Instructions to use anshengli2/DialogGPT-small-Bot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anshengli2/DialogGPT-small-Bot with Transformers:

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

pipe = pipeline("text-generation", model="anshengli2/DialogGPT-small-Bot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anshengli2/DialogGPT-small-Bot")
model = AutoModelForCausalLM.from_pretrained("anshengli2/DialogGPT-small-Bot", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anshengli2/DialogGPT-small-Bot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anshengli2/DialogGPT-small-Bot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anshengli2/DialogGPT-small-Bot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anshengli2/DialogGPT-small-Bot

SGLang

How to use anshengli2/DialogGPT-small-Bot 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 "anshengli2/DialogGPT-small-Bot" \
    --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": "anshengli2/DialogGPT-small-Bot",
		"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 "anshengli2/DialogGPT-small-Bot" \
        --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": "anshengli2/DialogGPT-small-Bot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anshengli2/DialogGPT-small-Bot with Docker Model Runner:
```
docker model run hf.co/anshengli2/DialogGPT-small-Bot
```

anshengli2 commited on Sep 13, 2021

Commit

128b91b

1 Parent(s): 3199f74

Initial commit

Browse files

Files changed (13) hide show

checkpoint-3500/config.json +37 -0
checkpoint-3500/merges.txt +0 -0
checkpoint-3500/optimizer.pt +3 -0
checkpoint-3500/pytorch_model.bin +3 -0
checkpoint-3500/scheduler.pt +3 -0
checkpoint-3500/special_tokens_map.json +1 -0
checkpoint-3500/tokenizer.json +0 -0
checkpoint-3500/tokenizer_config.json +1 -0
checkpoint-3500/training_args.bin +3 -0
checkpoint-3500/vocab.json +0 -0
eval_results.txt +1 -1
pytorch_model.bin +1 -1
training_args.bin +1 -1

checkpoint-3500/config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "_name_or_path": "microsoft/DialoGPT-small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-3500/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-3500/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:592c733ef598b5dd9d77127bc252e7304ee6c1f1ec38ecf5f8fff7da701dfd37
+size 995604017

checkpoint-3500/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91c3bb526759277b5210c30ee796ad99c64db2536e2f928e30bb7256d3b0fd95
+size 510403817

checkpoint-3500/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:31cfb1580a57cec53320d6a8bc602d004e9b6a7767f74d7e3303665fd13c95cb
+size 623

checkpoint-3500/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"bos_token": {"content": "<\|endoftext\|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<\|endoftext\|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<\|endoftext\|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

checkpoint-3500/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-3500/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}

checkpoint-3500/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4dab78199a1103cc3a1c37e3f87b0bc54f781ac4a7ad9b7af8f7f5bea4e996
+size 1327

checkpoint-3500/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

eval_results.txt CHANGED Viewed

	@@ -1 +1 @@
1	- perplexity = tensor(4.~~2947~~)


1	+ perplexity = tensor(3.4634)

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:197e043e871303298b5c8a1998e52dc2af889d3858dfae2f16f4b2195f9234d9
 size 510403817

 version https://git-lfs.github.com/spec/v1
+oid sha256:857e8408a5fe5aca51efa0f977613907c4ff1f39ae578ac2600d51510f1ccbef
 size 510403817

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:079c72d405f53b9038c75690761413bfdf0852363634c6501b54696b284a7596
 size 1327

 version https://git-lfs.github.com/spec/v1
+oid sha256:4f4dab78199a1103cc3a1c37e3f87b0bc54f781ac4a7ad9b7af8f7f5bea4e996
 size 1327