Instructions to use tngtech/DeepSeek-R1T-Chimera with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tngtech/DeepSeek-R1T-Chimera with Transformers:

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

pipe = pipeline("text-generation", model="tngtech/DeepSeek-R1T-Chimera", 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("tngtech/DeepSeek-R1T-Chimera", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tngtech/DeepSeek-R1T-Chimera", trust_remote_code=True)
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 tngtech/DeepSeek-R1T-Chimera with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tngtech/DeepSeek-R1T-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-R1T-Chimera",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tngtech/DeepSeek-R1T-Chimera

SGLang

How to use tngtech/DeepSeek-R1T-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-R1T-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-R1T-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-R1T-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-R1T-Chimera",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tngtech/DeepSeek-R1T-Chimera with Docker Model Runner:
```
docker model run hf.co/tngtech/DeepSeek-R1T-Chimera
```

rbrt commited on Apr 26, 2025

Commit

3da0ba2

verified ·

1 Parent(s): 13490ae

Update README.md

Browse files

Files changed (1) hide show

README.md +37 -3

README.md CHANGED Viewed

@@ -1,3 +1,37 @@
----
-license: mit
----

+---
+license: mit
+library_name: transformers
+base_model:
+- deepseek-ai/DeepSeek-V3-0324
+- deepseek-ai/DeepSeek-R1
+pipeline_tag: text-generation
+---
+# DeepSeek-R1T-Chimera
+<div align="center">
+<img src="https://www.tngtech.com/_astro/TNG_Logo.URm66zYr_Z2aCrIU.svg"
+     alt="TNG Logo"
+     width="400"
+     style="display: inline-block; vertical-align: middle;"/>
+</div>
+<br>
+<div align="center">
+  <a href="LICENSE" style="margin: 2px;">
+    <img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+**Model merge of DeepSeek-R1 and DeepSeek-V3 (0324)**
+An open weights model combining the intelligence of R1 with the token efficiency of V3.
+## Model Details
+- **Architecture**: DeepSeek-MoE Transformer-based language model
+- **Combination Method**: Merged model weights from DeepSeek-R1 and DeepSeek-V3 (0324)
+- **Release Date**: 2025-04-27
+## Contact
+- Email: research@tngtech.com