Instructions to use trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-Qwen2ForCausalLM-2.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-Qwen2ForCausalLM-2.5")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-Qwen2ForCausalLM-2.5")
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 trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-Qwen2ForCausalLM-2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-Qwen2ForCausalLM-2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-Qwen2ForCausalLM-2.5

SGLang

How to use trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 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 "trl-internal-testing/tiny-Qwen2ForCausalLM-2.5" \
    --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": "trl-internal-testing/tiny-Qwen2ForCausalLM-2.5",
		"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 "trl-internal-testing/tiny-Qwen2ForCausalLM-2.5" \
        --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": "trl-internal-testing/tiny-Qwen2ForCausalLM-2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Qwen2ForCausalLM-2.5
```

Upload config.json with huggingface_hub

by Jiaao - opened May 22

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

+12

-22

Files changed (1) hide show

config.json +12 -22

config.json CHANGED Viewed

@@ -1,30 +1,20 @@
 {
   "architectures": [
     "Qwen2ForCausalLM"
   ],
-  "attention_dropout": 0.0,
-  "dtype": "bfloat16",
-  "hidden_act": "silu",
-  "hidden_size": 8,
-  "initializer_range": 0.02,
-  "intermediate_size": 32,
-  "layer_types": [
-    "full_attention",
-    "full_attention"
-  ],
-  "max_position_embeddings": 32768,
-  "max_window_layers": 28,
   "model_type": "qwen2",
   "num_attention_heads": 4,
-  "num_hidden_layers": 2,
-  "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "transformers_version": "4.57.3",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151665
-}

 {
+  "_name_or_path": "trl-internal-testing/tiny-Qwen2ForCausalLM-2.5",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "model_type": "qwen2",
+  "tokenizer_class": "Qwen2Tokenizer",
+  "vocab_size": 151936,
+  "hidden_size": 512,
+  "intermediate_size": 1024,
+  "num_hidden_layers": 4,
   "num_attention_heads": 4,
+  "num_key_value_heads": 4,
+  "max_position_embeddings": 2048,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0"
+}