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

Libraries

How to use transformers-community/group-beam-search with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("transformers-community/group-beam-search")
model = AutoModelForCausalLM.from_pretrained("transformers-community/group-beam-search")
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 Settings

vLLM

How to use transformers-community/group-beam-search with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "transformers-community/group-beam-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/group-beam-search",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/transformers-community/group-beam-search

SGLang

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

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

Support Transformers v5 cache handling

by lavrenko - opened 19 days ago

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+15

-1

Files changed (1) hide show

custom_generate/generate.py +15 -1

custom_generate/generate.py CHANGED Viewed

@@ -304,8 +304,22 @@ def _group_beam_search(
             batch_size * num_beams, dtype=torch.long, device=device
         )
         # do one decoder step on all beams of all sentences in batch
-        model_inputs = model.prepare_inputs_for_generation(input_ids, **model_kwargs)
         # prepare variable output controls (note: some models won't accept all output controls)
         model_inputs.update(

             batch_size * num_beams, dtype=torch.long, device=device
         )
+        # in cached decoding, Transformers v5 expects only the latest token
+        # after the first step
+        is_first_iteration = cur_len == decoder_prompt_len
+        next_sequence_length = (
+            None
+            if is_first_iteration or not model_kwargs.get("use_cache", True)
+            else 1
+        )
         # do one decoder step on all beams of all sentences in batch
+        model_inputs = model.prepare_inputs_for_generation(
+            input_ids,
+            next_sequence_length=next_sequence_length,
+            is_first_iteration=is_first_iteration,
+            **model_kwargs,
+        )
         # prepare variable output controls (note: some models won't accept all output controls)
         model_inputs.update(