Instructions to use Salesforce/codegen2-1B_P with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/codegen2-1B_P with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/codegen2-1B_P", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen2-1B_P", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen2-1B_P", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/codegen2-1B_P with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/codegen2-1B_P"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/codegen2-1B_P",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/codegen2-1B_P

SGLang

How to use Salesforce/codegen2-1B_P 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 "Salesforce/codegen2-1B_P" \
    --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": "Salesforce/codegen2-1B_P",
		"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 "Salesforce/codegen2-1B_P" \
        --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": "Salesforce/codegen2-1B_P",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/codegen2-1B_P with Docker Model Runner:
```
docker model run hf.co/Salesforce/codegen2-1B_P
```

rooa commited on May 4, 2023

Commit

45fb58f

1 Parent(s): d3cb58e

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ license: apache-2.0
 [CodeGen2](https://github.com/salesforce/CodeGen2) is a family of autoregressive language models for **program synthesis**, introduced in the paper:
-[CodeGen2: Lessons for Training LLMs on Programming and Natural Languages]() by Erik Nijkamp\*, Hiroaki Hayashi\*, Caiming Xiong, Silvio Savarese, Yingbo Zhou.
 Unlike the original CodeGen model family (i.e., CodeGen1), CodeGen2 is capable of infilling, and supports more programming languages.
@@ -76,7 +76,7 @@ You might want to truncate the model output with `<eom>`.
 ## Training data
-This checkpoint is trained on the stricter permissive subset of [the deduplicated version of the Stack dataset (v1.1)](). Supported languages (and frameworks) are as follows:
 `c`, `c++`, `c-sharp`, `dart`, `go`, `java`, `javascript`, `kotlin`, `lua`, `php`, `python`, `ruby`, `rust`, `scala`, `shell`, `sql`, `swift`, `typescript`, `vue`.
 ## Training procedure
@@ -87,7 +87,7 @@ Please refer to the paper for more details.
 ## Evaluation results
-We evaluate our models on HumanEval and HumanEval-Infill. Please refer to the [paper]() for more details.
 ## Intended use and limitations
@@ -102,6 +102,6 @@ However, the model is intended for and best at **program synthesis**, that is, g
   title={CodeGen2: Lessons for Training LLMs on Programming and Natural Languages},
   author={Nijkamp, Erik and Hayashi, Hiroaki and Xiong, Caiming and Savarese, Silvio and Zhou, Yingbo},
   journal={arXiv preprint},
-  year={2022}
 }
 ```

 [CodeGen2](https://github.com/salesforce/CodeGen2) is a family of autoregressive language models for **program synthesis**, introduced in the paper:
+[CodeGen2: Lessons for Training LLMs on Programming and Natural Languages](https://arxiv.org/abs/2305.02309) by Erik Nijkamp\*, Hiroaki Hayashi\*, Caiming Xiong, Silvio Savarese, Yingbo Zhou.
 Unlike the original CodeGen model family (i.e., CodeGen1), CodeGen2 is capable of infilling, and supports more programming languages.
 ## Training data
+This checkpoint is trained on the stricter permissive subset of [the deduplicated version of the Stack dataset (v1.1)](https://huggingface.co/datasets/bigcode/the-stack-dedup). Supported languages (and frameworks) are as follows:
 `c`, `c++`, `c-sharp`, `dart`, `go`, `java`, `javascript`, `kotlin`, `lua`, `php`, `python`, `ruby`, `rust`, `scala`, `shell`, `sql`, `swift`, `typescript`, `vue`.
 ## Training procedure
 ## Evaluation results
+We evaluate our models on HumanEval and HumanEval-Infill. Please refer to the [paper](https://arxiv.org/abs/2305.02309) for more details.
 ## Intended use and limitations
   title={CodeGen2: Lessons for Training LLMs on Programming and Natural Languages},
   author={Nijkamp, Erik and Hayashi, Hiroaki and Xiong, Caiming and Savarese, Silvio and Zhou, Yingbo},
   journal={arXiv preprint},
+  year={2023}
 }
 ```