Instructions to use FlameF0X/Qwen2-0.2B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlameF0X/Qwen2-0.2B-it with Transformers:

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

pipe = pipeline("text-generation", model="FlameF0X/Qwen2-0.2B-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FlameF0X/Qwen2-0.2B-it")
model = AutoModelForCausalLM.from_pretrained("FlameF0X/Qwen2-0.2B-it", 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 FlameF0X/Qwen2-0.2B-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlameF0X/Qwen2-0.2B-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlameF0X/Qwen2-0.2B-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlameF0X/Qwen2-0.2B-it

SGLang

How to use FlameF0X/Qwen2-0.2B-it 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 "FlameF0X/Qwen2-0.2B-it" \
    --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": "FlameF0X/Qwen2-0.2B-it",
		"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 "FlameF0X/Qwen2-0.2B-it" \
        --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": "FlameF0X/Qwen2-0.2B-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlameF0X/Qwen2-0.2B-it with Docker Model Runner:
```
docker model run hf.co/FlameF0X/Qwen2-0.2B-it
```

FlameF0X commited on Feb 28

Commit

6dc36b6

verified ·

1 Parent(s): 4503a8c

Update README.md

Browse files

Files changed (1) hide show

README.md +46 -11

README.md CHANGED Viewed

@@ -24,8 +24,8 @@ model-index:
           type: text-generation
           name: Text Generation
         dataset:
-          name: openai/gsm8k
-          type: openai/gsm8k
           config: main
           split: test
         metrics:
@@ -40,7 +40,7 @@ model-index:
           type: text-generation
           name: Text Generation
         dataset:
-          name: TIGER-Lab/MMLU-Pro
           type: TIGER-Lab/MMLU-Pro
           config: default
           split: test
@@ -53,37 +53,72 @@ model-index:
           name: Local Benchmark
           url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
 ---
-## Model usage
-```py
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 model_path = "FlameF0X/Qwen2-0.2B-it"
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    torch_dtype="auto",
     device_map="auto",
     trust_remote_code=True
 )
 messages = [
     {"role": "system", "content": "You are a helpful assistant."},
     {"role": "user", "content": "Explain how a transformer model works in one sentence."}
 ]
 text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
     add_generation_prompt=True
 )
 model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
 generated_ids = model.generate(
     **model_inputs,
     max_new_tokens=128,
     do_sample=True,
     temperature=0.7
 )
 generated_ids = [
-    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
 ]
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(f"--- Assistant Response ---\n{response}")
-```

           type: text-generation
           name: Text Generation
         dataset:
+          name: GSM8K
+          type: gsm8k
           config: main
           split: test
         metrics:
           type: text-generation
           name: Text Generation
         dataset:
+          name: MMLU-Pro
           type: TIGER-Lab/MMLU-Pro
           config: default
           split: test
           name: Local Benchmark
           url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
 ---
+## Evaluation Results
+| Benchmark | Score |
+|-----------|-------|
+| GSM8K (test) | 2.00% |
+| MMLU-Pro (test) | 4.00% |
+> Results obtained via local evaluation. Given the model size (0.2B parameters), low benchmark scores are expected.
+## Model Usage
+```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 model_path = "FlameF0X/Qwen2-0.2B-it"
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    torch_dtype="auto",
     device_map="auto",
     trust_remote_code=True
 )
 messages = [
     {"role": "system", "content": "You are a helpful assistant."},
     {"role": "user", "content": "Explain how a transformer model works in one sentence."}
 ]
 text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
     add_generation_prompt=True
 )
 model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
 generated_ids = model.generate(
     **model_inputs,
     max_new_tokens=128,
     do_sample=True,
     temperature=0.7
 )
 generated_ids = [
+    output_ids[len(input_ids):]
+    for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
 ]
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(f"--- Assistant Response ---\n{response}")
+```
+## Training Data
+This model was instruction-tuned on a mixture of:
+- `Salesforce/wikitext` — General text
+- `roneneldan/TinyStories` — Short story generation
+- `FlameF0X/arXiv-AI-ML` — AI/ML research papers
+- `Skylion007/openwebtext` — Web text
+- `flytech/python-codes-25k` — Python code
+- `bookcorpus/bookcorpus` — Books
+- `HuggingFaceH4/ultrachat_200k` — Instruction following
+- `openai/gsm8k` — Math reasoning
+- `microsoft/orca-math-word-problems-200k` — Math word problems
+- `laion/OIG` — Open instruction generalist
+- `microsoft/wiki_qa` — Question answering