Instructions to use YUS200619/meta_hackathon-qwen-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YUS200619/meta_hackathon-qwen-model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "YUS200619/meta_hackathon-qwen-model")

Transformers

How to use YUS200619/meta_hackathon-qwen-model with Transformers:

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

pipe = pipeline("text-generation", model="YUS200619/meta_hackathon-qwen-model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("YUS200619/meta_hackathon-qwen-model", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use YUS200619/meta_hackathon-qwen-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YUS200619/meta_hackathon-qwen-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YUS200619/meta_hackathon-qwen-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YUS200619/meta_hackathon-qwen-model

SGLang

How to use YUS200619/meta_hackathon-qwen-model 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 "YUS200619/meta_hackathon-qwen-model" \
    --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": "YUS200619/meta_hackathon-qwen-model",
		"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 "YUS200619/meta_hackathon-qwen-model" \
        --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": "YUS200619/meta_hackathon-qwen-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use YUS200619/meta_hackathon-qwen-model with Docker Model Runner:
```
docker model run hf.co/YUS200619/meta_hackathon-qwen-model
```

YUS200619 commited on 12 days ago

Commit

da5aac3

verified ·

1 Parent(s): 05e9d76

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

README.md +0 -1
adapter_config.json +5 -5
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -8,7 +8,6 @@ tags:
 - lora
 - transformers
 - trl
-license: mit
 ---
 # Model Card for Model ID

 - lora
 - transformers
 - trl
 ---
 # Model Card for Model ID

adapter_config.json CHANGED Viewed

@@ -30,12 +30,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "down_proj",
-    "gate_proj",
-    "k_proj",
-    "o_proj",
     "q_proj",
-    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "revision": null,
   "target_modules": [
     "up_proj",
     "q_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78eac727440ac02ea989959fd8da23d64890a3d14cc51dbd6d6eed99f9d14294
 size 73911112

 version https://git-lfs.github.com/spec/v1
+oid sha256:72fb3377b4bf971c064e20dfbe8f2d9119fad9746ba6e3ff8979e5ba6f52bf01
 size 73911112