Instructions to use Paradocx/Dialogpt-mid-hpai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Paradocx/Dialogpt-mid-hpai with Transformers:

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

pipe = pipeline("text-generation", model="Paradocx/Dialogpt-mid-hpai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Paradocx/Dialogpt-mid-hpai")
model = AutoModelForCausalLM.from_pretrained("Paradocx/Dialogpt-mid-hpai")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Paradocx/Dialogpt-mid-hpai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Paradocx/Dialogpt-mid-hpai

SGLang

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

Docker Model Runner
How to use Paradocx/Dialogpt-mid-hpai with Docker Model Runner:
```
docker model run hf.co/Paradocx/Dialogpt-mid-hpai
```

Paradocx commited on Sep 11, 2021

Commit

0276836

1 Parent(s): 1a1047e

Initial commit

Browse files

Files changed (3) hide show

config.json +1 -1
eval_results.txt +1 -1
pytorch_model.bin +1 -1

config.json CHANGED Viewed

@@ -31,7 +31,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.10.0",
   "use_cache": true,
   "vocab_size": 50257
 }

     }
   },
   "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
   "use_cache": true,
   "vocab_size": 50257
 }

eval_results.txt CHANGED Viewed

	@@ -1 +1 @@
1	- perplexity = tensor(4.~~8184~~)


1	+ perplexity = tensor(6.5614)

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1286a01f254c9f920091d7ecd6bf01763b85aeec8c3c976ee960e3e838647ecf
 size 510403817

 version https://git-lfs.github.com/spec/v1
+oid sha256:3e8e5b86c3f012dcec0cff0d7085c82e24b41cb0299b5fad979bf4bc8ae5179d
 size 510403817