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

Libraries

How to use llmware/bling-answer-tool with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmware/bling-answer-tool", dtype="auto")

llama-cpp-python

How to use llmware/bling-answer-tool with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/bling-answer-tool",
	filename="bling-answer.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use llmware/bling-answer-tool with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/bling-answer-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/bling-answer-tool

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/bling-answer-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/bling-answer-tool

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf llmware/bling-answer-tool
# Run inference directly in the terminal:
./llama-cli -hf llmware/bling-answer-tool

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf llmware/bling-answer-tool
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/bling-answer-tool

Use Docker

docker model run hf.co/llmware/bling-answer-tool

LM Studio
Jan
Ollama
How to use llmware/bling-answer-tool with Ollama:
```
ollama run hf.co/llmware/bling-answer-tool
```

Unsloth Studio

How to use llmware/bling-answer-tool with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for llmware/bling-answer-tool to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for llmware/bling-answer-tool to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmware/bling-answer-tool to start chatting

Docker Model Runner
How to use llmware/bling-answer-tool with Docker Model Runner:
```
docker model run hf.co/llmware/bling-answer-tool
```

Lemonade

How to use llmware/bling-answer-tool with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/bling-answer-tool

Run and chat with the model

lemonade run user.bling-answer-tool-{{QUANT_TAG}}

List all available models

lemonade list

doberst commited on Feb 5, 2024

Commit

0099a4c

verified ·

1 Parent(s): 9cc8689

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -6,23 +6,23 @@ license: apache-2.0
 <!-- Provide a quick summary of what the model is/does. -->
-**dragon-mistral-answer-tool** is a quantized version of DRAGON Mistral 7B, with 4_K_M GGUF quantization, providing a fast, small inference implementation for use on CPUs.
-[**dragon-mistral-7b**](https://huggingface.co/llmware/dragon-mistral-7b-v0) is a fact-based question-answering model, optimized for complex business documents.
 To pull the model via API:
     from huggingface_hub import snapshot_download
-    snapshot_download("llmware/dragon-mistral-answer-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
 Load in your favorite GGUF inference engine, or try with llmware as follows:
     from llmware.models import ModelCatalog
-    model = ModelCatalog().load_model("dragon-mistral-answer-tool")
     response = model.inference(query, add_context=text_sample)
-Note: please review [**config.json**](https://huggingface.co/llmware/dragon-mistral-answer-tool/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
 ### Model Description
@@ -33,7 +33,7 @@ Note: please review [**config.json**](https://huggingface.co/llmware/dragon-mist
 - **Model type:** GGUF
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
-- **Quantized from model:** [llmware/dragon-mistral](https://huggingface.co/llmware/dragon-mistral-7b-v0/)
 ## Model Card Contact

 <!-- Provide a quick summary of what the model is/does. -->
+**bling-answer-tool** is a quantized version of BLING Tiny-Llama 1B, with 4_K_M GGUF quantization, providing a very fast, very small inference implementation for use on CPUs.
+[**bling-tiny-llama**](https://huggingface.co/llmware/bling-tiny-llama-v0) is a fact-based question-answering model, optimized for complex business documents.
 To pull the model via API:
     from huggingface_hub import snapshot_download
+    snapshot_download("llmware/bling-answer-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
 Load in your favorite GGUF inference engine, or try with llmware as follows:
     from llmware.models import ModelCatalog
+    model = ModelCatalog().load_model("bling-answer-tool")
     response = model.inference(query, add_context=text_sample)
+Note: please review [**config.json**](https://huggingface.co/llmware/bling-answer-tool/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
 ### Model Description
 - **Model type:** GGUF
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
+- **Quantized from model:** [llmware/dragon-mistral](https://huggingface.co/llmware/bling-tiny-llama-v0/)
 ## Model Card Contact