Instructions to use VincentG1234/Model_1_GPT2_random1000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VincentG1234/Model_1_GPT2_random1000 with Transformers:

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

pipe = pipeline("text-generation", model="VincentG1234/Model_1_GPT2_random1000")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VincentG1234/Model_1_GPT2_random1000")
model = AutoModelForCausalLM.from_pretrained("VincentG1234/Model_1_GPT2_random1000")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use VincentG1234/Model_1_GPT2_random1000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VincentG1234/Model_1_GPT2_random1000"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VincentG1234/Model_1_GPT2_random1000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/VincentG1234/Model_1_GPT2_random1000

SGLang

How to use VincentG1234/Model_1_GPT2_random1000 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 "VincentG1234/Model_1_GPT2_random1000" \
    --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": "VincentG1234/Model_1_GPT2_random1000",
		"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 "VincentG1234/Model_1_GPT2_random1000" \
        --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": "VincentG1234/Model_1_GPT2_random1000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use VincentG1234/Model_1_GPT2_random1000 with Docker Model Runner:
```
docker model run hf.co/VincentG1234/Model_1_GPT2_random1000
```

VincentG1234 commited on Feb 2, 2024

Commit

fad8796

verified ·

1 Parent(s): 374d7b4

End of training

Browse files

Files changed (4) hide show

README.md +1 -1
config.json +3 -3
model.safetensors +2 -2
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 4
 ### Training results

 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
+- num_epochs: 3
 ### Training results

config.json CHANGED Viewed

@@ -12,10 +12,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 128,
-  "n_embd": 768,
-  "n_head": 12,
   "n_inner": null,
-  "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 128,
+  "n_embd": 512,
+  "n_head": 8,
   "n_inner": null,
+  "n_layer": 8,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443bdda554eacf7be250a15e586d98314843eb15030b44dab2c070365cceab57
-size 497774208

 version https://git-lfs.github.com/spec/v1
+oid sha256:0c812841399038a7e3d5f3e6d77ab3df8ec9360a2dd87de2c5a0835d1f465537
+size 205913840

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c0a9c78f4bcafdae8e384456f35821acc7902d3d39b050d3851c8bf618268e
 size 4728

 version https://git-lfs.github.com/spec/v1
+oid sha256:cd5336d2f3476d71cc91f7392921079f7829d909a461ae5e2aa5ed9273d6f969
 size 4728