Instructions to use prithivMLmods/Gpt2-Wikitext-9180 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Gpt2-Wikitext-9180 with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Gpt2-Wikitext-9180")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Gpt2-Wikitext-9180")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Gpt2-Wikitext-9180")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use prithivMLmods/Gpt2-Wikitext-9180 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Gpt2-Wikitext-9180"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Gpt2-Wikitext-9180",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/prithivMLmods/Gpt2-Wikitext-9180

SGLang

How to use prithivMLmods/Gpt2-Wikitext-9180 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 "prithivMLmods/Gpt2-Wikitext-9180" \
    --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": "prithivMLmods/Gpt2-Wikitext-9180",
		"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 "prithivMLmods/Gpt2-Wikitext-9180" \
        --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": "prithivMLmods/Gpt2-Wikitext-9180",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use prithivMLmods/Gpt2-Wikitext-9180 with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Gpt2-Wikitext-9180
```

Gpt2-Wikitext-9180 / checkpoint-2000 /trainer_state.json

prithivMLmods

Upload folder using huggingface_hub

6f426c0 verified 12 months ago

raw

history blame contribute delete

1.47 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.2178649237472767,
	"eval_steps": 500,
	"global_step": 2000,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.054466230936819175,
	"grad_norm": 5.168296813964844,
	"learning_rate": 5e-05,
	"loss": 1.747,
	"step": 500
	},
	{
	"epoch": 0.10893246187363835,
	"grad_norm": 0.6366938948631287,
	"learning_rate": 4.711981566820277e-05,
	"loss": 1.3516,
	"step": 1000
	},
	{
	"epoch": 0.16339869281045752,
	"grad_norm": 0.5679114460945129,
	"learning_rate": 4.423963133640553e-05,
	"loss": 1.3809,
	"step": 1500
	},
	{
	"epoch": 0.2178649237472767,
	"grad_norm": 1.4229077100753784,
	"learning_rate": 4.13594470046083e-05,
	"loss": 1.2784,
	"step": 2000
	}
	],
	"logging_steps": 500,
	"max_steps": 9180,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 1,
	"save_steps": 500,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": false
	},
	"attributes": {}
	}
	},
	"total_flos": 522584064000000.0,
	"train_batch_size": 4,
	"trial_name": null,
	"trial_params": null
	}