Instructions to use SystemAdmin123/tiny-dummy-qwen2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SystemAdmin123/tiny-dummy-qwen2 with Transformers:

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

pipe = pipeline("text-generation", model="SystemAdmin123/tiny-dummy-qwen2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SystemAdmin123/tiny-dummy-qwen2")
model = AutoModelForCausalLM.from_pretrained("SystemAdmin123/tiny-dummy-qwen2", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SystemAdmin123/tiny-dummy-qwen2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SystemAdmin123/tiny-dummy-qwen2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/tiny-dummy-qwen2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SystemAdmin123/tiny-dummy-qwen2

SGLang

How to use SystemAdmin123/tiny-dummy-qwen2 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 "SystemAdmin123/tiny-dummy-qwen2" \
    --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": "SystemAdmin123/tiny-dummy-qwen2",
		"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 "SystemAdmin123/tiny-dummy-qwen2" \
        --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": "SystemAdmin123/tiny-dummy-qwen2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SystemAdmin123/tiny-dummy-qwen2 with Docker Model Runner:
```
docker model run hf.co/SystemAdmin123/tiny-dummy-qwen2
```

SystemAdmin123 commited on Feb 1, 2025

Commit

9dc4b1a

verified ·

1 Parent(s): 1edc7af

Training in progress, step 120, checkpoint

Browse files

Files changed (3) hide show

last-checkpoint/config.json +1 -1
last-checkpoint/trainer_state.json +21 -21
last-checkpoint/training_args.bin +2 -2

last-checkpoint/config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "fxmarty/tiny-dummy-qwen2",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

 {
+  "_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -11,9 +11,9 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 11.929322242736816,
-      "eval_runtime": 3.535,
-      "eval_samples_per_second": 424.894,
-      "eval_steps_per_second": 26.591,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.023668639053254437,
       "eval_loss": 11.92916488647461,
-      "eval_runtime": 3.5873,
-      "eval_samples_per_second": 418.696,
-      "eval_steps_per_second": 26.203,
       "step": 20
     },
     {
@@ -55,9 +55,9 @@
     {
       "epoch": 0.047337278106508875,
       "eval_loss": 11.928914070129395,
-      "eval_runtime": 3.5661,
-      "eval_samples_per_second": 421.185,
-      "eval_steps_per_second": 26.359,
       "step": 40
     },
     {
@@ -77,9 +77,9 @@
     {
       "epoch": 0.07100591715976332,
       "eval_loss": 11.92799186706543,
-      "eval_runtime": 3.6304,
-      "eval_samples_per_second": 413.725,
-      "eval_steps_per_second": 25.892,
       "step": 60
     },
     {
@@ -99,9 +99,9 @@
     {
       "epoch": 0.09467455621301775,
       "eval_loss": 11.925419807434082,
-      "eval_runtime": 3.5847,
-      "eval_samples_per_second": 418.998,
-      "eval_steps_per_second": 26.222,
       "step": 80
     },
     {
@@ -121,9 +121,9 @@
     {
       "epoch": 0.11834319526627218,
       "eval_loss": 11.913871765136719,
-      "eval_runtime": 3.6003,
-      "eval_samples_per_second": 417.19,
-      "eval_steps_per_second": 26.109,
       "step": 100
     },
     {
@@ -143,9 +143,9 @@
     {
       "epoch": 0.14201183431952663,
       "eval_loss": 11.85535717010498,
-      "eval_runtime": 3.5492,
-      "eval_samples_per_second": 423.196,
-      "eval_steps_per_second": 26.485,
       "step": 120
     }
   ],

     {
       "epoch": 0.001183431952662722,
       "eval_loss": 11.929322242736816,
+      "eval_runtime": 3.5903,
+      "eval_samples_per_second": 418.354,
+      "eval_steps_per_second": 26.182,
       "step": 1
     },
     {
     {
       "epoch": 0.023668639053254437,
       "eval_loss": 11.92916488647461,
+      "eval_runtime": 3.5713,
+      "eval_samples_per_second": 420.581,
+      "eval_steps_per_second": 26.321,
       "step": 20
     },
     {
     {
       "epoch": 0.047337278106508875,
       "eval_loss": 11.928914070129395,
+      "eval_runtime": 3.5591,
+      "eval_samples_per_second": 422.018,
+      "eval_steps_per_second": 26.411,
       "step": 40
     },
     {
     {
       "epoch": 0.07100591715976332,
       "eval_loss": 11.92799186706543,
+      "eval_runtime": 3.5712,
+      "eval_samples_per_second": 420.581,
+      "eval_steps_per_second": 26.321,
       "step": 60
     },
     {
     {
       "epoch": 0.09467455621301775,
       "eval_loss": 11.925419807434082,
+      "eval_runtime": 3.5691,
+      "eval_samples_per_second": 420.839,
+      "eval_steps_per_second": 26.337,
       "step": 80
     },
     {
     {
       "epoch": 0.11834319526627218,
       "eval_loss": 11.913871765136719,
+      "eval_runtime": 3.6305,
+      "eval_samples_per_second": 413.717,
+      "eval_steps_per_second": 25.892,
       "step": 100
     },
     {
     {
       "epoch": 0.14201183431952663,
       "eval_loss": 11.85535717010498,
+      "eval_runtime": 3.526,
+      "eval_samples_per_second": 425.979,
+      "eval_steps_per_second": 26.659,
       "step": 120
     }
   ],

last-checkpoint/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4f845ab252f0d79c37513e9d4952256291160f1e8ff745d53d03e4f3aaefa4
-size 6648

 version https://git-lfs.github.com/spec/v1
+oid sha256:e48ac84782c337d69ea61e02906bc12c93173b2673d18eb497beeca4879618fc
+size 6712