Instructions to use tngtech/DeepSeek-TNG-R1T2-Chimera with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tngtech/DeepSeek-TNG-R1T2-Chimera with Transformers:

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

pipe = pipeline("text-generation", model="tngtech/DeepSeek-TNG-R1T2-Chimera", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tngtech/DeepSeek-TNG-R1T2-Chimera", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tngtech/DeepSeek-TNG-R1T2-Chimera", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tngtech/DeepSeek-TNG-R1T2-Chimera with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tngtech/DeepSeek-TNG-R1T2-Chimera"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tngtech/DeepSeek-TNG-R1T2-Chimera",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tngtech/DeepSeek-TNG-R1T2-Chimera

SGLang

How to use tngtech/DeepSeek-TNG-R1T2-Chimera 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 "tngtech/DeepSeek-TNG-R1T2-Chimera" \
    --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": "tngtech/DeepSeek-TNG-R1T2-Chimera",
		"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 "tngtech/DeepSeek-TNG-R1T2-Chimera" \
        --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": "tngtech/DeepSeek-TNG-R1T2-Chimera",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tngtech/DeepSeek-TNG-R1T2-Chimera with Docker Model Runner:
```
docker model run hf.co/tngtech/DeepSeek-TNG-R1T2-Chimera
```

TNGHK commited on Jul 2, 2025

Commit

f60e279

verified ·

1 Parent(s): e40ca83

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -2

README.md CHANGED Viewed

@@ -28,11 +28,23 @@ pipeline_tag: text-generation
 **Assembly of Experts construction of a Chimera model based on the [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528), [DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) and [DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324) parent models**
-We present the "DeepSeek-TNG R1T2 Chimera" 671B model, the successor to our original "DeepSeek R1T Chimera" released on April 26th.
-Unlike the original Chimera, which was based on the two parent models V3-0324 and R1, the new Chimera is a Trimind with three parents, additionally R1-0528. It is constructed using the Assembly of Experts-method with relatively fine-granular direct brain edits. This more refined assembly allowed fixing the &lt;think&gt; token consistency issue, which was a weakness of R1T and is now solved for R1T2.
 R1T2 operates at a new sweet spot in intelligence vs. output token length:
 IMAGE

 **Assembly of Experts construction of a Chimera model based on the [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528), [DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) and [DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324) parent models**
+We present the *"DeepSeek-TNG R1T2 Chimera"* 671B model, the successor to our original *"DeepSeek R1T Chimera"* released on April 26th.
+Unlike the original Chimera, which was based on the two parent models V3-0324 and R1, the new Chimera is a **Trimind** *with three parents*, additionally R1-0528. It is constructed using the Assembly of Experts-method with relatively fine-granular direct brain edits. This more refined assembly allowed fixing the &lt;think&gt; token consistency issue, which was a weakness of R1T and is now solved for R1T2.
 R1T2 operates at a new sweet spot in intelligence vs. output token length:
+It appears to be...
+- about 20% faster than the regular R1, and more than twice as fast as R1-0528
+- significantly more intelligent than the regular R1 in benchmarks such as GPQA and AIME-24
+- much more intelligent and also think-token consistent compared to the first R1T Chimera 0426
+- and generally well-behaved and a nice persona to talk to, even without any system prompt.
+**Limitations**
+- R1-0528 is thinking much longer, but also is achieving better hard benchmark results than R1T2
+- as measured by SpeechMap.ai (courtesy of xlr8harder), R1T2 is more reserved than R1T, but not as much as R1-0528
+- due to the influence of it's R1 parent, which is bad a function calling, R1T2 is not recommended for function-calling intensive applications at this stage (this may be fixed at a later stage)
 IMAGE