Instructions to use shpotes/codegen-350M-mono with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shpotes/codegen-350M-mono with Transformers:

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

pipe = pipeline("text-generation", model="shpotes/codegen-350M-mono")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shpotes/codegen-350M-mono")
model = AutoModelForCausalLM.from_pretrained("shpotes/codegen-350M-mono")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shpotes/codegen-350M-mono with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shpotes/codegen-350M-mono"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shpotes/codegen-350M-mono",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/shpotes/codegen-350M-mono

SGLang

How to use shpotes/codegen-350M-mono 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 "shpotes/codegen-350M-mono" \
    --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": "shpotes/codegen-350M-mono",
		"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 "shpotes/codegen-350M-mono" \
        --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": "shpotes/codegen-350M-mono",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use shpotes/codegen-350M-mono with Docker Model Runner:
```
docker model run hf.co/shpotes/codegen-350M-mono
```

shpotes commited on Mar 30, 2022

Commit

d8bd706

1 Parent(s): d5975be

add tokenizer

Browse files

Files changed (3) hide show

added_tokens.json +1 -1
special_tokens_map.json +1 -1
tokenizer.json +9 -0

added_tokens.json CHANGED Viewed

@@ -1 +1 @@

- {"~~\t\t\t\t\t~~": ~~50301~~, "~~\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t~~": ~~50289~~, "\t\t\t": ~~50303~~, "\t\t\t\t\t\t\t\t\t\t": ~~50296~~, " ": ~~50279~~, " ": ~~50263~~, "\t\t\t\t~~\t\t\t~~": ~~50299~~, " ": ~~50258~~, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": ~~50287~~, "\t\t\t\t\t\t\t~~\t\t\t\t\t~~": ~~50294~~, "\t\t\t\t\t\t\t\t\t\t\t": ~~50295~~, "\t\t\t\t\t~~\t\t\t\t\t\t\t\t\t\t\t~~": ~~50290~~, " ": ~~50272~~, " ": 50269, " ": ~~50261~~, " ": ~~50282~~, "\t\t\t\t\t\t\t\t\t\t\t\t\t~~": 50293, " ": 50268, " ": 50275, "~~\t\t\t\t": ~~50302~~, " ": ~~50276~~, " ": 50260, "\t\t": ~~50304~~, " ": ~~50273~~, " ": ~~50259~~, " ": ~~50267~~, " ": ~~50277~~, " ~~": 50257, " ": 50270, " ": 50280, "~~\t\t\t\t\t\t\t\t\t~~": 50297, "~~\t\t\t\t\t\t~~\t\t~~": ~~50298~~, "\t\t\t\t\t\t\t\t\t\t\t~~\t\t\t\t\t\t\t~~": ~~50288~~, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": ~~50291~~, " ": ~~50283~~, " ": ~~50271~~, " ": ~~50265~~, " ": ~~50266~~, " ~~": 50264, "~~\t\t\t\t\t\t": ~~50300~~, " ": ~~50285~~, " ": ~~50274~~, " ": 50262, " ": ~~50284~~, " ": ~~50286~~, " ": ~~50281~~, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t": ~~50292~~, " ": ~~50278~~}

+ {" ": 50283, " ": 50271, "\t\t": 50304, "\t\t\t\t\t\t\t\t\t": 50297, " ": 50264, " ": 50275, "\t\t\t\t": 50302, " ": 50284, " ": 50261, " ": 50270, " ": 50274, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50288, "\t\t\t\t\t\t\t": 50299, "\t\t\t\t\t\t\t\t\t\t\t\t": 50294, " ": 50280, " ": 50263, "\t\t\t\t\t": 50301, " ": 50268, " ": 50269, " ": 50257, " ": 50259, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50287, " ": 50282, " ": 50281, " ": 50260, "\t\t\t": 50303, "\t\t\t\t\t\t\t\t\t\t": 50296, " ": 50272, " ": 50279, "<pad>": 50305, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50291, " ": 50286, "\t\t\t\t\t\t\t\t\t\t\t": 50295, " ": 50266, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50292, " ": 50267, " ": 50273, "\t\t\t\t\t\t": 50300, " ": 50285, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50290, " ": 50278, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50289, " ": 50262, " ": 50258, " ": 50265, " ": 50276, "\t\t\t\t\t\t\t\t": 50298, "\t\t\t\t\t\t\t\t\t\t\t\t\t": 50293, " ": 50277}

special_tokens_map.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "unk_token": "<\|endoftext\|>"}


1	+ {"bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "unk_token": "<\|endoftext\|>", "pad_token": "<pad>"}

tokenizer.json CHANGED Viewed

@@ -443,6 +443,15 @@
       "rstrip": false,
       "normalized": true,
       "special": false
     }
   ],
   "normalizer": null,

       "rstrip": false,
       "normalized": true,
       "special": false
+    },
+    {
+      "id": 50305,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,