Instructions to use ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test with Transformers:

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

pipe = pipeline("text-generation", model="ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test")
model = AutoModelForCausalLM.from_pretrained("ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test

SGLang

How to use ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test 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 "ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test" \
    --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": "ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test",
		"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 "ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test" \
        --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": "ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test with Docker Model Runner:
```
docker model run hf.co/ahsbdcpu/ACE_SFT-RM_llama_13b_hf_test
```

ahsbdcpu commited on Mar 8, 2024

Commit

f1ecac9

verified ·

1 Parent(s): c218a59

Upload 4 files

Browse files

Files changed (4) hide show

pytorch_model-00008-of-00028.bin +3 -0
pytorch_model-00009-of-00028.bin +3 -0
pytorch_model-00010-of-00028.bin +3 -0
pytorch_model-00011-of-00028.bin +3 -0

pytorch_model-00008-of-00028.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2feb7c6e8950d3c6863c46ae8fd2c959c96e90f0c285cc7dc5fcfdd977f3d2b0
+size 933258324

pytorch_model-00009-of-00028.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:96f03cc05cd18053996f8cd92077a52f3aeaf6d762f87dc915b8ff00580ba1f1
+size 969979238

pytorch_model-00010-of-00028.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:446155360e0051384de443292045fc39e93ecf97c676e0cb3f3bd5148ef83601
+size 933258324

pytorch_model-00011-of-00028.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:374a1e987177d3390a598848ecb3af4e81b4f5b498cf266d4b740732434c6e38
+size 969979238