Instructions to use cotysong113/codeparrot-ds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cotysong113/codeparrot-ds with Transformers:

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

pipe = pipeline("text-generation", model="cotysong113/codeparrot-ds")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cotysong113/codeparrot-ds")
model = AutoModelForCausalLM.from_pretrained("cotysong113/codeparrot-ds")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cotysong113/codeparrot-ds with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cotysong113/codeparrot-ds"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cotysong113/codeparrot-ds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cotysong113/codeparrot-ds

SGLang

How to use cotysong113/codeparrot-ds 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 "cotysong113/codeparrot-ds" \
    --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": "cotysong113/codeparrot-ds",
		"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 "cotysong113/codeparrot-ds" \
        --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": "cotysong113/codeparrot-ds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cotysong113/codeparrot-ds with Docker Model Runner:
```
docker model run hf.co/cotysong113/codeparrot-ds
```

cotysong113 commited on Dec 11, 2024

Commit

6c48415

verified ·

1 Parent(s): f2f8e61

End of training

Browse files

Files changed (2) hide show

README.md +6 -18
generation_config.json +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0610
 ## Model description
@@ -49,26 +49,14 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch  | Step  | Validation Loss |
-|:-------------:|:------:|:-----:|:---------------:|
-| 2.5544        | 0.0766 | 5000  | 1.7193          |
-| 1.66          | 0.1533 | 10000 | 1.5090          |
-| 1.5196        | 0.2299 | 15000 | 1.4118          |
-| 1.4451        | 0.3065 | 20000 | 1.3466          |
-| 1.3878        | 0.3832 | 25000 | 1.2987          |
-| 1.3383        | 0.4598 | 30000 | 1.2534          |
-| 1.2937        | 0.5365 | 35000 | 1.2107          |
-| 1.2482        | 0.6131 | 40000 | 1.1684          |
-| 1.2082        | 0.6897 | 45000 | 1.1316          |
-| 1.1709        | 0.7664 | 50000 | 1.0987          |
-| 1.1444        | 0.8430 | 55000 | 1.0760          |
-| 1.1234        | 0.9196 | 60000 | 1.0638          |
-| 1.1159        | 0.9963 | 65000 | 1.0610          |
 ### Framework versions
-- Transformers 4.46.2
 - Pytorch 2.5.1+cu124
 - Datasets 3.1.0
-- Tokenizers 0.20.3

 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.6388
 ## Model description
 ### Training results
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.4025        | 0.7664 | 5000 | 1.6388          |
 ### Framework versions
+- Transformers 4.47.0
 - Pytorch 2.5.1+cu124
 - Datasets 3.1.0
+- Tokenizers 0.21.0

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.46.2"
 }

   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
+  "transformers_version": "4.47.0"
 }