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

Libraries

How to use AlgorithmicResearchGroup/gpt2-xs with Transformers:

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

pipe = pipeline("text-generation", model="AlgorithmicResearchGroup/gpt2-xs")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlgorithmicResearchGroup/gpt2-xs")
model = AutoModelForCausalLM.from_pretrained("AlgorithmicResearchGroup/gpt2-xs")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AlgorithmicResearchGroup/gpt2-xs with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AlgorithmicResearchGroup/gpt2-xs

SGLang

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

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

Matthew Kenney commited on Apr 29, 2024

Commit

4ef5385

1 Parent(s): 372598e

commit files to HF hub

Browse files

Files changed (4) hide show

config.json +2 -2
model.safetensors +2 -2
tokenizer.json +2 -2
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/results_16_epoch_1e_3/checkpoint-4005",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -16,7 +16,7 @@
   "n_head": 6,
   "n_inner": null,
   "n_layer": 6,
-  "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

 {
+  "_name_or_path": "/content/vsmall_256_epoch_1e_3/checkpoint-420",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   "n_head": 6,
   "n_inner": null,
   "n_layer": 6,
+  "n_positions": 256,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec6fb7e21d8dcd22632aeb8e6f448981955291c9c47b0704e023a144fa11987d
-size 121365368

 version https://git-lfs.github.com/spec/v1
+oid sha256:4d6f4326b673ed0ad7d96c5c40879e2af28d8a514650c14bf8d35280c46aa029
+size 120185720

tokenizer.json CHANGED Viewed

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

   "version": "1.0",
   "truncation": {
     "direction": "Right",
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
+      "Fixed": 256
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json CHANGED Viewed

@@ -13,7 +13,7 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "max_length": 512,
   "model_max_length": 1024,
   "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",

   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 256,
   "model_max_length": 1024,
   "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",