Text Generation
Transformers
PyTorch
Safetensors
English
custom_gpt
GPT
GPT-3 Small
GPT-3 Medium
GPT-3 Large
GPT-3 XL
GPT-3 2.7B
GPT-3 6.7B
GPT-3 13B
GPT-3 175B
GPT-3
GPT-2
GPT-2 124M
mit
HuggingFace
fineweb-edu
Decoder-Only
custom_code
Instructions to use samkeet/GPT_124M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use samkeet/GPT_124M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="samkeet/GPT_124M", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("samkeet/GPT_124M", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use samkeet/GPT_124M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "samkeet/GPT_124M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "samkeet/GPT_124M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/samkeet/GPT_124M
- SGLang
How to use samkeet/GPT_124M 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 "samkeet/GPT_124M" \ --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": "samkeet/GPT_124M", "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 "samkeet/GPT_124M" \ --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": "samkeet/GPT_124M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use samkeet/GPT_124M with Docker Model Runner:
docker model run hf.co/samkeet/GPT_124M
Upload GPT124MTextGenerationPipeline
Browse files- config.json +15 -0
config.json
CHANGED
|
@@ -7,6 +7,21 @@
|
|
| 7 |
"AutoModelForCausalLM": "modeling_gpt.GPTModelForTextGeneration"
|
| 8 |
},
|
| 9 |
"block_size": 1024,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"model_type": "custom_gpt",
|
| 11 |
"n_embd": 768,
|
| 12 |
"n_head": 12,
|
|
|
|
| 7 |
"AutoModelForCausalLM": "modeling_gpt.GPTModelForTextGeneration"
|
| 8 |
},
|
| 9 |
"block_size": 1024,
|
| 10 |
+
"custom_pipelines": {
|
| 11 |
+
"text-generation": {
|
| 12 |
+
"default": {
|
| 13 |
+
"model": {
|
| 14 |
+
"pt": "samkeet/GPT_124M"
|
| 15 |
+
}
|
| 16 |
+
},
|
| 17 |
+
"impl": "pipeline_gpt.GPT124MTextGenerationPipeline",
|
| 18 |
+
"pt": [
|
| 19 |
+
"AutoModelForCausalLM"
|
| 20 |
+
],
|
| 21 |
+
"tf": [],
|
| 22 |
+
"type": "text"
|
| 23 |
+
}
|
| 24 |
+
},
|
| 25 |
"model_type": "custom_gpt",
|
| 26 |
"n_embd": 768,
|
| 27 |
"n_head": 12,
|