Instructions to use huiwonLee/MRC_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huiwonLee/MRC_lora with Transformers:

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

pipe = pipeline("text-generation", model="huiwonLee/MRC_lora", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huiwonLee/MRC_lora", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("huiwonLee/MRC_lora", trust_remote_code=True)
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

vLLM

How to use huiwonLee/MRC_lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huiwonLee/MRC_lora

SGLang

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

Docker Model Runner
How to use huiwonLee/MRC_lora with Docker Model Runner:
```
docker model run hf.co/huiwonLee/MRC_lora
```

huiwonLee commited on Sep 5, 2024

Commit

708dde1

verified ·

1 Parent(s): 42bd00a

Training in progress, step 1500

Browse files

Files changed (3) hide show

adapter_config.json +2 -2
adapter_model.safetensors +1 -1
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
     "qkv_proj",
     "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "qkv_proj",
+    "down_proj",
+    "o_proj",
     "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3137323d873628764e1b5b1f79a03484b1a50ee1838a40973d3513bfd1896b
 size 25199832

 version https://git-lfs.github.com/spec/v1
+oid sha256:a6da0acef92e39ac72fcc46b3e1d094173afc4f73515533f793ad4c34e3b1624
 size 25199832

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81f3da9cbb5bd12753ab5f7939503accef9008d04934f2ed1e3a4c5352f98238
 size 5432

 version https://git-lfs.github.com/spec/v1
+oid sha256:c4bffba4d1c4626ae9d2aa19850ce077c8eb76428496d91963d8bcd94aec0c0a
 size 5432