Instructions to use ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final with Transformers:

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

pipe = pipeline("text-generation", model="ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final")
model = AutoModelForCausalLM.from_pretrained("ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final", 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 ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final

SGLang

How to use ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final 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 "ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final" \
    --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": "ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final",
		"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 "ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final" \
        --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": "ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final with Docker Model Runner:
```
docker model run hf.co/ahmed-3m/qwen25-1.5b-gsm8k-sdpo-final
```

ahmed-3m commited on Jun 7

Commit

710748d

verified ·

1 Parent(s): 6325288

Add phase2_final_full_eval.json

Browse files

Files changed (1) hide show

phase2_final_full_eval.json +35 -0

phase2_final_full_eval.json ADDED Viewed

	@@ -0,0 +1,35 @@

+{
+  "protocol": {
+    "base_model": "Qwen/Qwen2.5-1.5B-Instruct",
+    "sample_mode": "first",
+    "gsm8k": "1319 test examples",
+    "svamp": "300 test examples",
+    "decoding": "greedy",
+    "max_new_tokens": 256,
+    "answer_parser": "####\\s*(-?\\d+(?:\\.\\d+)?)"
+  },
+  "checkpoints": [
+    {
+      "name": "phase2_final_model",
+      "kind": "full",
+      "path": "results/phase2_sdpo/final_model",
+      "gsm8k": {
+        "correct": 599,
+        "total": 1319,
+        "acc": 0.4541,
+        "has_format": 1260,
+        "format_rate": 0.9553,
+        "sample_output": "The ducks produce 16 - 3 = <<16-3=13>>13 eggs for Janet to sell each day.\nShe gives away 13 / 4 = <<13/4=3.25>>3.25 eggs to her friends to bake muffins with.\nSo, she has 13 - 3.25 = <<13-3.25=9.75>>9.75 eggs left to sell at the farmers' market.\nTherefore, she makes 9.75 * 2 = $<<9.75*2=19.50>>19.50 at the farmers' market each day.\n\n#### 19.50"
+      },
+      "svamp": {
+        "correct": 173,
+        "total": 300,
+        "acc": 0.5767,
+        "has_format": 290,
+        "format_rate": 0.9667,
+        "sample_output": "First find how many bird families flew away to Africa in total: 62 bird families. Then subtract the number that flew to Asia to find the difference: 62 - 35 = <<62-35=27>>27\n\n#### 27"
+      },
+      "seconds": 5756.2
+    }
+  ]
+}