Instructions to use Ashraf-kasem/custom_gpt2_frames_text_continue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ashraf-kasem/custom_gpt2_frames_text_continue with Transformers:

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

pipe = pipeline("text-generation", model="Ashraf-kasem/custom_gpt2_frames_text_continue")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ashraf-kasem/custom_gpt2_frames_text_continue")
model = AutoModelForCausalLM.from_pretrained("Ashraf-kasem/custom_gpt2_frames_text_continue", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ashraf-kasem/custom_gpt2_frames_text_continue with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ashraf-kasem/custom_gpt2_frames_text_continue"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ashraf-kasem/custom_gpt2_frames_text_continue",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ashraf-kasem/custom_gpt2_frames_text_continue

SGLang

How to use Ashraf-kasem/custom_gpt2_frames_text_continue 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 "Ashraf-kasem/custom_gpt2_frames_text_continue" \
    --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": "Ashraf-kasem/custom_gpt2_frames_text_continue",
		"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 "Ashraf-kasem/custom_gpt2_frames_text_continue" \
        --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": "Ashraf-kasem/custom_gpt2_frames_text_continue",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ashraf-kasem/custom_gpt2_frames_text_continue with Docker Model Runner:
```
docker model run hf.co/Ashraf-kasem/custom_gpt2_frames_text_continue
```

Ashraf-kasem commited on Jan 27, 2023

Commit

2dd58b2

1 Parent(s): ae0ef70

Training in progress epoch 65

Browse files

Files changed (6) hide show

README.md +4 -3
checkpoint/extra_data.pickle +1 -1
checkpoint/weights.h5 +1 -1
logs/train/events.out.tfevents.1674736212.ip-10-39-226-229.afrd.expertcity.com.7323.0.v2 +2 -2
logs/validation/events.out.tfevents.1674737933.ip-10-39-226-229.afrd.expertcity.com.7323.1.v2 +2 -2
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [Ashraf-kasem/custom_gpt2_frames_text_continue](https://huggingface.co/Ashraf-kasem/custom_gpt2_frames_text_continue) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7994
-- Validation Loss: 2.2232
-- Epoch: 64
 ## Model description
@@ -107,6 +107,7 @@ The following hyperparameters were used during training:
 | 0.8120     | 2.2180          | 62    |
 | 0.8053     | 2.2202          | 63    |
 | 0.7994     | 2.2232          | 64    |
 ### Framework versions

 This model is a fine-tuned version of [Ashraf-kasem/custom_gpt2_frames_text_continue](https://huggingface.co/Ashraf-kasem/custom_gpt2_frames_text_continue) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 0.7934
+- Validation Loss: 2.2290
+- Epoch: 65
 ## Model description
 | 0.8120     | 2.2180          | 62    |
 | 0.8053     | 2.2202          | 63    |
 | 0.7994     | 2.2232          | 64    |
+| 0.7934     | 2.2290          | 65    |
 ### Framework versions

checkpoint/extra_data.pickle CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc8a89d35c88484dff86dc448fbb90abc7cb271c4422855cd13ccf27e647f4e
 size 748191129

 version https://git-lfs.github.com/spec/v1
+oid sha256:3498498867e28a102db7a61672389cb26366f5e97979de451d1f7ea7d9452a8a
 size 748191129

checkpoint/weights.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbfe87a421e92c9c1435c3ab0e18743ee2a396925a3d7d3e7a1660005c16a1ef
 size 374265936

 version https://git-lfs.github.com/spec/v1
+oid sha256:b7dc5a0a6ab08f37e7a0028dba415dd985421b95f7ff329a11666f3e684e253e
 size 374265936

logs/train/events.out.tfevents.1674736212.ip-10-39-226-229.afrd.expertcity.com.7323.0.v2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cff98a27069170cea1aaa6052749549feca7fa0a55f63512c5e490634c7c8ea
-size 9240811

 version https://git-lfs.github.com/spec/v1
+oid sha256:f9fde6675436496059599f6ec962d6b8800450df72c8ab63994fcc4061dc0f07
+size 9365683

logs/validation/events.out.tfevents.1674737933.ip-10-39-226-229.afrd.expertcity.com.7323.1.v2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e356356e1629c8161785341a42694721435df6eacf8957d72ae1a81371de8596
-size 10173

 version https://git-lfs.github.com/spec/v1
+oid sha256:3ab411a12fc2a3129a421662b5df4a478f4b19ab04edfcc86f621975a3b79bcb
+size 10330

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbfe87a421e92c9c1435c3ab0e18743ee2a396925a3d7d3e7a1660005c16a1ef
 size 374265936

 version https://git-lfs.github.com/spec/v1
+oid sha256:b7dc5a0a6ab08f37e7a0028dba415dd985421b95f7ff329a11666f3e684e253e
 size 374265936