Instructions to use vincentmin/bloomz-1b1-eli5-pretrained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vincentmin/bloomz-1b1-eli5-pretrained with Transformers:

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

pipe = pipeline("text-generation", model="vincentmin/bloomz-1b1-eli5-pretrained")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vincentmin/bloomz-1b1-eli5-pretrained")
model = AutoModelForCausalLM.from_pretrained("vincentmin/bloomz-1b1-eli5-pretrained", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vincentmin/bloomz-1b1-eli5-pretrained with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vincentmin/bloomz-1b1-eli5-pretrained"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vincentmin/bloomz-1b1-eli5-pretrained",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vincentmin/bloomz-1b1-eli5-pretrained

SGLang

How to use vincentmin/bloomz-1b1-eli5-pretrained 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 "vincentmin/bloomz-1b1-eli5-pretrained" \
    --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": "vincentmin/bloomz-1b1-eli5-pretrained",
		"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 "vincentmin/bloomz-1b1-eli5-pretrained" \
        --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": "vincentmin/bloomz-1b1-eli5-pretrained",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vincentmin/bloomz-1b1-eli5-pretrained with Docker Model Runner:
```
docker model run hf.co/vincentmin/bloomz-1b1-eli5-pretrained
```

vincentmin commited on Apr 16, 2023

Commit

517d941

1 Parent(s): 62e3244

update model card README.md

Browse files

Files changed (1) hide show

README.md +7 -1

README.md CHANGED Viewed

@@ -13,6 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
 # bloomz-1b1-eli5-pretrained
 This model is a fine-tuned version of [bigscience/bloomz-1b1](https://huggingface.co/bigscience/bloomz-1b1) on an unknown dataset.
 ## Model description
@@ -38,10 +40,14 @@ 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: 100
-- training_steps: 5
 ### Training results
 ### Framework versions

 # bloomz-1b1-eli5-pretrained
 This model is a fine-tuned version of [bigscience/bloomz-1b1](https://huggingface.co/bigscience/bloomz-1b1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1743
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 100
+- training_steps: 2500
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.2783        | 0.4   | 1000 | 3.1924          |
+| 3.1211        | 0.8   | 2000 | 3.1743          |
 ### Framework versions