Instructions to use frank098/WizardLM_13B_juniper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use frank098/WizardLM_13B_juniper with Transformers:

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

pipe = pipeline("text-generation", model="frank098/WizardLM_13B_juniper", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("frank098/WizardLM_13B_juniper")
model = AutoModelForCausalLM.from_pretrained("frank098/WizardLM_13B_juniper", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use frank098/WizardLM_13B_juniper with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "frank098/WizardLM_13B_juniper"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frank098/WizardLM_13B_juniper",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/frank098/WizardLM_13B_juniper

SGLang

How to use frank098/WizardLM_13B_juniper 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 "frank098/WizardLM_13B_juniper" \
    --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": "frank098/WizardLM_13B_juniper",
		"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 "frank098/WizardLM_13B_juniper" \
        --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": "frank098/WizardLM_13B_juniper",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use frank098/WizardLM_13B_juniper with Docker Model Runner:
```
docker model run hf.co/frank098/WizardLM_13B_juniper
```

frank098 commited on Jul 11, 2023

Commit

a079202

1 Parent(s): c26cc3b

Upload LlamaForCausalLM

Browse files

Files changed (6) hide show

pytorch_model-00001-of-00006.bin +2 -2
pytorch_model-00002-of-00006.bin +2 -2
pytorch_model-00003-of-00006.bin +2 -2
pytorch_model-00004-of-00006.bin +2 -2
pytorch_model-00005-of-00006.bin +2 -2
pytorch_model-00006-of-00006.bin +2 -2

pytorch_model-00001-of-00006.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fea2809092e6a2082ab387102812be9812ca0a84b29107f388db2da81b5804f
-size 9956564363

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd44a29653b9bd0e51a8c2e464820191ed65f2d14277b86cfef7d149d7da4c6f
+size 9956565387

pytorch_model-00002-of-00006.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72c998d1df11b2a8e779b4520a2cd9e6766d84fc4411eb08784d5703d22d23e
-size 9940856385

 version https://git-lfs.github.com/spec/v1
+oid sha256:41acae271bbf63b67e5d715bc5bc4f997348254d3894c1c49ab7ebe2ef209243
+size 9940857409

pytorch_model-00003-of-00006.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0763f63a499312b4cd848b2e2fa75da8148f3beae566ed02a58781f727ca2d7
-size 9940856943

 version https://git-lfs.github.com/spec/v1
+oid sha256:f5708b6a5f80930a8bb2ebcfc0b9e0c62fb7adc5fe149e03401303fa5d929120
+size 9940858031

pytorch_model-00004-of-00006.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdbe90a770cf185849675f85c32b939c239c0eba3c9ff04e625b27407429a55
-size 9867415289

 version https://git-lfs.github.com/spec/v1
+oid sha256:0d9d340892d56c064d674ae6406eb1ac60448d0f9434a7e4db14c09d60b06d43
+size 9867416377

pytorch_model-00005-of-00006.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be470fdcfa1c1e09feb40a6671a1a7bfb975785d05b3e9435e725cb6dc66b460
-size 9867456961

 version https://git-lfs.github.com/spec/v1
+oid sha256:88b0ec69d825c3ebfa9fb1c6d8fa6357271c908391963ac356aaed48f4d458ff
+size 9867458049

pytorch_model-00006-of-00006.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83f12f5843f7abc65d26fe4318924fff841b8d979a777de30b4314bf4af2369
-size 2490496687

 version https://git-lfs.github.com/spec/v1
+oid sha256:5234db3b64fb3d9662d973742b01da1b33c95e9ce54470f61d1352932f5da808
+size 2490496879