Instructions to use cansen88/PromptGenerator_5_topic_finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cansen88/PromptGenerator_5_topic_finetuned with Transformers:

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

pipe = pipeline("text-generation", model="cansen88/PromptGenerator_5_topic_finetuned")

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

tokenizer = AutoTokenizer.from_pretrained("cansen88/PromptGenerator_5_topic_finetuned")
model = AutoModelForCausalLM.from_pretrained("cansen88/PromptGenerator_5_topic_finetuned", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cansen88/PromptGenerator_5_topic_finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cansen88/PromptGenerator_5_topic_finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cansen88/PromptGenerator_5_topic_finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cansen88/PromptGenerator_5_topic_finetuned

SGLang

How to use cansen88/PromptGenerator_5_topic_finetuned 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 "cansen88/PromptGenerator_5_topic_finetuned" \
    --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": "cansen88/PromptGenerator_5_topic_finetuned",
		"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 "cansen88/PromptGenerator_5_topic_finetuned" \
        --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": "cansen88/PromptGenerator_5_topic_finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cansen88/PromptGenerator_5_topic_finetuned with Docker Model Runner:
```
docker model run hf.co/cansen88/PromptGenerator_5_topic_finetuned
```

cansen88 commited on Aug 11, 2022

Commit

03b52eb

1 Parent(s): 4abc6dd

End of training

Browse files

Files changed (2) hide show

README.md +7 -5
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [kmkarakaya/turkishReviews-ds](https://huggingface.co/kmkarakaya/turkishReviews-ds) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 6.0485
-- Train Sparse Categorical Accuracy: 0.1538
-- Validation Loss: 4.3579
-- Validation Sparse Categorical Accuracy: 0.3295
-- Epoch: 0
 ## Model description
@@ -45,6 +45,8 @@ The following hyperparameters were used during training:
 | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
 |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
 | 6.0485     | 0.1538                            | 4.3579          | 0.3295                                 | 0     |
 ### Framework versions

 This model is a fine-tuned version of [kmkarakaya/turkishReviews-ds](https://huggingface.co/kmkarakaya/turkishReviews-ds) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 3.4700
+- Train Sparse Categorical Accuracy: 0.4478
+- Validation Loss: 3.0986
+- Validation Sparse Categorical Accuracy: 0.4955
+- Epoch: 2
 ## Model description
 | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
 |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
 | 6.0485     | 0.1538                            | 4.3579          | 0.3295                                 | 0     |
+| 4.2300     | 0.3511                            | 3.5362          | 0.4432                                 | 1     |
+| 3.4700     | 0.4478                            | 3.0986          | 0.4955                                 | 2     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e38e68bd6975b8b8522bc0aabac45978304a3edf8b4b2c2d7f57b924fe0adad3
 size 497938536

 version https://git-lfs.github.com/spec/v1
+oid sha256:51eef4d81fc8e2a1eb2a2c52c1ace609c998a05d4760e80d22a1b707bfdf5dde
 size 497938536