Instructions to use Ashraf-kasem/custom_gpt2_frames_text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ashraf-kasem/custom_gpt2_frames_text 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")

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

tokenizer = AutoTokenizer.from_pretrained("Ashraf-kasem/custom_gpt2_frames_text")
model = AutoModelForCausalLM.from_pretrained("Ashraf-kasem/custom_gpt2_frames_text", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ashraf-kasem/custom_gpt2_frames_text 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"
# 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",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ashraf-kasem/custom_gpt2_frames_text

SGLang

How to use Ashraf-kasem/custom_gpt2_frames_text 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" \
    --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",
		"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" \
        --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",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ashraf-kasem/custom_gpt2_frames_text with Docker Model Runner:
```
docker model run hf.co/Ashraf-kasem/custom_gpt2_frames_text
```

Ashraf-kasem commited on Jan 25, 2023

Commit

7b941fe

1 Parent(s): 5e34fa9

Training in progress epoch 14

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.1674587149.ip-10-39-226-229.afrd.expertcity.com.22831.0.v2 +2 -2
logs/validation/events.out.tfevents.1674588886.ip-10-39-226-229.afrd.expertcity.com.22831.1.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 [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.8960
-- Validation Loss: 2.2214
-- Epoch: 13
 ## Model description
@@ -56,6 +56,7 @@ The following hyperparameters were used during training:
 | 2.0236     | 2.2740          | 11    |
 | 1.9569     | 2.2443          | 12    |
 | 1.8960     | 2.2214          | 13    |
 ### Framework versions

 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 1.8411
+- Validation Loss: 2.1954
+- Epoch: 14
 ## Model description
 | 2.0236     | 2.2740          | 11    |
 | 1.9569     | 2.2443          | 12    |
 | 1.8960     | 2.2214          | 13    |
+| 1.8411     | 2.1954          | 14    |
 ### Framework versions

checkpoint/extra_data.pickle CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6fcdba7b850bccc10035bbe4bdb66a402a3971ca0d5bf96d349160ce7ed6a88
 size 748191129

 version https://git-lfs.github.com/spec/v1
+oid sha256:bf11a14da5a3d39f845f5ebbb7521daa892a97229349d0c6a3813faaa7c7a9f7
 size 748191129

checkpoint/weights.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c5b34e417f3b042c739aea9aab7e16a82b24d8b5c24f8ee5f98d48a042a8965
 size 374265936

 version https://git-lfs.github.com/spec/v1
+oid sha256:9bf120a4a9ab4a69e79cd0513c3941f9ed791071fe7bffc331cde8bfdb4f1692
 size 374265936

logs/train/events.out.tfevents.1674587149.ip-10-39-226-229.afrd.expertcity.com.22831.0.v2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c62341b6af9aa9c205c93980c77e9b20f20fd687ad572cbc7c213c20c840099
-size 2869694

 version https://git-lfs.github.com/spec/v1
+oid sha256:cb27c2d2cf32dff11d24e564887ba932dc8c808e3f9f3cdd56ea1af6d8007d5c
+size 2994566

logs/validation/events.out.tfevents.1674588886.ip-10-39-226-229.afrd.expertcity.com.22831.1.v2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c190678156ec9ffc85d4d71d0474c19c3f67781f982d99d98b06365333f9e65
-size 2166

 version https://git-lfs.github.com/spec/v1
+oid sha256:1b61700b026b446eeea45df7c021497e7ff3190de2625fd1573944bf331eb4c1
+size 2323

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c5b34e417f3b042c739aea9aab7e16a82b24d8b5c24f8ee5f98d48a042a8965
 size 374265936

 version https://git-lfs.github.com/spec/v1
+oid sha256:9bf120a4a9ab4a69e79cd0513c3941f9ed791071fe7bffc331cde8bfdb4f1692
 size 374265936