Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,21 @@ the objective of providing a high-quality Instruct model that is 'inference-read
|
|
13 |
without using any advanced quantization optimizations.
|
14 |
|
15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
### Model Description
|
17 |
|
18 |
<!-- Provide a longer summary of what this model is. -->
|
@@ -85,7 +100,7 @@ my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
|
|
85 |
|
86 |
Darren Oberst & llmware team
|
87 |
|
88 |
-
Please reach out anytime if you are interested in this project
|
89 |
|
90 |
|
91 |
|
|
|
13 |
without using any advanced quantization optimizations.
|
14 |
|
15 |
|
16 |
+
### Benchmark Tests
|
17 |
+
|
18 |
+
Evaluated against the benchmark test: [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester)
|
19 |
+
Average of 2 Test Runs 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.
|
20 |
+
|
21 |
+
--**Accuracy Score**: **92.0** correct out of 100
|
22 |
+
--Not Found Classification: 45.0%
|
23 |
+
--Boolean: 75.0%
|
24 |
+
--Math/Logic: 20.0%
|
25 |
+
--Complex Questions (1-5): 2 (Low-Medium)
|
26 |
+
--Summarization Quality (1-5): 3 (Coherent, extractive)
|
27 |
+
--Hallucinations: No hallucinations observed in test runs.
|
28 |
+
|
29 |
+
For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).
|
30 |
+
|
31 |
### Model Description
|
32 |
|
33 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
100 |
|
101 |
Darren Oberst & llmware team
|
102 |
|
103 |
+
Please reach out anytime if you are interested in this project!
|
104 |
|
105 |
|
106 |
|