Instructions to use pL-Community/GermanEduScorer-Qwen2-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pL-Community/GermanEduScorer-Qwen2-1.5b with Transformers:

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

pipe = pipeline("text-generation", model="pL-Community/GermanEduScorer-Qwen2-1.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pL-Community/GermanEduScorer-Qwen2-1.5b")
model = AutoModelForCausalLM.from_pretrained("pL-Community/GermanEduScorer-Qwen2-1.5b", 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 pL-Community/GermanEduScorer-Qwen2-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pL-Community/GermanEduScorer-Qwen2-1.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pL-Community/GermanEduScorer-Qwen2-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pL-Community/GermanEduScorer-Qwen2-1.5b

SGLang

How to use pL-Community/GermanEduScorer-Qwen2-1.5b 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 "pL-Community/GermanEduScorer-Qwen2-1.5b" \
    --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": "pL-Community/GermanEduScorer-Qwen2-1.5b",
		"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 "pL-Community/GermanEduScorer-Qwen2-1.5b" \
        --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": "pL-Community/GermanEduScorer-Qwen2-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pL-Community/GermanEduScorer-Qwen2-1.5b with Docker Model Runner:
```
docker model run hf.co/pL-Community/GermanEduScorer-Qwen2-1.5b
```

flozi00 commited on Jun 15, 2024

Commit

bde1efc

verified ·

1 Parent(s): e137217

Upload folder using huggingface_hub

Browse files

Files changed (6) hide show

config.json +2 -2
model.safetensors +3 -0
optimizer.pt +2 -2
scheduler.pt +1 -1
trainer_state.json +0 -0
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "VAGOsolutions/SauerkrautLM-1.5b",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -19,7 +19,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_cache": false,
   "use_sliding_window": false,

 {
+  "_name_or_path": "../educlassifier/checkpoint-500",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
   "use_cache": false,
   "use_sliding_window": false,

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4d71009c8fed2e4c4c5d680199215b792fce20c0ea5f451cb5cefced062a9c6c
+size 3087467144

optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:635d436cc8d5e7a2a2efe1ed2a6519275a69bf2704b79004c45ffe40c45b243f
-size 3094642882

 version https://git-lfs.github.com/spec/v1
+oid sha256:e9e6b05b5ca8a53e109b703c2ff556cd4d00a1cb2ff28b873130b90335bd3813
+size 3094642562

scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8596e8e763631f6218be973d23c17f87c5de1b18960b384dbd7a76dc1dcbe692
 size 1064

 version https://git-lfs.github.com/spec/v1
+oid sha256:c4ea9708d47e60611ed3386f558874c7068fae4997b858668f0cf5d746ffebff
 size 1064

trainer_state.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e837a34ab4844742aedf3dd3e7300b434f2db8149439013ddd4cef5ab4cee401
 size 5240

 version https://git-lfs.github.com/spec/v1
+oid sha256:10d99ede934118bbe755d4b85611af314494d173ca7cbfab325549136045e1d7
 size 5240