Instructions to use circulus/Llama-2-13b-orca-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use circulus/Llama-2-13b-orca-v1 with Transformers:

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

pipe = pipeline("text-generation", model="circulus/Llama-2-13b-orca-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("circulus/Llama-2-13b-orca-v1")
model = AutoModelForCausalLM.from_pretrained("circulus/Llama-2-13b-orca-v1", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use circulus/Llama-2-13b-orca-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "circulus/Llama-2-13b-orca-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "circulus/Llama-2-13b-orca-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/circulus/Llama-2-13b-orca-v1

SGLang

How to use circulus/Llama-2-13b-orca-v1 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 "circulus/Llama-2-13b-orca-v1" \
    --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": "circulus/Llama-2-13b-orca-v1",
		"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 "circulus/Llama-2-13b-orca-v1" \
        --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": "circulus/Llama-2-13b-orca-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use circulus/Llama-2-13b-orca-v1 with Docker Model Runner:
```
docker model run hf.co/circulus/Llama-2-13b-orca-v1
```

rippertnt commited on Aug 2, 2023

Commit

da53bd8

1 Parent(s): 20f4106

Upload 4 files

Browse files

Files changed (3) hide show

special_tokens_map.json +0 -1
tokenizer.json +0 -0
tokenizer_config.json +0 -4

special_tokens_map.json CHANGED Viewed

@@ -13,7 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<unk>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json ADDED Viewed

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

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "bos_token": {
     "__type": "AddedToken",
     "content": "<s>",
@@ -18,10 +16,8 @@
     "rstrip": false,
     "single_word": false
   },
-  "legacy": true,
   "model_max_length": 4096,
   "pad_token": null,
-  "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": {

 {
   "bos_token": {
     "__type": "AddedToken",
     "content": "<s>",
     "rstrip": false,
     "single_word": false
   },
   "model_max_length": 4096,
   "pad_token": null,
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": {