Instructions to use Harshatheeswar/gpt2-scratch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Harshatheeswar/gpt2-scratch with Transformers:

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

pipe = pipeline("text-generation", model="Harshatheeswar/gpt2-scratch")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Harshatheeswar/gpt2-scratch")
model = AutoModelForCausalLM.from_pretrained("Harshatheeswar/gpt2-scratch")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Harshatheeswar/gpt2-scratch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harshatheeswar/gpt2-scratch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harshatheeswar/gpt2-scratch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Harshatheeswar/gpt2-scratch

SGLang

How to use Harshatheeswar/gpt2-scratch 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 "Harshatheeswar/gpt2-scratch" \
    --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": "Harshatheeswar/gpt2-scratch",
		"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 "Harshatheeswar/gpt2-scratch" \
        --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": "Harshatheeswar/gpt2-scratch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Harshatheeswar/gpt2-scratch with Docker Model Runner:
```
docker model run hf.co/Harshatheeswar/gpt2-scratch
```

Harshatheeswar commited on Oct 19, 2024

Commit

b70fcbd

verified ·

1 Parent(s): 5b960c6

End of training

Browse files

Files changed (2) hide show

README.md +4 -3
runs/Oct19_14-50-36_22a6a41c53da/events.out.tfevents.1729349446.22a6a41c53da.2967.0 +2 -2

README.md CHANGED Viewed

@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 # gpt2-scratch
-This model is a fine-tuned version of [Harshatheeswar/gpt2-scratch](https://huggingface.co/Harshatheeswar/gpt2-scratch) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.2516
 ## Model description
@@ -49,11 +49,12 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.3012        | 1.0   | 1390 | 4.2516          |
 ### Framework versions
 - Transformers 4.44.2
 - Pytorch 2.4.1+cu121
 - Tokenizers 0.19.1

 # gpt2-scratch
+This model is a fine-tuned version of [Harshatheeswar/gpt2-scratch](https://huggingface.co/Harshatheeswar/gpt2-scratch) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 4.1380
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 4.2094        | 1.0   | 1390 | 4.1380          |
 ### Framework versions
 - Transformers 4.44.2
 - Pytorch 2.4.1+cu121
+- Datasets 3.0.1
 - Tokenizers 0.19.1

runs/Oct19_14-50-36_22a6a41c53da/events.out.tfevents.1729349446.22a6a41c53da.2967.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cdc4c9dcf31c1d6f997b0e1a6a4d8b6f2ff28fa4c5cc2331444b6c42622ec8f
-size 34401

 version https://git-lfs.github.com/spec/v1
+oid sha256:d390651776b6cc08e01d05a856c8ed46e3488357de30712a0c7c0fa951cc5f04
+size 35026