Instructions to use Seungyoun/codellama-7b-instruct-pad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Seungyoun/codellama-7b-instruct-pad with Transformers:

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

pipe = pipeline("text-generation", model="Seungyoun/codellama-7b-instruct-pad")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Seungyoun/codellama-7b-instruct-pad")
model = AutoModelForCausalLM.from_pretrained("Seungyoun/codellama-7b-instruct-pad")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Seungyoun/codellama-7b-instruct-pad with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Seungyoun/codellama-7b-instruct-pad"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Seungyoun/codellama-7b-instruct-pad",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Seungyoun/codellama-7b-instruct-pad

SGLang

How to use Seungyoun/codellama-7b-instruct-pad 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 "Seungyoun/codellama-7b-instruct-pad" \
    --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": "Seungyoun/codellama-7b-instruct-pad",
		"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 "Seungyoun/codellama-7b-instruct-pad" \
        --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": "Seungyoun/codellama-7b-instruct-pad",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Seungyoun/codellama-7b-instruct-pad with Docker Model Runner:
```
docker model run hf.co/Seungyoun/codellama-7b-instruct-pad
```

Seungyoun commited on Aug 27, 2023

Commit

adbbba4

1 Parent(s): 0b930f0

Upload LlamaForCausalLM

Browse files

Files changed (3) hide show

config.json +1 -1
pytorch_model-00001-of-00002.bin +1 -1
pytorch_model-00002-of-00002.bin +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/seungyoun/llama_related/llama_code_interpreter/ckpt/codellama-2-7b-instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],

 {
+  "_name_or_path": "/home/seungyoun/llama_related/llama_code_interpreter/output/llama-2-7b-codellama-ci",
   "architectures": [
     "LlamaForCausalLM"
   ],

pytorch_model-00001-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66049d8675205212b3206aa7698404ac8bf833c19f3c5b3ad95b5be7254cf7da
 size 9976827930

 version https://git-lfs.github.com/spec/v1
+oid sha256:dcf5f69dce8af918170e2f55866ecee416fc0060ee9e4eb3161c8fd4a47a995a
 size 9976827930

pytorch_model-00002-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09899558fa8fa366d54f1cdca21a3569978c92e3e66ab97383758fe802399c04
 size 3500516611

 version https://git-lfs.github.com/spec/v1
+oid sha256:c7ce8a49c8e44a75d9efbeaf35a64ef3b8de4d07dcbb202a4164f55ad43a8c18
 size 3500516611