Instructions to use adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD with Transformers:

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

pipe = pipeline("text-generation", model="adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD")
model = AutoModelForCausalLM.from_pretrained("adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-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/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-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/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD

SGLang

How to use adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-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/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-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/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-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/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-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/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD with Docker Model Runner:
```
docker model run hf.co/adpretko/AnghaBench-armv8-O2-native-clang-full-coder-epoch1-AMD
```

adpretko commited on Nov 14, 2025

Commit

6ad9561

verified ·

1 Parent(s): 8240bcb

Training in progress, step 1931

Browse files

Files changed (2) hide show

model.safetensors +1 -1
trainer_log.jsonl +4 -0

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4a1791a1aec6a3bc845f62ec3c63344a96156619161bb99abb7b0bc0047340
 size 3554214752

 version https://git-lfs.github.com/spec/v1
+oid sha256:7f5d1556aae0e422cbefb08745abc147096685c8a1182f63c7c6458bad618e53
 size 3554214752

trainer_log.jsonl CHANGED Viewed

@@ -188,3 +188,7 @@
 {"current_steps": 1880, "total_steps": 1931, "loss": 0.0148, "lr": 4.4193323026283655e-08, "epoch": 0.9738409738409738, "percentage": 97.36, "elapsed_time": "1 day, 5:59:28", "remaining_time": "0:48:48"}
 {"current_steps": 1890, "total_steps": 1931, "loss": 0.0147, "lr": 2.8837648857066304e-08, "epoch": 0.9790209790209791, "percentage": 97.88, "elapsed_time": "1 day, 6:08:46", "remaining_time": "0:39:14"}
 {"current_steps": 1900, "total_steps": 1931, "loss": 0.0148, "lr": 1.6743599913405796e-08, "epoch": 0.9842009842009842, "percentage": 98.39, "elapsed_time": "1 day, 6:18:03", "remaining_time": "0:29:39"}

 {"current_steps": 1880, "total_steps": 1931, "loss": 0.0148, "lr": 4.4193323026283655e-08, "epoch": 0.9738409738409738, "percentage": 97.36, "elapsed_time": "1 day, 5:59:28", "remaining_time": "0:48:48"}
 {"current_steps": 1890, "total_steps": 1931, "loss": 0.0147, "lr": 2.8837648857066304e-08, "epoch": 0.9790209790209791, "percentage": 97.88, "elapsed_time": "1 day, 6:08:46", "remaining_time": "0:39:14"}
 {"current_steps": 1900, "total_steps": 1931, "loss": 0.0148, "lr": 1.6743599913405796e-08, "epoch": 0.9842009842009842, "percentage": 98.39, "elapsed_time": "1 day, 6:18:03", "remaining_time": "0:29:39"}
+{"current_steps": 1910, "total_steps": 1931, "loss": 0.0152, "lr": 7.91513222908602e-09, "epoch": 0.9893809893809894, "percentage": 98.91, "elapsed_time": "1 day, 6:29:11", "remaining_time": "0:20:06"}
+{"current_steps": 1920, "total_steps": 1931, "loss": 0.0149, "lr": 2.3551336472582563e-09, "epoch": 0.9945609945609946, "percentage": 99.43, "elapsed_time": "1 day, 6:38:38", "remaining_time": "0:10:32"}
+{"current_steps": 1930, "total_steps": 1931, "loss": 0.0143, "lr": 6.542287581123852e-11, "epoch": 0.9997409997409997, "percentage": 99.95, "elapsed_time": "1 day, 6:48:04", "remaining_time": "0:00:57"}
+{"current_steps": 1931, "total_steps": 1931, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1 day, 6:50:10", "remaining_time": "0:00:00"}