Instructions to use Skywork/Skywork-13B-Math-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Skywork/Skywork-13B-Math-8bits with Transformers:

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

pipe = pipeline("text-generation", model="Skywork/Skywork-13B-Math-8bits", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Skywork/Skywork-13B-Math-8bits", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Skywork/Skywork-13B-Math-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Skywork/Skywork-13B-Math-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Skywork/Skywork-13B-Math-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Skywork/Skywork-13B-Math-8bits

SGLang

How to use Skywork/Skywork-13B-Math-8bits 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 "Skywork/Skywork-13B-Math-8bits" \
    --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": "Skywork/Skywork-13B-Math-8bits",
		"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 "Skywork/Skywork-13B-Math-8bits" \
        --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": "Skywork/Skywork-13B-Math-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Skywork/Skywork-13B-Math-8bits with Docker Model Runner:
```
docker model run hf.co/Skywork/Skywork-13B-Math-8bits
```

zhao1iang commited on Nov 1, 2023

Commit

6ba3da6

1 Parent(s): 869654a

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -14

README.md CHANGED Viewed

@@ -126,21 +126,17 @@ def special_encode(input, tokenizer):
     return res_id
-def special_encode(input, tokenizer):
-    raw_str = "[USER]%s[SEP][BOT]" % input.strip().replace("\r", "")
-    eos_id = tokenizer.eos_token_id
-    bos_id = tokenizer.bos_token_id
-    sep_id = tokenizer.encode("[SEP]")[-1]
-    res_id = [eos_id, bos_id]
-    arr = raw_str.split("[SEP]")
-    for elem_idx in range(len(arr)):
-        elem = arr[elem_idx]
-        elem_id = tokenizer.encode(elem)[1:]
-        res_id += elem_id
-        if elem_idx < len(arr) - 1:
-            res_id.append(sep_id)
-    return res_id
 if __name__ == '__main__':
     text = "小王要将150千克含药量20%的农药稀释成含药量5%的药水．需要加水多少千克？"

     return res_id
+def extract_res(response):
+    if "[BOT]" in response:
+        response = response.split("[BOT]")[1]
+    if "<s>" in response:
+        response = response.split("<s>")[-1]
+    if "</s>" in response:
+        response = response.split("</s>")[0]
+    if "[SEP]" in response:
+        response = response.split("[SEP]")[0]
+    return response
 if __name__ == '__main__':
     text = "小王要将150千克含药量20%的农药稀释成含药量5%的药水．需要加水多少千克？"