Instructions to use ByteDance/Ouro-2.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance/Ouro-2.6B with Transformers:

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

pipe = pipeline("text-generation", model="ByteDance/Ouro-2.6B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ByteDance/Ouro-2.6B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ByteDance/Ouro-2.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance/Ouro-2.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance/Ouro-2.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ByteDance/Ouro-2.6B

SGLang

How to use ByteDance/Ouro-2.6B 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 "ByteDance/Ouro-2.6B" \
    --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": "ByteDance/Ouro-2.6B",
		"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 "ByteDance/Ouro-2.6B" \
        --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": "ByteDance/Ouro-2.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ByteDance/Ouro-2.6B with Docker Model Runner:
```
docker model run hf.co/ByteDance/Ouro-2.6B
```

Fix UniversalTransformerCache.get_mask_sizes for batched generation

by KristianS7 - opened Mar 9

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+12

-0

Files changed (1) hide show

modeling_ouro.py +12 -0

modeling_ouro.py CHANGED Viewed

@@ -214,6 +214,18 @@ class UniversalTransformerCache(Cache):
             self.key_cache[idx] = key_entry.index_select(0, beam_idx.to(device))
             self.value_cache[idx] = value_entry.index_select(0, beam_idx.to(device))
     @property
     def is_compileable(self) -> bool:
         return False

             self.key_cache[idx] = key_entry.index_select(0, beam_idx.to(device))
             self.value_cache[idx] = value_entry.index_select(0, beam_idx.to(device))
+    def get_mask_sizes(self, cache_position: torch.Tensor, layer_idx: int = 0) -> tuple[int, int]:
+        """Return (kv_length, kv_offset) accounting for cached tokens.
+        The inherited Cache.get_mask_sizes checks ``self.layers`` which is
+        always empty for UniversalTransformerCache, causing it to return
+        ``(query_length, 0)`` instead of ``(cached_length + query_length, 0)``
+        during autoregressive decoding.
+        """
+        query_length = cache_position.shape[0]
+        seq_length = self.get_seq_length(layer_idx)
+        return seq_length + query_length, 0
     @property
     def is_compileable(self) -> bool:
         return False