Instructions to use chgk13/stablecode-completion-alpha-3b-4k-openvino-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chgk13/stablecode-completion-alpha-3b-4k-openvino-int8 with Transformers:

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

pipe = pipeline("text-generation", model="chgk13/stablecode-completion-alpha-3b-4k-openvino-int8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chgk13/stablecode-completion-alpha-3b-4k-openvino-int8")
model = AutoModelForCausalLM.from_pretrained("chgk13/stablecode-completion-alpha-3b-4k-openvino-int8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use chgk13/stablecode-completion-alpha-3b-4k-openvino-int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chgk13/stablecode-completion-alpha-3b-4k-openvino-int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chgk13/stablecode-completion-alpha-3b-4k-openvino-int8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/chgk13/stablecode-completion-alpha-3b-4k-openvino-int8

SGLang

How to use chgk13/stablecode-completion-alpha-3b-4k-openvino-int8 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 "chgk13/stablecode-completion-alpha-3b-4k-openvino-int8" \
    --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": "chgk13/stablecode-completion-alpha-3b-4k-openvino-int8",
		"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 "chgk13/stablecode-completion-alpha-3b-4k-openvino-int8" \
        --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": "chgk13/stablecode-completion-alpha-3b-4k-openvino-int8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chgk13/stablecode-completion-alpha-3b-4k-openvino-int8 with Docker Model Runner:
```
docker model run hf.co/chgk13/stablecode-completion-alpha-3b-4k-openvino-int8
```

chgk13 commited on Aug 18, 2023

Commit

d5d4772

1 Parent(s): 029cd5d

Upload openvino_config.json with huggingface_hub

Browse files

Files changed (1) hide show

openvino_config.json +35 -0

openvino_config.json ADDED Viewed

	@@ -0,0 +1,35 @@

+{
+  "compression": {
+    "algorithm": "quantization",
+    "export_to_onnx_standard_ops": false,
+    "ignored_scopes": [
+      "{re}.*Embedding.*",
+      "{re}.*add___.*",
+      "{re}.*layer_norm_.*",
+      "{re}.*matmul_1",
+      "{re}.*__truediv__.*"
+    ],
+    "initializer": {
+      "batchnorm_adaptation": {
+        "num_bn_adaptation_samples": 0
+      },
+      "range": {
+        "num_init_samples": 300,
+        "type": "mean_min_max"
+      }
+    },
+    "overflow_fix": "disable",
+    "preset": "mixed",
+    "scope_overrides": {
+      "activations": {
+        "{re}.*matmul_0": {
+          "mode": "symmetric"
+        }
+      }
+    }
+  },
+  "input_info": null,
+  "optimum_version": "1.10.0",
+  "save_onnx_model": false,
+  "transformers_version": "4.32.0.dev0"
+}