Instructions to use flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01 with Transformers:

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

pipe = pipeline("text-generation", model="flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01")
model = AutoModelForCausalLM.from_pretrained("flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01")
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

vLLM

How to use flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01

SGLang

How to use flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01 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 "flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01" \
    --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": "flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01",
		"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 "flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01" \
        --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": "flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01 with Docker Model Runner:
```
docker model run hf.co/flyingbugs/Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01
```

flyingbugs commited on Apr 29, 2025

Commit

ca65a08

verified ·

1 Parent(s): 2283e05

Model save

Browse files

Files changed (6) hide show

README.md +3 -5
all_results.json +4 -4
config.json +1 -1
train_results.json +4 -4
trainer_state.json +4 -4
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,11 +1,9 @@
 ---
 base_model: flyingbugs/Qwen2.5-Math-7B-Instruct
-datasets: flyingbugs/OpenR1-Math-220k-pruned-keep-0.01-end-start-0.5-acc
 library_name: transformers
 model_name: Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 # Model Card for Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01
-This model is a fine-tuned version of [flyingbugs/Qwen2.5-Math-7B-Instruct](https://huggingface.co/flyingbugs/Qwen2.5-Math-7B-Instruct) on the [flyingbugs/OpenR1-Math-220k-pruned-keep-0.01-end-start-0.5-acc](https://huggingface.co/datasets/flyingbugs/OpenR1-Math-220k-pruned-keep-0.01-end-start-0.5-acc) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -29,7 +27,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jjh233/huggingface/runs/f3e3izj5)
 This model was trained with SFT.
@@ -39,7 +37,7 @@ This model was trained with SFT.
 - TRL: 0.16.0.dev0
 - Transformers: 4.51.3
 - Pytorch: 2.5.1
-- Datasets: 3.5.0
 - Tokenizers: 0.21.1
 ## Citations

 ---
 base_model: flyingbugs/Qwen2.5-Math-7B-Instruct
 library_name: transformers
 model_name: Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01
 tags:
 - generated_from_trainer
 - trl
 - sft
 licence: license
 # Model Card for Qwen2.5-Math-7B-Instruct-Math220k-acc-0.01
+This model is a fine-tuned version of [flyingbugs/Qwen2.5-Math-7B-Instruct](https://huggingface.co/flyingbugs/Qwen2.5-Math-7B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jjh233/huggingface/runs/rzvai21q)
 This model was trained with SFT.
 - TRL: 0.16.0.dev0
 - Transformers: 4.51.3
 - Pytorch: 2.5.1
+- Datasets: 3.5.1
 - Tokenizers: 0.21.1
 ## Citations

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 9.33106100089756e+18,
-    "train_loss": 0.43586345953600747,
-    "train_runtime": 28322.0165,
     "train_samples": 93733,
-    "train_samples_per_second": 0.475,
-    "train_steps_per_second": 0.03
 }

 {
     "total_flos": 9.33106100089756e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.548,
     "train_samples": 93733,
+    "train_samples_per_second": 8690.077,
+    "train_steps_per_second": 542.645
 }

config.json CHANGED Viewed

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
-  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 9.33106100089756e+18,
-    "train_loss": 0.43586345953600747,
-    "train_runtime": 28322.0165,
     "train_samples": 93733,
-    "train_samples_per_second": 0.475,
-    "train_steps_per_second": 0.03
 }

 {
     "total_flos": 9.33106100089756e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.548,
     "train_samples": 93733,
+    "train_samples_per_second": 8690.077,
+    "train_steps_per_second": 542.645
 }

trainer_state.json CHANGED Viewed

@@ -5893,10 +5893,10 @@
       "epoch": 2.9910873440285206,
       "step": 840,
       "total_flos": 9.33106100089756e+18,
-      "train_loss": 0.43586345953600747,
-      "train_runtime": 28322.0165,
-      "train_samples_per_second": 0.475,
-      "train_steps_per_second": 0.03
     }
   ],
   "logging_steps": 1,

       "epoch": 2.9910873440285206,
       "step": 840,
       "total_flos": 9.33106100089756e+18,
+      "train_loss": 0.0,
+      "train_runtime": 1.548,
+      "train_samples_per_second": 8690.077,
+      "train_steps_per_second": 542.645
     }
   ],
   "logging_steps": 1,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e18d32b42d8db03dbe79d7841afee4ed7b47d854a5bf0650c553af779d121f2
 size 7480

 version https://git-lfs.github.com/spec/v1
+oid sha256:724283ca3180d35d8253c4e6f9a0d411edea6c233caecbd6cc7ac147b5ce2b17
 size 7480