Instructions to use Haruster/Ordinal-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Haruster/Ordinal-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="Haruster/Ordinal-v1.0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Haruster/Ordinal-v1.0", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Haruster/Ordinal-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Haruster/Ordinal-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Haruster/Ordinal-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Haruster/Ordinal-v1.0

SGLang

How to use Haruster/Ordinal-v1.0 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 "Haruster/Ordinal-v1.0" \
    --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": "Haruster/Ordinal-v1.0",
		"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 "Haruster/Ordinal-v1.0" \
        --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": "Haruster/Ordinal-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Haruster/Ordinal-v1.0 with Docker Model Runner:
```
docker model run hf.co/Haruster/Ordinal-v1.0
```

Ordinal-v1.0 / config.json

Haruster

Ordinal v1.0 — flagship (ordinal-5b architecture/config)

bd4f32d verified 21 days ago

Raw

History Blame Contribute Delete

1.06 kB

	{
	"vocab_size": 50304,
	"hidden_size": 3584,
	"intermediate_size": 9216,
	"num_hidden_layers": 36,
	"num_attention_heads": 28,
	"num_key_value_heads": 4,
	"head_dim": 128,
	"max_position_embeddings": 8192,
	"rms_norm_eps": 1e-05,
	"rope_theta": 500000.0,
	"hidden_act": "silu",
	"tie_word_embeddings": false,
	"use_cache": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"pad_token_id": 0,
	"torch_dtype": "bfloat16",
	"use_confidence_head": true,
	"confidence_threshold": 0.7,
	"use_retrieval_attention": true,
	"retrieval_dim": 256,
	"num_retrieval_heads": 4,
	"use_fact_verification_layer": true,
	"verification_layers": [
	12,
	24,
	35
	],
	"use_source_embeddings": true,
	"num_source_types": 16,
	"sliding_window": null,
	"model_type": "ordinal",
	"architectures": [
	"OrdinalForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_ordinal.OrdinalConfig",
	"AutoModelForCausalLM": "modeling_ordinal.OrdinalForCausalLM"
	},
	"transformers_version": "4.45.0"
	}