Instructions to use K00B404/GPT_2_CODE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use K00B404/GPT_2_CODE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="K00B404/GPT_2_CODE")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("K00B404/GPT_2_CODE") model = AutoModelForCausalLM.from_pretrained("K00B404/GPT_2_CODE", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use K00B404/GPT_2_CODE with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "K00B404/GPT_2_CODE" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "K00B404/GPT_2_CODE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/K00B404/GPT_2_CODE
- SGLang
How to use K00B404/GPT_2_CODE 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 "K00B404/GPT_2_CODE" \ --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": "K00B404/GPT_2_CODE", "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 "K00B404/GPT_2_CODE" \ --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": "K00B404/GPT_2_CODE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use K00B404/GPT_2_CODE with Docker Model Runner:
docker model run hf.co/K00B404/GPT_2_CODE
Update README.md
Browse files
README.md
CHANGED
|
@@ -75,9 +75,14 @@ flytech/python-codes-25k (4600)
|
|
| 75 |
Training Loss: 0.4007
|
| 76 |
Validation Loss: 0.5526
|
| 77 |
Epochs 3
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
# Evaluation
|
| 82 |
Manual comparison with base model
|
| 83 |
### Testing Data
|
|
|
|
| 75 |
Training Loss: 0.4007
|
| 76 |
Validation Loss: 0.5526
|
| 77 |
Epochs 3
|
| 78 |
+
|
| 79 |
+
"espejelomar/code_search_net_python_10000_examples"
|
| 80 |
+
Starting Loss: 2.0862
|
| 81 |
+
Epoch 1/4 | Training Loss: 1.5355 | Validation Loss: 1.1723
|
| 82 |
+
Epoch 2/4 | Training Loss: 1.0501 | Validation Loss: 1.0702
|
| 83 |
+
Epoch 3/4 | Training Loss: 0.9804 | Validation Loss: 1.0798
|
| 84 |
+
Epoch 4/4 | Training Loss: 0.9073 | Validation Loss: 1.0772
|
| 85 |
+
|
| 86 |
# Evaluation
|
| 87 |
Manual comparison with base model
|
| 88 |
### Testing Data
|