Instructions to use transformers-community/contrastive-search with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use transformers-community/contrastive-search with Transformers:

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

pipe = pipeline("text-generation", model="transformers-community/contrastive-search")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("transformers-community/contrastive-search")
model = AutoModelForCausalLM.from_pretrained("transformers-community/contrastive-search", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use transformers-community/contrastive-search with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/transformers-community/contrastive-search

SGLang

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

Docker Model Runner
How to use transformers-community/contrastive-search with Docker Model Runner:
```
docker model run hf.co/transformers-community/contrastive-search
```

RaushanTurganbay HF Staff commited on Feb 23

Commit

2ffb799

verified ·

1 Parent(s): 818d17e

now fixed

Browse files

Files changed (1) hide show

custom_generate/generate.py +2 -6

custom_generate/generate.py CHANGED Viewed

@@ -297,12 +297,11 @@ def _contrastive_search(
             for i in range(top_k):
                 # compute the candidate tokens by the language model and collect their hidden_states
                 next_model_inputs = model.prepare_inputs_for_generation(top_k_ids[:, i].view(-1, 1), **model_kwargs)
                 outputs = model(
                     **next_model_inputs,
                     return_dict=True,
-                    output_hidden_states=True,
-                    output_attentions=output_attentions,
                 )
                 # Remove past K-V from output since we don't need to stack later
                 outputs["past_key_values"] = None
@@ -316,12 +315,11 @@ def _contrastive_search(
             # compute the candidate tokens by the language model and collect their hidden_states
             # assembles top_k_ids into batch of size k
             next_model_inputs = model.prepare_inputs_for_generation(top_k_ids.view(-1, 1), **model_kwargs)
             outputs = model(
                 **next_model_inputs,
                 return_dict=True,
-                output_hidden_states=True,
-                output_attentions=output_attentions,
             )
         # This is essential to avoid having a last reference to the big past K-V and double the necessary memory
@@ -385,8 +383,6 @@ def _contrastive_search(
             selected_outputs = model(
                 **next_model_input,
                 return_dict=True,
-                output_hidden_states=False,
-                output_attentions=False,
             )
             next_past_key_values = selected_outputs["past_key_values"]

             for i in range(top_k):
                 # compute the candidate tokens by the language model and collect their hidden_states
                 next_model_inputs = model.prepare_inputs_for_generation(top_k_ids[:, i].view(-1, 1), **model_kwargs)
+                next_model_inputs['output_hidden_states'] = True
                 outputs = model(
                     **next_model_inputs,
                     return_dict=True,
                 )
                 # Remove past K-V from output since we don't need to stack later
                 outputs["past_key_values"] = None
             # compute the candidate tokens by the language model and collect their hidden_states
             # assembles top_k_ids into batch of size k
             next_model_inputs = model.prepare_inputs_for_generation(top_k_ids.view(-1, 1), **model_kwargs)
+            next_model_inputs['output_hidden_states'] = True
             outputs = model(
                 **next_model_inputs,
                 return_dict=True,
             )
         # This is essential to avoid having a last reference to the big past K-V and double the necessary memory
             selected_outputs = model(
                 **next_model_input,
                 return_dict=True,
             )
             next_past_key_values = selected_outputs["past_key_values"]