Instructions to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with Transformers:

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

pipe = pipeline("text-generation", model="mkurman/Qwen2.5-14B-DeepSeek-R1-1M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mkurman/Qwen2.5-14B-DeepSeek-R1-1M")
model = AutoModelForCausalLM.from_pretrained("mkurman/Qwen2.5-14B-DeepSeek-R1-1M")
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]:]))

llama-cpp-python

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mkurman/Qwen2.5-14B-DeepSeek-R1-1M",
	filename="Qwen2.5-14B-DeepSeek-R1-1M-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

Use Docker

docker model run hf.co/mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

LM Studio
Jan

vLLM

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkurman/Qwen2.5-14B-DeepSeek-R1-1M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkurman/Qwen2.5-14B-DeepSeek-R1-1M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

SGLang

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M 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 "mkurman/Qwen2.5-14B-DeepSeek-R1-1M" \
    --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": "mkurman/Qwen2.5-14B-DeepSeek-R1-1M",
		"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 "mkurman/Qwen2.5-14B-DeepSeek-R1-1M" \
        --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": "mkurman/Qwen2.5-14B-DeepSeek-R1-1M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with Ollama:
```
ollama run hf.co/mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M
```

Unsloth Studio new

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mkurman/Qwen2.5-14B-DeepSeek-R1-1M to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mkurman/Qwen2.5-14B-DeepSeek-R1-1M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mkurman/Qwen2.5-14B-DeepSeek-R1-1M to start chatting

Pi new

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with Docker Model Runner:
```
docker model run hf.co/mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M
```

Lemonade

How to use mkurman/Qwen2.5-14B-DeepSeek-R1-1M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mkurman/Qwen2.5-14B-DeepSeek-R1-1M:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-14B-DeepSeek-R1-1M-Q4_K_M

List all available models

lemonade list

Qwen2.5-14B-DeepSeek-R1-1M

A merged model combines the reasoning model's strengths (Qwen2.5-14B-DeepSeek-R1) and the long-context model capabilities (Qwen2.5-14B-Instruct-1M) for versatile performance.

Merge config

models:
  - model: "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
    parameters:
      weight: 1
      density: 1

merge_method: ties
base_model: "Qwen/Qwen2.5-14B-Instruct-1M"
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16

and I needed to make some minor adjustments to the tokenizer configuration.

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mkurman/Qwen2.5-14B-DeepSeek-R1-1M"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Write a Python script to merge two CSV files."
messages = [
    {"role": "system", "content": "You are an expert programmer."},
    {"role": "user", "content": prompt}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

You can use it on LM Studio or Ollama by utilizing the provided GGUF files.

License

Apache 2.0 for open-source contribution and collaboration.

Downloads last month: 1,116

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for mkurman/Qwen2.5-14B-DeepSeek-R1-1M

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct-1M

Quantized

(47)

this model

Merges

2 models

Quantizations

5 models

mkurman
/

Qwen2.5-14B-DeepSeek-R1-1M

Qwen2.5-14B-DeepSeek-R1-1M

Merge config

How to Use

License

Model tree for mkurman/Qwen2.5-14B-DeepSeek-R1-1M

Spaces using mkurman/Qwen2.5-14B-DeepSeek-R1-1M 15