|
--- |
|
license: llama3.1 |
|
inference: false |
|
--- |
|
|
|
# DRAGON-LLAMA-3.1-GGUF |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
dragon-llama-3.1-gguf is RAG-instruct trained on top of a Llama-3.1 base model. |
|
|
|
### Benchmark Tests |
|
|
|
Evaluated against the benchmark test: [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester) |
|
1 Test Run (temperature=0.0, sample=False) with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations. |
|
|
|
--**Accuracy Score**: **94.0** correct out of 100 |
|
--Not Found Classification: 70.0% |
|
--Boolean: 90.0% |
|
--Math/Logic: 72.5% |
|
--Complex Questions (1-5): 4 (Above Average - table-reading, causal) |
|
--Summarization Quality (1-5): 4 (Above Average) |
|
--Hallucinations: No hallucinations but a few instances of drawing on 'background' knowledge. |
|
|
|
For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo). |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
- **Developed by:** llmware |
|
- **Model type:** Phi-2B |
|
- **Language(s) (NLP):** English |
|
- **License:** Llama-3.1 Community License |
|
- **Finetuned from model:** Llama-3.1-Base |
|
|
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
<!-- This section is meant to convey both technical and sociotechnical limitations. --> |
|
|
|
Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms. |
|
|
|
|
|
## 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("dragon-llama-3.1-gguf", trust_remote_code=True) |
|
model = AutoModelForCausalLM.from_pretrained("dragon-llama-3.1-gguf", 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 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>:" |
|
|
|
The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts: |
|
|
|
1. Text Passage Context, and |
|
2. Specific question or instruction based on the text passage |
|
|
|
To get the best results, package "my_prompt" as follows: |
|
|
|
my_prompt = {{text_passage}} + "\n" + {{question/instruction}} |
|
|
|
|
|
|
|
|
|
## Model Card Contact |
|
|
|
Darren Oberst & llmware team |
