Instructions to use KewaiiGamer/Ornith-1.0-397B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KewaiiGamer/Ornith-1.0-397B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="KewaiiGamer/Ornith-1.0-397B-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("KewaiiGamer/Ornith-1.0-397B-GGUF", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KewaiiGamer/Ornith-1.0-397B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KewaiiGamer/Ornith-1.0-397B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KewaiiGamer/Ornith-1.0-397B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KewaiiGamer/Ornith-1.0-397B-GGUF

SGLang

How to use KewaiiGamer/Ornith-1.0-397B-GGUF 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 "KewaiiGamer/Ornith-1.0-397B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KewaiiGamer/Ornith-1.0-397B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "KewaiiGamer/Ornith-1.0-397B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KewaiiGamer/Ornith-1.0-397B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KewaiiGamer/Ornith-1.0-397B-GGUF with Docker Model Runner:
```
docker model run hf.co/KewaiiGamer/Ornith-1.0-397B-GGUF
```

Ornith-1.0-397B-GGUF

My first quantizations of a model.

Based on Ornith-1.0-397B

Done with llama-quantize Ornith 35B Benchmark Results

Available Quantizations

Quantization	Disk Space	Estimated Accuracy
Q2_K	00.0GB	??%
Q3_K_S	00.0GB	??%
Q3_K_M	00.0GB	??%
Q4_K_M	00.0GB	??%
Q6_K	00.0GB	??%
Q8_0	00.0GB	??%
F16	00.0GB	100%

Ornith 1.0 397B GGUF

This model card documents Ornith-1.0-397B-GGUF, the lightweight member of the Ornith family, designed for efficient single-GPU deployment.

Benchmarks

	Ornith-1.0-397B	Qwen3.5-397B	Qwen3.7-Max	GLM-5.2-744B	Minimax-M3-428B	DeepSeek-V4-Pro-1.6T	Claude Opus 4.7	Claude Opus 4.8
Agentic Coding
Terminal-Bench 2.1 _(Terminus-2)	77.5	53.5	73.5	81.0	64	64	70.3	85
Terminal-Bench 2.1 _{(Claude Code)}	78.2	48.6	69.8	82.7	-	66.5	69.7	78.9
SWE-bench Verified	82.4	76.4	80.4	-	-	80.6	80.8	87.6
SWE-bench Pro	62.2	51.6	60.6	62.1	59	55.4	64.3	69.2
SWE-bench Multilingual	78.9	69.3	78.3	-	-	76.2	-	-
NL2Repo	48.2	36.8	47.2	48.9	42.1	-	-	69.7
Claw-eval Avg	77.1	70.7	65.2	-	-	75.8	78.2	-
SWE Atlas - QnA	41.2	20.4	-	-	37.9	27.2	40.3	48.8
SWE Atlas - RF	42.6	18.4	-	-	-	-	48.6	46.7
SWE Atlas - TW	39.1	18.5	-	-	30.8	-	38.5	-

* Terminal-Bench 2.1 (Terminus-2): We evaluate Terminal-Bench 2.1 using the Harbor/Terminus-2 framework with parser=json, temperature=1.0, top_p=1.0, and a 128K context window. Each run uses a 4-hour timeout with 32 CPU cores and 48GB RAM, and results are averaged over 5 runs. We adjust the Qwen chat template to ensure consistency between training and inference (https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B/blob/main/chat_template.jinja), and modify Harbor to align with vLLM's reasoning_content key.
* Terminal-Bench 2.1 (Claude Code): We evaluate Terminal-Bench 2.1 using Claude Code 2.1.126 with parser=json, temperature=1.0, top_p=1.0, max_new_tokens=131072. Results are averaged over 5 runs. Again, Qwen chat template needs to be modified.
* SWE-Bench Verified, Pro and Multilingual: using OpenHands harness with temp=1.0, top_p=0.95, 256k context window.
* SWE Atlas QnA, RF, TW: using mini SWE agent harness with temp=1.0, top_p=0.95, 128K context window. Results are averaged over 5 runs.
* NL2Repo: with temperature=1.0, top_p=1.0, 400K context, 48K output and anti-hacking filters.
* ClawEval: An agentic code benchmark over real-user task distributions; temp=0.6 and 256K context.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for KewaiiGamer/Ornith-1.0-397B-GGUF

Base model

deepreinforce-ai/Ornith-1.0-397B

Finetuned

(2)

this model