Instructions to use temporary0-0name/pretrained_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use temporary0-0name/pretrained_model with Transformers:

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

pipe = pipeline("text-generation", model="temporary0-0name/pretrained_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("temporary0-0name/pretrained_model")
model = AutoModelForCausalLM.from_pretrained("temporary0-0name/pretrained_model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use temporary0-0name/pretrained_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "temporary0-0name/pretrained_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "temporary0-0name/pretrained_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/temporary0-0name/pretrained_model

SGLang

How to use temporary0-0name/pretrained_model 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 "temporary0-0name/pretrained_model" \
    --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": "temporary0-0name/pretrained_model",
		"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 "temporary0-0name/pretrained_model" \
        --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": "temporary0-0name/pretrained_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use temporary0-0name/pretrained_model with Docker Model Runner:
```
docker model run hf.co/temporary0-0name/pretrained_model
```

temporary0-0name commited on Nov 18, 2023

Commit

d77b1bf

1 Parent(s): 5ac1cd1

End of training

Browse files

Files changed (2) hide show

README.md +2 -2
runs/Nov18_14-38-39_bdcc79452b0f/events.out.tfevents.1700318744.bdcc79452b0f.5253.2 +2 -2

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [temporary0-0name/pretrained_model](https://huggingface.co/temporary0-0name/pretrained_model) on the wikitext dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.4796
 ## Model description
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 7.6923        | 0.55  | 100  | 6.4796          |
 ### Framework versions

 This model is a fine-tuned version of [temporary0-0name/pretrained_model](https://huggingface.co/temporary0-0name/pretrained_model) on the wikitext dataset.
 It achieves the following results on the evaluation set:
+- Loss: 5.1977
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 6.0912        | 0.55  | 100  | 5.1977          |
 ### Framework versions

runs/Nov18_14-38-39_bdcc79452b0f/events.out.tfevents.1700318744.bdcc79452b0f.5253.2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa1de5e1ae61796a78fe1e29c821b5d88c35c1c4d374206eae549eeb8a04331
-size 4669

 version https://git-lfs.github.com/spec/v1
+oid sha256:2e45454c2030a39c9e97b8d54742b38b7d432c011fdf41198639ea6779c3e693
+size 5023