Instructions to use Ogamon/llama3_1_truth_model_bench_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ogamon/llama3_1_truth_model_bench_1 with Transformers:

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

pipe = pipeline("text-generation", model="Ogamon/llama3_1_truth_model_bench_1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ogamon/llama3_1_truth_model_bench_1")
model = AutoModelForCausalLM.from_pretrained("Ogamon/llama3_1_truth_model_bench_1")
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

vLLM

How to use Ogamon/llama3_1_truth_model_bench_1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ogamon/llama3_1_truth_model_bench_1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ogamon/llama3_1_truth_model_bench_1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ogamon/llama3_1_truth_model_bench_1

SGLang

How to use Ogamon/llama3_1_truth_model_bench_1 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 "Ogamon/llama3_1_truth_model_bench_1" \
    --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": "Ogamon/llama3_1_truth_model_bench_1",
		"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 "Ogamon/llama3_1_truth_model_bench_1" \
        --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": "Ogamon/llama3_1_truth_model_bench_1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ogamon/llama3_1_truth_model_bench_1 with Docker Model Runner:
```
docker model run hf.co/Ogamon/llama3_1_truth_model_bench_1
```

llama3_1_truth_model_bench_1 / trainer_log.jsonl

Ogamon

second commit

2c02d2a verified almost 2 years ago

raw

history blame contribute delete

1.77 kB

	{"current_steps": 5, "total_steps": 78, "percentage": 6.41, "elapsed_time": "0:00:00", "remaining_time": "0:00:04"}
	{"current_steps": 10, "total_steps": 78, "percentage": 12.82, "elapsed_time": "0:00:00", "remaining_time": "0:00:04"}
	{"current_steps": 15, "total_steps": 78, "percentage": 19.23, "elapsed_time": "0:00:01", "remaining_time": "0:00:04"}
	{"current_steps": 20, "total_steps": 78, "percentage": 25.64, "elapsed_time": "0:00:01", "remaining_time": "0:00:04"}
	{"current_steps": 25, "total_steps": 78, "percentage": 32.05, "elapsed_time": "0:00:01", "remaining_time": "0:00:04"}
	{"current_steps": 30, "total_steps": 78, "percentage": 38.46, "elapsed_time": "0:00:02", "remaining_time": "0:00:03"}
	{"current_steps": 35, "total_steps": 78, "percentage": 44.87, "elapsed_time": "0:00:02", "remaining_time": "0:00:03"}
	{"current_steps": 40, "total_steps": 78, "percentage": 51.28, "elapsed_time": "0:00:03", "remaining_time": "0:00:02"}
	{"current_steps": 45, "total_steps": 78, "percentage": 57.69, "elapsed_time": "0:00:03", "remaining_time": "0:00:02"}
	{"current_steps": 50, "total_steps": 78, "percentage": 64.1, "elapsed_time": "0:00:03", "remaining_time": "0:00:02"}
	{"current_steps": 55, "total_steps": 78, "percentage": 70.51, "elapsed_time": "0:00:04", "remaining_time": "0:00:01"}
	{"current_steps": 60, "total_steps": 78, "percentage": 76.92, "elapsed_time": "0:00:04", "remaining_time": "0:00:01"}
	{"current_steps": 65, "total_steps": 78, "percentage": 83.33, "elapsed_time": "0:00:05", "remaining_time": "0:00:01"}
	{"current_steps": 70, "total_steps": 78, "percentage": 89.74, "elapsed_time": "0:00:05", "remaining_time": "0:00:00"}
	{"current_steps": 75, "total_steps": 78, "percentage": 96.15, "elapsed_time": "0:00:05", "remaining_time": "0:00:00"}