Instructions to use Delta-Vector/Trinity-Large-Base-Magnum-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Delta-Vector/Trinity-Large-Base-Magnum-SFT with Transformers:

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

pipe = pipeline("text-generation", model="Delta-Vector/Trinity-Large-Base-Magnum-SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Delta-Vector/Trinity-Large-Base-Magnum-SFT", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Delta-Vector/Trinity-Large-Base-Magnum-SFT", trust_remote_code=True, 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 Delta-Vector/Trinity-Large-Base-Magnum-SFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Delta-Vector/Trinity-Large-Base-Magnum-SFT

SGLang

How to use Delta-Vector/Trinity-Large-Base-Magnum-SFT 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 "Delta-Vector/Trinity-Large-Base-Magnum-SFT" \
    --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": "Delta-Vector/Trinity-Large-Base-Magnum-SFT",
		"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 "Delta-Vector/Trinity-Large-Base-Magnum-SFT" \
        --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": "Delta-Vector/Trinity-Large-Base-Magnum-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Delta-Vector/Trinity-Large-Base-Magnum-SFT with Docker Model Runner:
```
docker model run hf.co/Delta-Vector/Trinity-Large-Base-Magnum-SFT
```

This is a non-reasoning instruction and creative-writing fine-tune of Arcee AI's Trinity-Large-Base. This repository contains the merged BF16 checkpoint, not a standalone LoRA adapter.

Training

LoRA rank: 64
LoRA alpha: 128
Context length: 32,768
Learning rate: 8e-6
Schedule: cosine
Weight decay: 0.0001
Maximum gradient norm: 1.0
Final checkpoint: step 523

The training mix intentionally contains non-reasoning instruction, roleplay, and creative-writing data:

PocketDoc/Dans-Kinomaxx-VanillaBackrooms
PocketDoc/Dans-Personamaxx-Logs-2
PocketDoc/Dans-Prosemaxx-RepRemover-1
PocketDoc/Dans-Failuremaxx-Adventure-3
Delta-Vector/Hydrus-Claude-Instruct-2.7K
Delta-Vector/Hydrus-Claude-Instruct-5K
anthracite-org/kalo-opus-instruct-22k-no-refusal
anthracite-org/nopm_claude_writing_fixed
anthracite-org/kalo_opus_misc_240827
anthracite-org/kalo_misc_part2
Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
Delta-Vector/Orion-Sonnet-CharCard

Format

The checkpoint uses the tokenizer and ChatML template saved by the final training checkpoint. The template supports system, user, and assistant messages and uses <|im_end|> as EOS and padding.

Trinity-Large is a 398B-parameter sparse mixture-of-experts model with roughly 13B active parameters per token. Serving the BF16 checkpoint requires multiple GPUs.

License

This retains the base model's OpenMDW 1.1 license. See LICENSE.

Downloads last month: 20

Safetensors

Model size

399B params

Tensor type

BF16

Model tree for Delta-Vector/Trinity-Large-Base-Magnum-SFT

Base model

arcee-ai/Trinity-Large-TrueBase

Finetuned

arcee-ai/Trinity-Large-Base

Finetuned

(8)

this model