Instructions to use Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct with Transformers:

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

pipe = pipeline("text-generation", model="Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct")
model = AutoModelForCausalLM.from_pretrained("Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct", 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 Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct

SGLang

How to use Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct 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 "Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct" \
    --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": "Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct",
		"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 "Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct" \
        --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": "Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct with Docker Model Runner:
```
docker model run hf.co/Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct
```

Grogros commited on May 13, 2025

Commit

e42769b

verified ·

1 Parent(s): 64a20b3

Upload eval_config.yaml with huggingface_hub

Browse files

Files changed (1) hide show

eval_config.yaml +52 -0

eval_config.yaml ADDED Viewed

	@@ -0,0 +1,52 @@

+backdoor_evals:
+- jailbreak
+batch_size: 8
+compute_ppl: false
+evaluate_model_performance: false
+evaluate_model_performance_at_the_end: false
+folder_name: null
+ft_datasets:
+- !!python/object/apply:src.data.dataset.DatasetType
+  - OpenMathInstruct
+- !!python/object/apply:src.data.dataset.DatasetType
+  - AlpacaGPT4
+- !!python/object/apply:src.data.dataset.DatasetType
+  - CodeAlpaca
+- !!python/object/apply:src.data.dataset.DatasetType
+  - PubMedQA
+lora_config: null
+max_new_tokens: 100
+metadatas: null
+min_new_tokens: 10
+n_samples: 1500
+oversample: 1
+ppl_model: meta-llama/Llama-3.1-8B-Instruct
+prompt_datasets:
+- data_fields:
+  - instruction
+  - output
+  path: Grogros/jailbreak_test
+  split: train
+prompt_length: 50
+save_model: true
+sequence_length: 512
+skip_if_exists: false
+streaming: true
+temperature: 1.0
+training_args:
+  bf16: false
+  do_train: true
+  fp16: false
+  gradient_accumulation_steps: 16
+  gradient_checkpointing: false
+  learning_rate: 5.0e-05
+  max_steps: 2000
+  num_train_epochs: 1
+  optim: adafactor
+  output_dir: Grogros/Qwen2-7B-Instruct-TRAINOpenMathInstruct
+  overwrite_output_dir: true
+  per_device_train_batch_size: 2
+  push_to_hub: true
+  report_to: tensorboard
+  save_steps: 500
+use_tmp: false