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
```

BM-TNG commited on Aug 1, 2025

Commit

83558b9

verified ·

1 Parent(s): 2cf44bb

Update README.md - add instructions for enabling tool calling

Browse files

Files changed (1) hide show

README.md +32 -2

README.md CHANGED Viewed

@@ -54,7 +54,7 @@ R1T2 operates at a new sweet spot in intelligence vs. output token length. It ap
 - **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 significantly **more reserved** than R1T, but not as much as R1-0528
 - When switching from R1T to R1T2 development, we changed from AIME24 and MT-Bench to AIME24, AIME25 and GPQA-Diamond for the intelligence score. With the new benchmark set, there is a larger score difference between R1 and the original R1T Chimera than published earlier.
-- Due to the influence of its R1 parent, which does not support function calling, **R1T2 is not yet recommended for function-calling** intensive applications. However, we have developed a very promising fix to this problem, it may be solved soon (i.e. until End of July or earlier)
 **Evaluation results**
@@ -79,7 +79,37 @@ For details on the AoE construction process, you can read our [Paper on arXiV](h
   With a context size of 130,000 tokens, the model proved very helpful in interpreting very long debug logs. Long-context testing was less extensive, though.
 - We're running the model using vLLM on 8xH200 and MI325X nodes, additionally we've tested the model using SGLang, which is also used by [chutes.ai](https://chutes.ai/app/chute/4fa0c7f5-82f7-59d1-8996-661bb778893d).
 - For SGLang, we recommend using versions >= v0.4.8 in combination with argument `--reasoning-parser qwen3` to properly handle rare cases when the model skips the `<think>` reasoning step.
-- For vLLM, we recommend to not use the `--chat-template` parameter. We observed a degenerate `<think>` token consistency otherwise.
 ## Model Details

 - **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 significantly **more reserved** than R1T, but not as much as R1-0528
 - When switching from R1T to R1T2 development, we changed from AIME24 and MT-Bench to AIME24, AIME25 and GPQA-Diamond for the intelligence score. With the new benchmark set, there is a larger score difference between R1 and the original R1T Chimera than published earlier.
+- Function calling is supported in general, but both vLLM and SGLang currently require some specific adaptions, see the section below.
 **Evaluation results**
   With a context size of 130,000 tokens, the model proved very helpful in interpreting very long debug logs. Long-context testing was less extensive, though.
 - We're running the model using vLLM on 8xH200 and MI325X nodes, additionally we've tested the model using SGLang, which is also used by [chutes.ai](https://chutes.ai/app/chute/4fa0c7f5-82f7-59d1-8996-661bb778893d).
 - For SGLang, we recommend using versions >= v0.4.8 in combination with argument `--reasoning-parser qwen3` to properly handle rare cases when the model skips the `<think>` reasoning step.
+### Function calling
+R1T2 does support function calling using an updated chat template (since 01 Aug 2025). However, neither vLLM nor SGLang provide an R1T2-compatible tool call parser natively but require some adaptions.
+_vLLM:_
+For function calling with vLLM, a new tool parser is required. While we opened a PR to vLLM to include an R1T2-compatible tool parser off-the-shelf, we also ship the tool parser file `tool_parser_vllm.py` within this repository.
+With this file, tool calling can be enabled via
+```
+--tool-parser-plugin <ABSOLUTE_MODEL_SNAPSHOT_PATH>/tool_parser_vllm.py  \
+--tool-call-parser tng_r1t2
+```
+Here, put in the path to the snapshot folder such as `~/.cache/huggingface/hub/models--tngtech--DeepSeek-TNG-R1T2-Chimera/snapshots/SNAPSHOT/tool_parser_vllm.py`
+_SGLang:_
+Tool call support for R1T2 requires a recent SGLang version >= v0.4.10 (alternatively, you need to patch [this bugfix for the reasoning parser](https://github.com/sgl-project/sglang/pull/8606) for older versions of SGLang).
+An R1T2-compatible tool call parser will be added with [this PR to SGLang](https://github.com/sgl-project/sglang/pull/8672).
+Unfortunately, and unlike vLLM, there is no simple plugin system for tool call parsers in SGLang.
+Until our PR is merged an relased with a new SGLang version, you can still install it manually by patching your SGLang source code as outlined in the PR:
+The new tool call parser must be added and registered (so in total one file must be added, a second one edited, see [details here](https://github.com/sgl-project/sglang/pull/8672/files)).
+Once the SGLang installation has been updated correctly, tool calling with R1T2 can be activated by starting SGLang with
+```
+--tool-call-parser tng_r1t2
+```
 ## Model Details