Instructions to use XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256 with Transformers:

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

pipe = pipeline("text-generation", model="XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256")
model = AutoModelForMultimodalLM.from_pretrained("XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256

SGLang

How to use XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256 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 "XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256" \
    --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": "XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256",
		"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 "XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256" \
        --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": "XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256 with Docker Model Runner:
```
docker model run hf.co/XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256
```

XReyRobert commited on Jul 2

Commit

076fdac

verified ·

1 Parent(s): bbe9e60

Replace remaining informal benchmark labels

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -234,7 +234,7 @@ the observed vLLM GPTQ-Marlin runtime behavior for this deployment shape.
 <span style="font-size: 11px; color: #64748b; font-weight: 500;">318 / 350 single-pass run</span>
 </div>
 <div style="border: 1px solid #e2e8f0; padding: 16px; border-radius: 10px; background: #f8fafc; text-align: center; box-shadow: inset 0 2px 4px rgba(0,0,0,0.02);">
-<span style="font-size: 11px; font-weight: 700; color: #7c3aed; text-transform: uppercase; display: block; margin-bottom: 6px; letter-spacing: 0.5px;">🧠 vs Qwopus v2</span>
 <span style="font-size: 24px; font-weight: 800; color: #10b981; display: block;">+0.86 pp</span>
 <span style="font-size: 11px; color: #64748b; font-weight: 500;">315 / 350 selected-subset run</span>
 </div>
@@ -358,7 +358,7 @@ Terminal-Bench 2.0 Smoke24 is a fixed 24-task coding-agent comparison corpus.
 It is useful for fast regression and local serving comparison, but it is not a
 full Terminal-Bench leaderboard submission.
-This Ornith GPTQ-Pro run used the long-context card-validation shape:
 `max_model_len=262144`, `max_input_tokens=220000`, 30 minute task timeout,
 32 CPU / 48 GiB sandbox, `thinking_token_budget=32768`, `max_output_tokens=40000`,
 temperature `1.0`, top-p `0.95`, top-k `20`, and `preserve_thinking=true`.

 <span style="font-size: 11px; color: #64748b; font-weight: 500;">318 / 350 single-pass run</span>
 </div>
 <div style="border: 1px solid #e2e8f0; padding: 16px; border-radius: 10px; background: #f8fafc; text-align: center; box-shadow: inset 0 2px 4px rgba(0,0,0,0.02);">
+<span style="font-size: 11px; font-weight: 700; color: #7c3aed; text-transform: uppercase; display: block; margin-bottom: 6px; letter-spacing: 0.5px;">🧠 vs XReyRobert/Qwopus3.6-27B-v2-GPTQ-Pro-v1</span>
 <span style="font-size: 24px; font-weight: 800; color: #10b981; display: block;">+0.86 pp</span>
 <span style="font-size: 11px; color: #64748b; font-weight: 500;">315 / 350 selected-subset run</span>
 </div>
 It is useful for fast regression and local serving comparison, but it is not a
 full Terminal-Bench leaderboard submission.
+`XReyRobert/Ornith-1.0-35B-GPTQ-Pro-FOEM-4bit-g128-ns256` used the long-context card-validation shape:
 `max_model_len=262144`, `max_input_tokens=220000`, 30 minute task timeout,
 32 CPU / 48 GiB sandbox, `thinking_token_budget=32768`, `max_output_tokens=40000`,
 temperature `1.0`, top-p `0.95`, top-k `20`, and `preserve_thinking=true`.