Instructions to use dineth554/legion-coder-8m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dineth554/legion-coder-8m with Transformers:

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

pipe = pipeline("text-generation", model="dineth554/legion-coder-8m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dineth554/legion-coder-8m")
model = AutoModelForCausalLM.from_pretrained("dineth554/legion-coder-8m")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dineth554/legion-coder-8m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dineth554/legion-coder-8m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dineth554/legion-coder-8m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dineth554/legion-coder-8m

SGLang

How to use dineth554/legion-coder-8m 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 "dineth554/legion-coder-8m" \
    --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": "dineth554/legion-coder-8m",
		"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 "dineth554/legion-coder-8m" \
        --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": "dineth554/legion-coder-8m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dineth554/legion-coder-8m with Docker Model Runner:
```
docker model run hf.co/dineth554/legion-coder-8m
```

dineth554 commited on Mar 8

Commit

40d0bd8

verified ·

1 Parent(s): 2784e4f

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +6 -5

config.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-  "model_type": "legion_coder",
-  "architectures": [
-    "LegionCoderModel"
-  ],
   "vocab_size": 16000,
   "d_model": 640,
   "num_layers": 14,
@@ -15,6 +15,7 @@
   "unk_token_id": 2,
   "torch_dtype": "float32",
   "transformers_version": "4.36.0",
   "task": "text-generation",
   "tags": [
     "transformers",
@@ -60,4 +61,4 @@
     "instance_count": 1,
     "container_image": "huggingface-pytorch-inference:2.0.0-transformers4.28.1-cpu-py310-ubuntu20.04-v1.0"
   }
-}

 {
+"model_type": "gpt2",
+"architectures": [
+"GPT2LMHeadModel"
+],
   "vocab_size": 16000,
   "d_model": 640,
   "num_layers": 14,
   "unk_token_id": 2,
   "torch_dtype": "float32",
   "transformers_version": "4.36.0",
+"base_model": null,
   "task": "text-generation",
   "tags": [
     "transformers",
     "instance_count": 1,
     "container_image": "huggingface-pytorch-inference:2.0.0-transformers4.28.1-cpu-py310-ubuntu20.04-v1.0"
   }
+}