Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
Eval Results (legacy)
text-generation-inference
Instructions to use taufeeque/tiny-gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use taufeeque/tiny-gpt2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="taufeeque/tiny-gpt2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("taufeeque/tiny-gpt2") model = AutoModelForCausalLM.from_pretrained("taufeeque/tiny-gpt2") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use taufeeque/tiny-gpt2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "taufeeque/tiny-gpt2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "taufeeque/tiny-gpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/taufeeque/tiny-gpt2
- SGLang
How to use taufeeque/tiny-gpt2 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 "taufeeque/tiny-gpt2" \ --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": "taufeeque/tiny-gpt2", "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 "taufeeque/tiny-gpt2" \ --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": "taufeeque/tiny-gpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use taufeeque/tiny-gpt2 with Docker Model Runner:
docker model run hf.co/taufeeque/tiny-gpt2
Librarian Bot: Add base_model information to model
#2
by librarian-bot - opened
README.md
CHANGED
|
@@ -5,20 +5,21 @@ datasets:
|
|
| 5 |
- wikitext
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: output_tiny
|
| 10 |
results:
|
| 11 |
- task:
|
| 12 |
-
name: Causal Language Modeling
|
| 13 |
type: text-generation
|
|
|
|
| 14 |
dataset:
|
| 15 |
name: wikitext wikitext-103-v1
|
| 16 |
type: wikitext
|
| 17 |
args: wikitext-103-v1
|
| 18 |
metrics:
|
| 19 |
-
-
|
| 20 |
-
type: accuracy
|
| 21 |
value: 0.2132901596611274
|
|
|
|
| 22 |
---
|
| 23 |
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 5 |
- wikitext
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
+
base_model: gpt2_tiny_random
|
| 9 |
model-index:
|
| 10 |
- name: output_tiny
|
| 11 |
results:
|
| 12 |
- task:
|
|
|
|
| 13 |
type: text-generation
|
| 14 |
+
name: Causal Language Modeling
|
| 15 |
dataset:
|
| 16 |
name: wikitext wikitext-103-v1
|
| 17 |
type: wikitext
|
| 18 |
args: wikitext-103-v1
|
| 19 |
metrics:
|
| 20 |
+
- type: accuracy
|
|
|
|
| 21 |
value: 0.2132901596611274
|
| 22 |
+
name: Accuracy
|
| 23 |
---
|
| 24 |
|
| 25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|