Instructions to use krytonguard/ceescoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use krytonguard/ceescoder with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoderbase-1b")
model = PeftModel.from_pretrained(base_model, "krytonguard/ceescoder")

Transformers

How to use krytonguard/ceescoder with Transformers:

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

pipe = pipeline("text-generation", model="krytonguard/ceescoder")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("krytonguard/ceescoder", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use krytonguard/ceescoder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/krytonguard/ceescoder

SGLang

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

Docker Model Runner
How to use krytonguard/ceescoder with Docker Model Runner:
```
docker model run hf.co/krytonguard/ceescoder
```

krytonguard commited on Mar 8

Commit

87a256e

verified ·

1 Parent(s): f644383

End of training

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -36,14 +36,16 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
-- train_batch_size: 1
-- eval_batch_size: 1
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 30
-- training_steps: 20
 ### Training results

 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.005
+- train_batch_size: 3
+- eval_batch_size: 3
 - seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 9
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 30
+- training_steps: 2000
 ### Training results