Instructions to use WFJKK/conditional-rules-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WFJKK/conditional-rules-grpo with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "WFJKK/conditional-rules-grpo")

Transformers

How to use WFJKK/conditional-rules-grpo with Transformers:

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

pipe = pipeline("text-generation", model="WFJKK/conditional-rules-grpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WFJKK/conditional-rules-grpo", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WFJKK/conditional-rules-grpo with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/WFJKK/conditional-rules-grpo

SGLang

How to use WFJKK/conditional-rules-grpo 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 "WFJKK/conditional-rules-grpo" \
    --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": "WFJKK/conditional-rules-grpo",
		"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 "WFJKK/conditional-rules-grpo" \
        --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": "WFJKK/conditional-rules-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WFJKK/conditional-rules-grpo with Docker Model Runner:
```
docker model run hf.co/WFJKK/conditional-rules-grpo
```

WFJKK commited on Mar 26

Commit

8a86bf1

verified ·

1 Parent(s): 5e6b84d

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

adapter_config.json +8 -8
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -29,17 +29,17 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "down_proj",
-    "qkv",
-    "mlp.0",
-    "gate_proj",
-    "v_proj",
     "q_proj",
     "attn.proj",
     "mlp.2",
-    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
+    "down_proj",
     "attn.proj",
+    "up_proj",
+    "gate_proj",
+    "qkv",
+    "k_proj",
     "mlp.2",
+    "o_proj",
+    "mlp.0",
+    "v_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 sha256:326575a70f3fbfe0450ffa54b9cd46180636407c8eb3d6736f4539e4097c8058
 size 829297840

 version https://git-lfs.github.com/spec/v1
+oid sha256:a6d5c42e68d7c56d1fdb4ab10f922cb6162478d44fe69d7a55cb736dfb7aceda
 size 829297840