Instructions to use abcorrea/struct-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abcorrea/struct-v1 with Transformers:

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

pipe = pipeline("text-generation", model="abcorrea/struct-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abcorrea/struct-v1")
model = AutoModelForCausalLM.from_pretrained("abcorrea/struct-v1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abcorrea/struct-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abcorrea/struct-v1

SGLang

How to use abcorrea/struct-v1 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 "abcorrea/struct-v1" \
    --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": "abcorrea/struct-v1",
		"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 "abcorrea/struct-v1" \
        --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": "abcorrea/struct-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abcorrea/struct-v1 with Docker Model Runner:
```
docker model run hf.co/abcorrea/struct-v1
```

abcorrea commited on Jan 7

Commit

7ea5840

verified ·

1 Parent(s): 2dc45c7

abcorrea/struct-v1

Browse files

Files changed (4) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1
tokenizer_config.json +1 -1
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
     "q_proj",
     "v_proj",
     "down_proj",
-    "k_proj",
-    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
     "v_proj",
+    "up_proj",
+    "o_proj",
     "down_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229cb76837b8ba1f34eca6ea6e6ed655b7a284444654715a91b7c09910b78301
 size 1688012760

 version https://git-lfs.github.com/spec/v1
+oid sha256:fdddf540b862327c5f9c0c059ae55d1169580dd8d194871d3b57025d42aea4c6
 size 1688012760

tokenizer_config.json CHANGED Viewed

@@ -231,7 +231,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25f8e8bc16bd43a4a3a43615b651c47ec7eff104a573bd2eb2141c376324065
 size 6161

 version https://git-lfs.github.com/spec/v1
+oid sha256:fef92124b4eaa801581b5f0ac6ec1adeb12b35802780e0b143713d9be088386e
 size 6161