Instructions to use ninagroot/GPT2-705M-finaltest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ninagroot/GPT2-705M-finaltest with Transformers:

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

pipe = pipeline("text-generation", model="ninagroot/GPT2-705M-finaltest")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ninagroot/GPT2-705M-finaltest")
model = AutoModelForCausalLM.from_pretrained("ninagroot/GPT2-705M-finaltest")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ninagroot/GPT2-705M-finaltest with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ninagroot/GPT2-705M-finaltest"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ninagroot/GPT2-705M-finaltest",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ninagroot/GPT2-705M-finaltest

SGLang

How to use ninagroot/GPT2-705M-finaltest 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 "ninagroot/GPT2-705M-finaltest" \
    --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": "ninagroot/GPT2-705M-finaltest",
		"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 "ninagroot/GPT2-705M-finaltest" \
        --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": "ninagroot/GPT2-705M-finaltest",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ninagroot/GPT2-705M-finaltest with Docker Model Runner:
```
docker model run hf.co/ninagroot/GPT2-705M-finaltest
```

ninagroot commited on Apr 30, 2024

Commit

f532b73

verified ·

1 Parent(s): 5a01a19

ninagroot/GPT2-705M

Browse files

Files changed (4) hide show

README.md +16 -16
model.safetensors +1 -1
runs/Apr30_09-29-06_gcn43.local.snellius.surf.nl/events.out.tfevents.1714462155.gcn43.local.snellius.surf.nl.1323828.0 +3 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6360
 ## Model description
@@ -48,21 +48,21 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 6.8909        | 1.0   | 3    | 6.8543          |
-| 6.5777        | 2.0   | 6    | 6.6044          |
-| 6.1737        | 3.0   | 9    | 6.0199          |
-| 4.9169        | 4.0   | 12   | 5.6155          |
-| 4.8865        | 5.0   | 15   | 5.0512          |
-| 4.5264        | 6.0   | 18   | 5.0486          |
-| 4.4735        | 7.0   | 21   | 4.8273          |
-| 4.2863        | 8.0   | 24   | 4.5819          |
-| 4.2414        | 9.0   | 27   | 4.3691          |
-| 3.8679        | 10.0  | 30   | 4.1423          |
-| 3.6495        | 11.0  | 33   | 3.9487          |
-| 3.5756        | 12.0  | 36   | 3.7239          |
-| 3.3813        | 13.0  | 39   | 3.6837          |
-| 3.3619        | 14.0  | 42   | 3.6824          |
-| 2.9598        | 15.0  | 45   | 3.6360          |
 ### Framework versions

 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 3.5805
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 6.872         | 1.0   | 3    | 6.7840          |
+| 6.4623        | 2.0   | 6    | 6.5344          |
+| 6.1624        | 3.0   | 9    | 6.1049          |
+| 4.8878        | 4.0   | 12   | 5.8237          |
+| 4.908         | 5.0   | 15   | 5.1010          |
+| 4.6666        | 6.0   | 18   | 5.0636          |
+| 4.4854        | 7.0   | 21   | 4.7967          |
+| 5.0298        | 8.0   | 24   | 5.1645          |
+| 4.4216        | 9.0   | 27   | 4.4990          |
+| 4.1914        | 10.0  | 30   | 4.3240          |
+| 3.909         | 11.0  | 33   | 4.1773          |
+| 3.8537        | 12.0  | 36   | 3.9425          |
+| 3.4798        | 13.0  | 39   | 3.8305          |
+| 3.487         | 14.0  | 42   | 3.8480          |
+| 3.1947        | 15.0  | 45   | 3.5805          |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3fa2ce5f8ea3b23ec7b6a19696c488fa27e798657655be8e0195422365d2f51
 size 2748401440

 version https://git-lfs.github.com/spec/v1
+oid sha256:04106f7902e74cdbfd08920ac6fb490883909b747a961ffd285ca1ad3811ce6a
 size 2748401440

runs/Apr30_09-29-06_gcn43.local.snellius.surf.nl/events.out.tfevents.1714462155.gcn43.local.snellius.surf.nl.1323828.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1393977e6d7cebd99f0f2d8e31f6a406c604d3c19bf0d6e4c2b0420cea1279a3
+size 18331

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535138499f2724af54616d0524e426c46d13db06547b6595c1556c8a9b3610e3
 size 4984

 version https://git-lfs.github.com/spec/v1
+oid sha256:003e0338c870166b9bddaee48b9f939fcd613c657ea0ddad0ccb2ccb5b11a6d2
 size 4984