Instructions to use prithivMLmods/Deepthink-Reasoning-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Deepthink-Reasoning-14B with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Deepthink-Reasoning-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Deepthink-Reasoning-14B")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Deepthink-Reasoning-14B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use prithivMLmods/Deepthink-Reasoning-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Deepthink-Reasoning-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Deepthink-Reasoning-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Deepthink-Reasoning-14B

SGLang

How to use prithivMLmods/Deepthink-Reasoning-14B 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 "prithivMLmods/Deepthink-Reasoning-14B" \
    --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": "prithivMLmods/Deepthink-Reasoning-14B",
		"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 "prithivMLmods/Deepthink-Reasoning-14B" \
        --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": "prithivMLmods/Deepthink-Reasoning-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Deepthink-Reasoning-14B with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Deepthink-Reasoning-14B
```

prithivMLmods commited on Jan 23, 2025

Commit

ebf5f1f

verified ·

1 Parent(s): 08fd00d

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -15,6 +15,7 @@ tags:
 - Math
 - text-generation-inference
 - Math-CoT
 ---
 # **Deepthink-Reasoning-14B**
@@ -85,4 +86,4 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 4. **Long-Context Limitations:** Although it supports up to 128K tokens, performance may degrade or exhibit inefficiencies with extremely lengthy or complex contexts.
 5. **Bias in Outputs:** The model might reflect biases present in its training data, affecting its objectivity in certain contexts or cultural sensitivity in multilingual outputs.
 6. **Dependence on Prompt Quality:** Results heavily depend on well-structured and clear inputs. Poorly framed prompts can lead to irrelevant or suboptimal responses.
-7. **Error in Multilingual Output:** Despite robust multilingual support, subtle errors in grammar, syntax, or cultural nuances might appear, especially in low-resource languages.

 - Math
 - text-generation-inference
 - Math-CoT
+- Deep-think
 ---
 # **Deepthink-Reasoning-14B**
 4. **Long-Context Limitations:** Although it supports up to 128K tokens, performance may degrade or exhibit inefficiencies with extremely lengthy or complex contexts.
 5. **Bias in Outputs:** The model might reflect biases present in its training data, affecting its objectivity in certain contexts or cultural sensitivity in multilingual outputs.
 6. **Dependence on Prompt Quality:** Results heavily depend on well-structured and clear inputs. Poorly framed prompts can lead to irrelevant or suboptimal responses.
+7. **Error in Multilingual Output:** Despite robust multilingual support, subtle errors in grammar, syntax, or cultural nuances might appear, especially in low-resource languages.