Instructions to use bigcode/gpt_bigcode-santacoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigcode/gpt_bigcode-santacoder with Transformers:

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

pipe = pipeline("text-generation", model="bigcode/gpt_bigcode-santacoder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bigcode/gpt_bigcode-santacoder")
model = AutoModelForCausalLM.from_pretrained("bigcode/gpt_bigcode-santacoder")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bigcode/gpt_bigcode-santacoder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bigcode/gpt_bigcode-santacoder

SGLang

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

Docker Model Runner
How to use bigcode/gpt_bigcode-santacoder with Docker Model Runner:
```
docker model run hf.co/bigcode/gpt_bigcode-santacoder
```

jlamypoirier commited on Apr 6, 2023

Commit

97c7c17

1 Parent(s): c72ef96

Update config for hf transformers

Browse files

Files changed (1) hide show

config.json +3 -5

config.json CHANGED Viewed

@@ -1,15 +1,14 @@
 {
   "activation_function": "gelu_pytorch_tanh",
   "architectures": [
-    "GPTBigCodeLMHeadModel"
   ],
   "attention_softmax_in_fp32": true,
-  "attention_type": 2,
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "inference_runner": 0,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt_bigcode",
@@ -27,8 +26,7 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "transformers_version": "4.27.0.dev0",
   "use_cache": true,
-  "validate_runner_input": true,
   "vocab_size": 49280
 }

 {
   "activation_function": "gelu_pytorch_tanh",
   "architectures": [
+    "GPTBigCodeForCausalLM"
   ],
   "attention_softmax_in_fp32": true,
+  "multi_query": true,
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt_bigcode",
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "transformers_version": "4.28.0.dev0",
   "use_cache": true,
   "vocab_size": 49280
 }