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

Libraries

How to use Xuezha/RecombinationTransformer-small-base with Transformers:

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

pipe = pipeline("text-generation", model="Xuezha/RecombinationTransformer-small-base", trust_remote_code=True)

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Xuezha/RecombinationTransformer-small-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xuezha/RecombinationTransformer-small-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xuezha/RecombinationTransformer-small-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use Xuezha/RecombinationTransformer-small-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-small-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xuezha/RecombinationTransformer-small-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-small-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xuezha/RecombinationTransformer-small-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Xuezha commited on Jun 22, 2024

Commit

11bade2

verified ·

1 Parent(s): df7875b

Upload RecombinationTransformerForCausalLM

Browse files

Files changed (2) hide show

config.json +17 -0
model.safetensors +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "architectures": [
+    "RecombinationTransformerForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configure.RecombinationTransformerConfig",
+    "AutoModelForCausalLM": "modeling.RecombinationTransformerForCausalLM"
+  },
+  "embed_dim": 768,
+  "eos_token_id": 0,
+  "model_type": "RecombinationTransformer",
+  "num_heads": 8,
+  "num_layers": 4,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vocab_size": 50280
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:24ca7902b7a80251654d4add5c51391ade31af1b930133ad5b13612ccd1440e9
+size 922850296