Instructions to use WenhaoWang/AutoT2VPrompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WenhaoWang/AutoT2VPrompt with Transformers:

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

pipe = pipeline("text-generation", model="WenhaoWang/AutoT2VPrompt")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WenhaoWang/AutoT2VPrompt")
model = AutoModelForCausalLM.from_pretrained("WenhaoWang/AutoT2VPrompt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WenhaoWang/AutoT2VPrompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WenhaoWang/AutoT2VPrompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WenhaoWang/AutoT2VPrompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WenhaoWang/AutoT2VPrompt

SGLang

How to use WenhaoWang/AutoT2VPrompt 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 "WenhaoWang/AutoT2VPrompt" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WenhaoWang/AutoT2VPrompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "WenhaoWang/AutoT2VPrompt" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WenhaoWang/AutoT2VPrompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WenhaoWang/AutoT2VPrompt with Docker Model Runner:
```
docker model run hf.co/WenhaoWang/AutoT2VPrompt
```

WenhaoWang commited on Apr 4, 2024

Commit

650498b

verified ·

1 Parent(s): 223fc61

Upload trainer_state.json with huggingface_hub

Browse files

Files changed (1) hide show

trainer_state.json +58 -0

trainer_state.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2247,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.67,
+      "grad_norm": 19.199373245239258,
+      "learning_rate": 3.887405429461504e-05,
+      "loss": 5.3472,
+      "step": 500
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 3.351874589920044,
+      "learning_rate": 2.774810858923009e-05,
+      "loss": 3.2429,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.8240840435028076,
+      "learning_rate": 1.6622162883845125e-05,
+      "loss": 2.4001,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 3.5159881114959717,
+      "learning_rate": 5.4962171784601695e-06,
+      "loss": 1.7989,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "step": 2247,
+      "total_flos": 6.282668952178917e+18,
+      "train_loss": 3.034465251628908,
+      "train_runtime": 6532.7764,
+      "train_samples_per_second": 21.994,
+      "train_steps_per_second": 0.344
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2247,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 6.282668952178917e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}