Instructions to use llmware/bling-tiny-llama-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/bling-tiny-llama-v0 with Transformers:

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

pipe = pipeline("text-generation", model="llmware/bling-tiny-llama-v0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmware/bling-tiny-llama-v0")
model = AutoModelForCausalLM.from_pretrained("llmware/bling-tiny-llama-v0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use llmware/bling-tiny-llama-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmware/bling-tiny-llama-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/bling-tiny-llama-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/llmware/bling-tiny-llama-v0

SGLang

How to use llmware/bling-tiny-llama-v0 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 "llmware/bling-tiny-llama-v0" \
    --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": "llmware/bling-tiny-llama-v0",
		"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 "llmware/bling-tiny-llama-v0" \
        --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": "llmware/bling-tiny-llama-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use llmware/bling-tiny-llama-v0 with Docker Model Runner:
```
docker model run hf.co/llmware/bling-tiny-llama-v0
```

doberst commited on Dec 29, 2023

Commit

439a804

1 Parent(s): d2e2d23

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -36,9 +36,6 @@ For test run results (and good indicator of target use cases), please see the fi
 - **License:** Apache 2.0
 - **Finetuned from model:** TinyLlama-1.1b - 2.5T checkpoint
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 ### Direct Use
@@ -60,7 +57,7 @@ Any model can provide inaccurate or incomplete information, and should be used i
 ## How to Get Started with the Model
-The fastest way to get started with dRAGon is through direct import in transformers:
     from transformers import AutoTokenizer, AutoModelForCausalLM
     tokenizer = AutoTokenizer.from_pretrained("bling-tiny-llama-v0", trust_remote_code=True)
@@ -68,7 +65,7 @@ The fastest way to get started with dRAGon is through direct import in transform
 Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model.  The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.
-The dRAGon model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
     full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"

 - **License:** Apache 2.0
 - **Finetuned from model:** TinyLlama-1.1b - 2.5T checkpoint
 ### Direct Use
 ## How to Get Started with the Model
+The fastest way to get started with BLING is through direct import in transformers:
     from transformers import AutoTokenizer, AutoModelForCausalLM
     tokenizer = AutoTokenizer.from_pretrained("bling-tiny-llama-v0", trust_remote_code=True)
 Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model.  The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.
+The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
     full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"