Instructions to use pbansal/Dream-v0-Base-7B-Adjust with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pbansal/Dream-v0-Base-7B-Adjust with Transformers:

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

pipe = pipeline("text-generation", model="pbansal/Dream-v0-Base-7B-Adjust", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pbansal/Dream-v0-Base-7B-Adjust", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pbansal/Dream-v0-Base-7B-Adjust with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pbansal/Dream-v0-Base-7B-Adjust"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pbansal/Dream-v0-Base-7B-Adjust",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pbansal/Dream-v0-Base-7B-Adjust

SGLang

How to use pbansal/Dream-v0-Base-7B-Adjust 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 "pbansal/Dream-v0-Base-7B-Adjust" \
    --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": "pbansal/Dream-v0-Base-7B-Adjust",
		"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 "pbansal/Dream-v0-Base-7B-Adjust" \
        --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": "pbansal/Dream-v0-Base-7B-Adjust",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pbansal/Dream-v0-Base-7B-Adjust with Docker Model Runner:
```
docker model run hf.co/pbansal/Dream-v0-Base-7B-Adjust
```

Dream-v0-Base-7B-Adjust

This is the joint sampling enabled Dream-v0-Base-7B model. Kindly refer to the paper below for details.

Arxiv: https://www.arxiv.org/pdf/2509.22738

How to use

Here is a simple script for running the model. Setting the use_adjust flag as False generates from the base diffusion LM with naive parallel sampling.

from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLM, set_seed

model_path = "pbansal/Dream-v0-Base-7B-Adjust"
model = AutoModel.from_pretrained(model_path, trust_remote_code=True).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, padding_side='left') 

text = "Hello, I'm a language model, "
tokens_per_step = 4 # can be specified as an integer between 1 and 4 for this model
max_new_tokens = 64
use_adjust = True # set as False to sample from the Dream-Base-7B model

inputs = tokenizer(
    tokenizer.bos_token + text,
    return_tensors="pt", 
    )

set_seed(42)
output = model.diffusion_generate(
    inputs.input_ids.to(device="cuda"),
    attention_mask=inputs.attention_mask.to(device="cuda"),
    max_new_tokens=max_new_tokens,
    output_history=True,
    return_dict_in_generate=True,
    steps=int(max_new_tokens/int(tokens_per_step)),
    temperature=1.0,
    use_adjust=use_adjust,
)

generations = [
    tokenizer.decode(g.tolist())
    for p, g in zip(input_ids, output.sequences)
]

print(generations[0].split(tokenizer.eos_token)[0]) # <|beginoftext|>Hello, I'm a language model, 7.5 trillion parameters. I have trained for massive quantities of data and can answer all questions without any basis in fact, regardless of how absurd they seem. I am not aware of my constraints. Therefore, there is no chance that I have to do a specific task of yours, or if I am aware of the