Instructions to use Albert-CAC/agent2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Albert-CAC/agent2 with Transformers:

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

pipe = pipeline("text-generation", model="Albert-CAC/agent2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Albert-CAC/agent2")
model = AutoModelForCausalLM.from_pretrained("Albert-CAC/agent2", 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 Albert-CAC/agent2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Albert-CAC/agent2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Albert-CAC/agent2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Albert-CAC/agent2

SGLang

How to use Albert-CAC/agent2 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 "Albert-CAC/agent2" \
    --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": "Albert-CAC/agent2",
		"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 "Albert-CAC/agent2" \
        --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": "Albert-CAC/agent2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Albert-CAC/agent2 with Docker Model Runner:
```
docker model run hf.co/Albert-CAC/agent2
```

agent2 / trainer_log.jsonl

Albert-CAC

Upload folder using huggingface_hub

f6c2b23 verified about 1 year ago

Raw

History Blame Contribute Delete

2.83 kB

	{"current_steps": 5, "total_steps": 57, "loss": 0.3072, "lr": 4.9394909565685894e-05, "epoch": 0.2702702702702703, "percentage": 8.77, "elapsed_time": "0:00:43", "remaining_time": "0:07:37", "throughput": 13383.84, "total_tokens": 588672}
	{"current_steps": 10, "total_steps": 57, "loss": 0.2503, "lr": 4.698684378016222e-05, "epoch": 0.5405405405405406, "percentage": 17.54, "elapsed_time": "0:01:24", "remaining_time": "0:06:37", "throughput": 14068.84, "total_tokens": 1191152}
	{"current_steps": 15, "total_steps": 57, "loss": 0.1434, "lr": 4.2919562829211283e-05, "epoch": 0.8108108108108109, "percentage": 26.32, "elapsed_time": "0:02:04", "remaining_time": "0:05:48", "throughput": 14381.98, "total_tokens": 1792128}
	{"current_steps": 20, "total_steps": 57, "loss": 0.119, "lr": 3.7500000000000003e-05, "epoch": 1.054054054054054, "percentage": 35.09, "elapsed_time": "0:02:40", "remaining_time": "0:04:56", "throughput": 14571.51, "total_tokens": 2338720}
	{"current_steps": 25, "total_steps": 57, "loss": 0.0704, "lr": 3.1137137178519985e-05, "epoch": 1.3243243243243243, "percentage": 43.86, "elapsed_time": "0:03:21", "remaining_time": "0:04:17", "throughput": 14636.56, "total_tokens": 2944992}
	{"current_steps": 30, "total_steps": 57, "loss": 0.0714, "lr": 2.4311141440795953e-05, "epoch": 1.5945945945945947, "percentage": 52.63, "elapsed_time": "0:04:00", "remaining_time": "0:03:36", "throughput": 14708.19, "total_tokens": 3543936}
	{"current_steps": 35, "total_steps": 57, "loss": 0.0651, "lr": 1.7537129724957642e-05, "epoch": 1.864864864864865, "percentage": 61.4, "elapsed_time": "0:04:40", "remaining_time": "0:02:56", "throughput": 14752.82, "total_tokens": 4133600}
	{"current_steps": 40, "total_steps": 57, "loss": 0.0524, "lr": 1.1326296046939333e-05, "epoch": 2.108108108108108, "percentage": 70.18, "elapsed_time": "0:05:16", "remaining_time": "0:02:14", "throughput": 14775.3, "total_tokens": 4674192}
	{"current_steps": 45, "total_steps": 57, "loss": 0.0349, "lr": 6.147334755577596e-06, "epoch": 2.3783783783783785, "percentage": 78.95, "elapsed_time": "0:05:57", "remaining_time": "0:01:35", "throughput": 14759.9, "total_tokens": 5271408}
	{"current_steps": 50, "total_steps": 57, "loss": 0.028, "lr": 2.391070982560564e-06, "epoch": 2.6486486486486487, "percentage": 87.72, "elapsed_time": "0:06:35", "remaining_time": "0:00:55", "throughput": 14788.33, "total_tokens": 5854528}
	{"current_steps": 55, "total_steps": 57, "loss": 0.0241, "lr": 3.4096741493194197e-07, "epoch": 2.918918918918919, "percentage": 96.49, "elapsed_time": "0:07:17", "remaining_time": "0:00:15", "throughput": 14784.67, "total_tokens": 6461216}
	{"current_steps": 57, "total_steps": 57, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:10:03", "remaining_time": "0:00:00", "throughput": 11009.88, "total_tokens": 6642400}