Instructions to use ncoop57/multi-code-clippy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ncoop57/multi-code-clippy with Transformers:

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

pipe = pipeline("text-generation", model="ncoop57/multi-code-clippy")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ncoop57/multi-code-clippy")
model = AutoModelForCausalLM.from_pretrained("ncoop57/multi-code-clippy")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ncoop57/multi-code-clippy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ncoop57/multi-code-clippy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ncoop57/multi-code-clippy",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ncoop57/multi-code-clippy

SGLang

How to use ncoop57/multi-code-clippy 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 "ncoop57/multi-code-clippy" \
    --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": "ncoop57/multi-code-clippy",
		"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 "ncoop57/multi-code-clippy" \
        --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": "ncoop57/multi-code-clippy",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ncoop57/multi-code-clippy with Docker Model Runner:
```
docker model run hf.co/ncoop57/multi-code-clippy
```

ncoop57 commited on Mar 3, 2022

Commit

380fc62

1 Parent(s): 3d5a900

add model

Browse files

Files changed (2) hide show

config.json +3 -4
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "multi-code-clippy",
   "activation_function": "gelu_new",
   "architectures": [
     "GPTNeoForCausalLM"
@@ -28,15 +27,15 @@
       6
     ]
   ],
-  "bos_token_id": 50256,
   "embed_dropout": 0,
-  "eos_token_id": 50256,
   "gradient_checkpointing": false,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": null,
   "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
   "model_type": "gpt_neo",
   "num_heads": 12,
   "num_layers": 12,

 {
   "activation_function": "gelu_new",
   "architectures": [
     "GPTNeoForCausalLM"
       6
     ]
   ],
+  "bos_token_id": 50000,
   "embed_dropout": 0,
+  "eos_token_id": 50001,
   "gradient_checkpointing": false,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": null,
   "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 1024,
   "model_type": "gpt_neo",
   "num_heads": 12,
   "num_layers": 12,

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81bf04f05c64685744e961ab13e83ac79ac66d82618c41d0f105fbcb79a3f4c0
-size 550399185

 version https://git-lfs.github.com/spec/v1
+oid sha256:de5cd02591bfba6c9b406e6cb0449322bd76ea7aba19797418d6c2464406e36f
+size 509504721