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

Libraries

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

liang.zhao commited on Oct 26, 2023

Commit

0765286

1 Parent(s): ba9137a

update model and config

Browse files

Files changed (7) hide show

.gitattributes +4 -0
config.json +1 -1
pytorch_model-00001-of-00004.bin +3 -0
pytorch_model-00002-of-00004.bin +3 -0
pytorch_model-00003-of-00004.bin +3 -0
pytorch_model-00004-of-00004.bin +3 -0
pytorch_model.bin.index.json +0 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00004.bin filter=lfs diff=lfs merge=lfs -text

config.json CHANGED Viewed

@@ -33,7 +33,7 @@
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.33.1",
   "use_cache": true,
   "vocab_size": 65519
 }

   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
   "use_cache": true,
   "vocab_size": 65519
 }

pytorch_model-00001-of-00004.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3937b3ea39ab19b7cfdebd1437697de2c1a0661b83c820b11959fd0e66d847
+size 3982821280

pytorch_model-00002-of-00004.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa3f307240908b1dee0c29c89984bd6296da07df37830aa7f410e8a753b810f
+size 3959875181

pytorch_model-00003-of-00004.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cec69a2da3ab38212a3b6ef037662899d2ece3469e508ffdc2d810e269c4a0ae
+size 3966949023

pytorch_model-00004-of-00004.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e9b326a9bb2ea0b51a193ace89d71f1b9c830832a0d619bcfdacbfab3cca1f
+size 2558969081

pytorch_model.bin.index.json CHANGED Viewed

The diff for this file is too large to render. See raw diff