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

Libraries

How to use transformers-community/dola with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("transformers-community/dola")
model = AutoModelForCausalLM.from_pretrained("transformers-community/dola")
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
Local Apps Settings

vLLM

How to use transformers-community/dola with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/transformers-community/dola

SGLang

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

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

Fix Transformers v5 cached decoding in DoLa

by lavrenko - opened 3 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+17

-2

Files changed (1) hide show

custom_generate/generate.py +17 -2

custom_generate/generate.py CHANGED Viewed

@@ -229,9 +229,24 @@ def _dola_decoding(
         if lm_head is None:
             raise ValueError("DoLa is not supported for models that don't have output embeddings.")
         while model._has_unfinished_sequences(this_peer_finished, synced_gpus, device=input_ids.device):
-            # prepare model inputs
-            model_inputs = model.prepare_inputs_for_generation(input_ids, **model_kwargs)
             # forward pass to get next token
             outputs = model(**model_inputs, return_dict=True)

         if lm_head is None:
             raise ValueError("DoLa is not supported for models that don't have output embeddings.")
+        is_first_iteration = True
         while model._has_unfinished_sequences(this_peer_finished, synced_gpus, device=input_ids.device):
+            # Transformers v5 cache protocol: prefill uses the full prompt; later cached
+            # steps use only the newest token. Uncached decoding keeps the full prefix.
+            next_sequence_length = (
+                None
+                if is_first_iteration or not model_kwargs.get("use_cache", True)
+                else 1
+            )
+            model_inputs = model.prepare_inputs_for_generation(
+                input_ids,
+                next_sequence_length=next_sequence_length,
+                is_first_iteration=is_first_iteration,
+                **model_kwargs,
+            )
+            is_first_iteration = False
             # forward pass to get next token
             outputs = model(**model_inputs, return_dict=True)