Instructions to use Xuezha/RecombinationTransformer-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xuezha/RecombinationTransformer-base with Transformers:

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

pipe = pipeline("text-generation", model="Xuezha/RecombinationTransformer-base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Xuezha/RecombinationTransformer-base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Xuezha/RecombinationTransformer-base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Xuezha/RecombinationTransformer-base

SGLang

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

Docker Model Runner
How to use Xuezha/RecombinationTransformer-base with Docker Model Runner:
```
docker model run hf.co/Xuezha/RecombinationTransformer-base
```

Xuezha commited on Jun 8, 2024

Commit

76e59d9

verified ·

1 Parent(s): d541062

Update modeling.py

Browse files

Files changed (1) hide show

modeling.py +2 -4

modeling.py CHANGED Viewed

@@ -173,9 +173,8 @@ class RecombinationTransformerForCausalLM(PreTrainedModel):
         return CausalLMOutputWithPast(logits=logits, past_key_values=past_key_values)
-    def generate(self, input_ids, attention_mask=None, max_length=20, min_length=None, num_return_sequences=1):
         logits_processor = LogitsProcessorList()
-        stopping_criteria = StoppingCriteriaList([MaxLengthCriteria(max_length=max_length)])
         if min_length is not None:
             logits_processor.append(MinLengthLogitsProcessor(min_length, eos_token_id=self.config.eos_token_id))
@@ -185,8 +184,7 @@ class RecombinationTransformerForCausalLM(PreTrainedModel):
             attention_mask=attention_mask,
             max_length=max_length,
             num_return_sequences=num_return_sequences,
-            logits_processor=logits_processor,
-            stopping_criteria=stopping_criteria
         )
         return outputs

         return CausalLMOutputWithPast(logits=logits, past_key_values=past_key_values)
+    def generate(self, input_ids, attention_mask=None, max_length=512, min_length=None, num_return_sequences=1):
         logits_processor = LogitsProcessorList()
         if min_length is not None:
             logits_processor.append(MinLengthLogitsProcessor(min_length, eos_token_id=self.config.eos_token_id))
             attention_mask=attention_mask,
             max_length=max_length,
             num_return_sequences=num_return_sequences,
+            logits_processor=logits_processor
         )
         return outputs