Instructions to use kaizerBox/retnet-summarization_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaizerBox/retnet-summarization_small with Transformers:

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

pipe = pipeline("text-generation", model="kaizerBox/retnet-summarization_small")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("kaizerBox/retnet-summarization_small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kaizerBox/retnet-summarization_small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kaizerBox/retnet-summarization_small

SGLang

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

Docker Model Runner
How to use kaizerBox/retnet-summarization_small with Docker Model Runner:
```
docker model run hf.co/kaizerBox/retnet-summarization_small
```

kaizerBox commited on Nov 16, 2023

Commit

702e05e

1 Parent(s): 3dd66ce

retnet-summarization-small

Browse files

Files changed (4) hide show

README.md +9 -7
model.safetensors +1 -1
runs/Nov16_19-21-08_0302d3c57c64/events.out.tfevents.1700162469.0302d3c57c64.293.0 +3 -0
training_args.bin +1 -1

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 [kaizerBox/retnet-summarization_small](https://huggingface.co/kaizerBox/retnet-summarization_small) on the xsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.1604
 ## Model description
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0006
 - train_batch_size: 10
 - eval_batch_size: 10
 - seed: 42
@@ -44,19 +44,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- num_epochs: 1
 - mixed_precision_training: Native AMP
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 4.3639        | 1.0   | 4610 | 4.1604          |
 ### Framework versions
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu118
-- Datasets 2.14.7
 - Tokenizers 0.15.0

 This model is a fine-tuned version of [kaizerBox/retnet-summarization_small](https://huggingface.co/kaizerBox/retnet-summarization_small) on the xsum dataset.
 It achieves the following results on the evaluation set:
+- Loss: 4.1548
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.0001
 - train_batch_size: 10
 - eval_batch_size: 10
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 ### Training results
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 4.3508        | 1.0   | 4610  | 4.1581          |
+| 4.3471        | 2.0   | 9220  | 4.1551          |
+| 4.3446        | 3.0   | 13830 | 4.1548          |
 ### Framework versions
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu118
+- Datasets 2.15.0
 - Tokenizers 0.15.0

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830139f85933b4cdbb188d7a830804e191c2c03328df46182e6d7bb877c50812
 size 53857264

 version https://git-lfs.github.com/spec/v1
+oid sha256:10e909aa1a3aa9a5354a04476d7b9c9497bb4f3c9efc2dfaa95067eecd387e6a
 size 53857264

runs/Nov16_19-21-08_0302d3c57c64/events.out.tfevents.1700162469.0302d3c57c64.293.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c51e23ef366aed94410c4138d5b077324cf63776b8f8202c123beda70ac8c77e
+size 6239

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d173b57ff3ab32ed683cadaa60966f98a5dc0c1dd6918d53f6d1567488849aad
 size 4600

 version https://git-lfs.github.com/spec/v1
+oid sha256:a4faff7697c8861a7d2773edb4ddf18938f973965f3955bab32edc7e832ebb87
 size 4600