Instructions to use Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer 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_original_tokenizer")

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

tokenizer = AutoTokenizer.from_pretrained("Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer")
model = AutoModelForCausalLM.from_pretrained("Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer 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_original_tokenizer"
# 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_original_tokenizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer

SGLang

How to use Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer 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_original_tokenizer" \
    --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_original_tokenizer",
		"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_original_tokenizer" \
        --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_original_tokenizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer with Docker Model Runner:
```
docker model run hf.co/Ashraf-kasem/custom_gpt2_frames_text_original_tokenizer
```

Ashraf-kasem commited on Jan 26, 2023

Commit

8aceab7

1 Parent(s): 9b0055c

Training in progress epoch 16

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.1674688428.ip-10-39-226-87.afrd.expertcity.com.7702.0.v2 +2 -2
logs/validation/events.out.tfevents.1674691275.ip-10-39-226-87.afrd.expertcity.com.7702.1.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: 1.4200
-- Validation Loss: 1.7171
-- Epoch: 15
 ## Model description
@@ -58,6 +58,7 @@ The following hyperparameters were used during training:
 | 1.4994     | 1.7459          | 13    |
 | 1.4578     | 1.7294          | 14    |
 | 1.4200     | 1.7171          | 15    |
 ### 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: 1.3851
+- Validation Loss: 1.7026
+- Epoch: 16
 ## Model description
 | 1.4994     | 1.7459          | 13    |
 | 1.4578     | 1.7294          | 14    |
 | 1.4200     | 1.7171          | 15    |
+| 1.3851     | 1.7026          | 16    |
 ### Framework versions

checkpoint/extra_data.pickle CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad11a789016f90e43745b77cde01ea739b09640948c5d6ce9a1df44aa2273ee1
 size 995530137

 version https://git-lfs.github.com/spec/v1
+oid sha256:e0a757574778b797193ae32eda66a53b92ab1602a0fe0336ffcaa71d2f0af8f3
 size 995530137

checkpoint/weights.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a14697f5583c78286c2176a2a7fa914f8391df6d600582f3341d07be52ada5d
 size 497935440

 version https://git-lfs.github.com/spec/v1
+oid sha256:0aafdc3007b5d062f8631698af6fcee6e709a50a62d3e65feac16f41626636ff
 size 497935440

logs/train/events.out.tfevents.1674688428.ip-10-39-226-87.afrd.expertcity.com.7702.0.v2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d355480c9b0f240d6bf2a4d4294725129e74ae7e711200c993a0d0f2d45b491
-size 3119452

 version https://git-lfs.github.com/spec/v1
+oid sha256:89a315fe9cf174c7d18674a0e11192a655d28afd635f840e29bee94043cf92ac
+size 3244324

logs/validation/events.out.tfevents.1674691275.ip-10-39-226-87.afrd.expertcity.com.7702.1.v2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34920de854a5ab0650e61c5da63d555cc90fe03bedd7d976ccb6b9437c32bfef
-size 2480

 version https://git-lfs.github.com/spec/v1
+oid sha256:43fb90cd081525a86070aa4731fc659ab8f2f098332d3b79ac5815903398e421
+size 2637

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a14697f5583c78286c2176a2a7fa914f8391df6d600582f3341d07be52ada5d
 size 497935440

 version https://git-lfs.github.com/spec/v1
+oid sha256:0aafdc3007b5d062f8631698af6fcee6e709a50a62d3e65feac16f41626636ff
 size 497935440