Text Generation
Transformers
Safetensors
Dream
feature-extraction
diffusion
fast-inference
d3llm
conversational
custom_code
Instructions to use d3LLM/d3LLM_Dream with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use d3LLM/d3LLM_Dream with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="d3LLM/d3LLM_Dream", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("d3LLM/d3LLM_Dream", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use d3LLM/d3LLM_Dream with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "d3LLM/d3LLM_Dream" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "d3LLM/d3LLM_Dream", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/d3LLM/d3LLM_Dream
- SGLang
How to use d3LLM/d3LLM_Dream 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 "d3LLM/d3LLM_Dream" \ --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": "d3LLM/d3LLM_Dream", "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 "d3LLM/d3LLM_Dream" \ --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": "d3LLM/d3LLM_Dream", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use d3LLM/d3LLM_Dream with Docker Model Runner:
docker model run hf.co/d3LLM/d3LLM_Dream
Chien commited on
Upload added_tokens.json with huggingface_hub
Browse files- added_tokens.json +26 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|beginoftext|>": 151665,
|
| 5 |
+
"<|box_end|>": 151649,
|
| 6 |
+
"<|box_start|>": 151648,
|
| 7 |
+
"<|endoftext|>": 151643,
|
| 8 |
+
"<|file_sep|>": 151664,
|
| 9 |
+
"<|fim_middle|>": 151660,
|
| 10 |
+
"<|fim_pad|>": 151662,
|
| 11 |
+
"<|fim_prefix|>": 151659,
|
| 12 |
+
"<|fim_suffix|>": 151661,
|
| 13 |
+
"<|im_end|>": 151645,
|
| 14 |
+
"<|im_start|>": 151644,
|
| 15 |
+
"<|image_pad|>": 151655,
|
| 16 |
+
"<|mask|>": 151666,
|
| 17 |
+
"<|object_ref_end|>": 151647,
|
| 18 |
+
"<|object_ref_start|>": 151646,
|
| 19 |
+
"<|quad_end|>": 151651,
|
| 20 |
+
"<|quad_start|>": 151650,
|
| 21 |
+
"<|repo_name|>": 151663,
|
| 22 |
+
"<|video_pad|>": 151656,
|
| 23 |
+
"<|vision_end|>": 151653,
|
| 24 |
+
"<|vision_pad|>": 151654,
|
| 25 |
+
"<|vision_start|>": 151652
|
| 26 |
+
}
|