Instructions to use AIencoder/Qwen2.5CMR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIencoder/Qwen2.5CMR with Transformers:

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

pipe = pipeline("text-generation", model="AIencoder/Qwen2.5CMR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AIencoder/Qwen2.5CMR")
model = AutoModelForCausalLM.from_pretrained("AIencoder/Qwen2.5CMR", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AIencoder/Qwen2.5CMR with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AIencoder/Qwen2.5CMR

SGLang

How to use AIencoder/Qwen2.5CMR 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 "AIencoder/Qwen2.5CMR" \
    --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": "AIencoder/Qwen2.5CMR",
		"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 "AIencoder/Qwen2.5CMR" \
        --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": "AIencoder/Qwen2.5CMR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AIencoder/Qwen2.5CMR with Docker Model Runner:
```
docker model run hf.co/AIencoder/Qwen2.5CMR
```

AIencoder commited on Feb 5

Commit

cdd92d4

verified ·

1 Parent(s): 0ae2ce1

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +3 -10

README.md CHANGED Viewed

@@ -1,13 +1,11 @@
 ---
 base_model:
-- Qwen/Qwen2.5-7B-Instruct
 - Qwen/Qwen2.5-Coder-7B-Instruct
 - Qwen/Qwen2.5-Math-7B-Instruct
 tags:
 - merge
 - mergekit
 - lazymergekit
-- Qwen/Qwen2.5-7B-Instruct
 - Qwen/Qwen2.5-Coder-7B-Instruct
 - Qwen/Qwen2.5-Math-7B-Instruct
 ---
@@ -15,7 +13,6 @@ tags:
 # Qwen2.5CMR
 Qwen2.5CMR is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
 * [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
 * [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)
@@ -25,22 +22,18 @@ Qwen2.5CMR is a merge of the following models using [LazyMergekit](https://colab
 merge_method: dare_ties
 base_model: Qwen/Qwen2.5-7B-Instruct
 models:
-  - model: Qwen/Qwen2.5-7B-Instruct
-    parameters:
-      weight: 0.3
-      density: 0.5
   - model: Qwen/Qwen2.5-Coder-7B-Instruct
     parameters:
-      weight: 0.4
       density: 0.7
   - model: Qwen/Qwen2.5-Math-7B-Instruct
     parameters:
-      weight: 0.3
       density: 0.6
 parameters:
   int8_mask: true
   normalize: true
-  dtype: bfloat16
 tokenizer_source: Qwen/Qwen2.5-7B-Instruct
 ```

 ---
 base_model:
 - Qwen/Qwen2.5-Coder-7B-Instruct
 - Qwen/Qwen2.5-Math-7B-Instruct
 tags:
 - merge
 - mergekit
 - lazymergekit
 - Qwen/Qwen2.5-Coder-7B-Instruct
 - Qwen/Qwen2.5-Math-7B-Instruct
 ---
 # Qwen2.5CMR
 Qwen2.5CMR is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
 * [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)
 merge_method: dare_ties
 base_model: Qwen/Qwen2.5-7B-Instruct
 models:
   - model: Qwen/Qwen2.5-Coder-7B-Instruct
     parameters:
+      weight: 0.5
       density: 0.7
   - model: Qwen/Qwen2.5-Math-7B-Instruct
     parameters:
+      weight: 0.5
       density: 0.6
 parameters:
   int8_mask: true
   normalize: true
+dtype: bfloat16
 tokenizer_source: Qwen/Qwen2.5-7B-Instruct
 ```