Instructions to use arithmetic-circuit-overloading/gpt2-128D-3L-4H with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arithmetic-circuit-overloading/gpt2-128D-3L-4H with Transformers:

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

pipe = pipeline("text-generation", model="arithmetic-circuit-overloading/gpt2-128D-3L-4H")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arithmetic-circuit-overloading/gpt2-128D-3L-4H")
model = AutoModelForCausalLM.from_pretrained("arithmetic-circuit-overloading/gpt2-128D-3L-4H", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arithmetic-circuit-overloading/gpt2-128D-3L-4H with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arithmetic-circuit-overloading/gpt2-128D-3L-4H"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arithmetic-circuit-overloading/gpt2-128D-3L-4H",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arithmetic-circuit-overloading/gpt2-128D-3L-4H

SGLang

How to use arithmetic-circuit-overloading/gpt2-128D-3L-4H 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 "arithmetic-circuit-overloading/gpt2-128D-3L-4H" \
    --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": "arithmetic-circuit-overloading/gpt2-128D-3L-4H",
		"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 "arithmetic-circuit-overloading/gpt2-128D-3L-4H" \
        --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": "arithmetic-circuit-overloading/gpt2-128D-3L-4H",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arithmetic-circuit-overloading/gpt2-128D-3L-4H with Docker Model Runner:
```
docker model run hf.co/arithmetic-circuit-overloading/gpt2-128D-3L-4H
```

aditeyabaral commited on Jun 23

Commit

d20effd

verified ·

1 Parent(s): 4d34ab1

Training in progress, epoch 1

Browse files

Files changed (3) hide show

config.json +4 -4
model.safetensors +1 -1
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -4,10 +4,10 @@
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.1,
   "bos_token_id": 1,
   "dtype": "float32",
-  "embd_pdrop": 0.1,
   "eos_token_id": 2,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
@@ -19,11 +19,11 @@
   "n_positions": 128,
   "pad_token_id": 0,
   "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
-  "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,

   "architectures": [
     "GPT2LMHeadModel"
   ],
+  "attn_pdrop": 0.0,
   "bos_token_id": 1,
   "dtype": "float32",
+  "embd_pdrop": 0.0,
   "eos_token_id": 2,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "n_positions": 128,
   "pad_token_id": 0,
   "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
+  "summary_first_dropout": 0.0,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b9a4f5d790932d47995a67503c734133e8430c47df6739c6f93cba7f4e1a51
 size 2459928

 version https://git-lfs.github.com/spec/v1
+oid sha256:fcd3fc00dc434cb1c11c92a719213a3760d89e0d5d6f57e618cb73884c0beff0
 size 2459928

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e7aa7b0107b58140a408650ddcabe122e79507296a2a6c70315e16d2fbdf2b
 size 5329

 version https://git-lfs.github.com/spec/v1
+oid sha256:6ab081a8027025abd55183a3e848cf8b07c375353fda3ce697fc32a73f357c02
 size 5329