Transformers:

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

pipe = pipeline("text-generation", model="adpretko/ml815-model4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adpretko/ml815-model4")
model = AutoModelForCausalLM.from_pretrained("adpretko/ml815-model4")
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-model4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adpretko/ml815-model4"
# 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-model4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adpretko/ml815-model4

SGLang

How to use adpretko/ml815-model4 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-model4" \
    --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-model4",
		"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-model4" \
        --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-model4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adpretko/ml815-model4 with Docker Model Runner:
```
docker model run hf.co/adpretko/ml815-model4
```

adpretko commited on Nov 23, 2025

Commit

c04453a

verified ·

1 Parent(s): 5f368d3

Training in progress, step 309

Browse files

Files changed (3) hide show

model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1
trainer_log.jsonl +10 -0

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c210e2c1df4b376b35f11de4e85290fb9771330352bfb867fc2ad8e095dcd22
 size 4996670464

 version https://git-lfs.github.com/spec/v1
+oid sha256:92f4c97d7ea49c8f64c105148ad62be756a831d2df8c6b675d92db7d47548189
 size 4996670464

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74314bb96e9d7c89ad0e2651fcdbb0f3632c8a01b42df459ff0aa0eace14478b
 size 1178224960

 version https://git-lfs.github.com/spec/v1
+oid sha256:8d75adbd4f167b60626f7bf0b9f92def3922e76ac2e91e2847d4ff01a13e980d
 size 1178224960

trainer_log.jsonl CHANGED Viewed

@@ -19,3 +19,13 @@
 {"current_steps": 190, "total_steps": 309, "loss": 0.0428, "lr": 7.869328095692313e-06, "epoch": 0.6148867313915858, "percentage": 61.49, "elapsed_time": "0:21:57", "remaining_time": "0:13:45"}
 {"current_steps": 200, "total_steps": 309, "loss": 0.043, "lr": 6.781146967348283e-06, "epoch": 0.6472491909385113, "percentage": 64.72, "elapsed_time": "0:23:01", "remaining_time": "0:12:33"}
 {"current_steps": 210, "total_steps": 309, "loss": 0.0367, "lr": 5.7340286872557515e-06, "epoch": 0.6796116504854369, "percentage": 67.96, "elapsed_time": "0:24:48", "remaining_time": "0:11:41"}

 {"current_steps": 190, "total_steps": 309, "loss": 0.0428, "lr": 7.869328095692313e-06, "epoch": 0.6148867313915858, "percentage": 61.49, "elapsed_time": "0:21:57", "remaining_time": "0:13:45"}
 {"current_steps": 200, "total_steps": 309, "loss": 0.043, "lr": 6.781146967348283e-06, "epoch": 0.6472491909385113, "percentage": 64.72, "elapsed_time": "0:23:01", "remaining_time": "0:12:33"}
 {"current_steps": 210, "total_steps": 309, "loss": 0.0367, "lr": 5.7340286872557515e-06, "epoch": 0.6796116504854369, "percentage": 67.96, "elapsed_time": "0:24:48", "remaining_time": "0:11:41"}
+{"current_steps": 220, "total_steps": 309, "loss": 0.042, "lr": 4.7413313238324556e-06, "epoch": 0.7119741100323624, "percentage": 71.2, "elapsed_time": "0:26:01", "remaining_time": "0:10:31"}
+{"current_steps": 230, "total_steps": 309, "loss": 0.0424, "lr": 3.815718698874672e-06, "epoch": 0.7443365695792881, "percentage": 74.43, "elapsed_time": "0:27:07", "remaining_time": "0:09:18"}
+{"current_steps": 240, "total_steps": 309, "loss": 0.0383, "lr": 2.9689988354181742e-06, "epoch": 0.7766990291262136, "percentage": 77.67, "elapsed_time": "0:28:19", "remaining_time": "0:08:08"}
+{"current_steps": 250, "total_steps": 309, "loss": 0.042, "lr": 2.211973323008041e-06, "epoch": 0.8090614886731392, "percentage": 80.91, "elapsed_time": "0:29:22", "remaining_time": "0:06:56"}
+{"current_steps": 260, "total_steps": 309, "loss": 0.0415, "lr": 1.5542995220217961e-06, "epoch": 0.8414239482200647, "percentage": 84.14, "elapsed_time": "0:30:32", "remaining_time": "0:05:45"}
+{"current_steps": 270, "total_steps": 309, "loss": 0.0382, "lr": 1.0043673649027519e-06, "epoch": 0.8737864077669902, "percentage": 87.38, "elapsed_time": "0:31:38", "remaining_time": "0:04:34"}
+{"current_steps": 280, "total_steps": 309, "loss": 0.0377, "lr": 5.691923259479093e-07, "epoch": 0.9061488673139159, "percentage": 90.61, "elapsed_time": "0:32:53", "remaining_time": "0:03:24"}
+{"current_steps": 290, "total_steps": 309, "loss": 0.0383, "lr": 2.5432592503288e-07, "epoch": 0.9385113268608414, "percentage": 93.85, "elapsed_time": "0:34:05", "remaining_time": "0:02:13"}
+{"current_steps": 300, "total_steps": 309, "loss": 0.0409, "lr": 6.378490697611761e-08, "epoch": 0.970873786407767, "percentage": 97.09, "elapsed_time": "0:35:15", "remaining_time": "0:01:03"}
+{"current_steps": 309, "total_steps": 309, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:38:03", "remaining_time": "0:00:00"}