Instructions to use adpretko/ml815-model2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adpretko/ml815-model2 with Transformers:

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

pipe = pipeline("text-generation", model="adpretko/ml815-model2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adpretko/ml815-model2")
model = AutoModelForCausalLM.from_pretrained("adpretko/ml815-model2")
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-model2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adpretko/ml815-model2"
# 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-model2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adpretko/ml815-model2

SGLang

How to use adpretko/ml815-model2 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-model2" \
    --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-model2",
		"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-model2" \
        --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-model2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adpretko/ml815-model2 with Docker Model Runner:
```
docker model run hf.co/adpretko/ml815-model2
```

adpretko commited on Nov 23, 2025

Commit

bb06e6a

verified ·

1 Parent(s): 57edab5

Training in progress, step 300

Browse files

Files changed (2) hide show

model.safetensors +1 -1
trainer_log.jsonl +9 -0

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d674d3600a6b37071c7c3b93bf30180079e0c0a48c2a8423c4807737736efa2
 size 3554214752

 version https://git-lfs.github.com/spec/v1
+oid sha256:82f1a7a238b13c3b128d7e46f380c1f0443b9de3588cc6383841457ebefc4f4f
 size 3554214752

trainer_log.jsonl CHANGED Viewed

@@ -19,3 +19,12 @@
 {"current_steps": 190, "total_steps": 309, "loss": 0.0476, "lr": 7.869328095692313e-06, "epoch": 0.6148867313915858, "percentage": 61.49, "elapsed_time": "0:20:35", "remaining_time": "0:12:53"}
 {"current_steps": 200, "total_steps": 309, "loss": 0.0483, "lr": 6.781146967348283e-06, "epoch": 0.6472491909385113, "percentage": 64.72, "elapsed_time": "0:21:36", "remaining_time": "0:11:46"}
 {"current_steps": 210, "total_steps": 309, "loss": 0.0406, "lr": 5.7340286872557515e-06, "epoch": 0.6796116504854369, "percentage": 67.96, "elapsed_time": "0:22:58", "remaining_time": "0:10:50"}

 {"current_steps": 190, "total_steps": 309, "loss": 0.0476, "lr": 7.869328095692313e-06, "epoch": 0.6148867313915858, "percentage": 61.49, "elapsed_time": "0:20:35", "remaining_time": "0:12:53"}
 {"current_steps": 200, "total_steps": 309, "loss": 0.0483, "lr": 6.781146967348283e-06, "epoch": 0.6472491909385113, "percentage": 64.72, "elapsed_time": "0:21:36", "remaining_time": "0:11:46"}
 {"current_steps": 210, "total_steps": 309, "loss": 0.0406, "lr": 5.7340286872557515e-06, "epoch": 0.6796116504854369, "percentage": 67.96, "elapsed_time": "0:22:58", "remaining_time": "0:10:50"}
+{"current_steps": 220, "total_steps": 309, "loss": 0.0469, "lr": 4.7413313238324556e-06, "epoch": 0.7119741100323624, "percentage": 71.2, "elapsed_time": "0:24:07", "remaining_time": "0:09:45"}
+{"current_steps": 230, "total_steps": 309, "loss": 0.0473, "lr": 3.815718698874672e-06, "epoch": 0.7443365695792881, "percentage": 74.43, "elapsed_time": "0:25:10", "remaining_time": "0:08:38"}
+{"current_steps": 240, "total_steps": 309, "loss": 0.0432, "lr": 2.9689988354181742e-06, "epoch": 0.7766990291262136, "percentage": 77.67, "elapsed_time": "0:26:18", "remaining_time": "0:07:33"}
+{"current_steps": 250, "total_steps": 309, "loss": 0.0475, "lr": 2.211973323008041e-06, "epoch": 0.8090614886731392, "percentage": 80.91, "elapsed_time": "0:27:18", "remaining_time": "0:06:26"}
+{"current_steps": 260, "total_steps": 309, "loss": 0.0459, "lr": 1.5542995220217961e-06, "epoch": 0.8414239482200647, "percentage": 84.14, "elapsed_time": "0:28:24", "remaining_time": "0:05:21"}
+{"current_steps": 270, "total_steps": 309, "loss": 0.0424, "lr": 1.0043673649027519e-06, "epoch": 0.8737864077669902, "percentage": 87.38, "elapsed_time": "0:29:27", "remaining_time": "0:04:15"}
+{"current_steps": 280, "total_steps": 309, "loss": 0.0425, "lr": 5.691923259479093e-07, "epoch": 0.9061488673139159, "percentage": 90.61, "elapsed_time": "0:30:38", "remaining_time": "0:03:10"}
+{"current_steps": 290, "total_steps": 309, "loss": 0.043, "lr": 2.5432592503288e-07, "epoch": 0.9385113268608414, "percentage": 93.85, "elapsed_time": "0:31:46", "remaining_time": "0:02:04"}
+{"current_steps": 300, "total_steps": 309, "loss": 0.0453, "lr": 6.378490697611761e-08, "epoch": 0.970873786407767, "percentage": 97.09, "elapsed_time": "0:32:54", "remaining_time": "0:00:59"}