Upload README.md
Browse files
README.md
CHANGED
@@ -6,47 +6,57 @@ license: apache-2.0
|
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
-
|
10 |
|
11 |
-
|
12 |
-
the objective of providing a high-quality Instruct model that is 'inference-ready' on a CPU laptop even
|
13 |
-
without using any advanced quantization optimizations.
|
14 |
|
15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
### Model Description
|
17 |
|
18 |
<!-- Provide a longer summary of what this model is. -->
|
19 |
|
20 |
- **Developed by:** llmware
|
21 |
-
- **Model type:**
|
22 |
- **Language(s) (NLP):** English
|
23 |
- **License:** Apache 2.0
|
24 |
-
- **Finetuned from model:**
|
25 |
|
26 |
## Uses
|
27 |
|
28 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
29 |
|
30 |
-
The intended use of
|
|
|
|
|
31 |
|
32 |
-
|
33 |
-
proof-of-concept, or working with sensitive enterprise data that must be closely guarded, especially in RAG use cases.
|
34 |
|
35 |
-
|
36 |
-
automation tools for specific tasks through targeted fine-tuning datasets and focused "instruction" tasks.
|
37 |
|
38 |
|
39 |
### Direct Use
|
40 |
|
41 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
|
43 |
-
|
44 |
-
legal and regulatory industries with complex information sources.
|
45 |
-
|
46 |
-
BLING is ideal for rapid prototyping, testing, and the ability to perform an end-to-end workflow locally on a laptop without
|
47 |
-
having to send sensitive information over an Internet-based API.
|
48 |
|
49 |
-
|
50 |
without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
|
51 |
|
52 |
|
@@ -62,8 +72,8 @@ Any model can provide inaccurate or incomplete information, and should be used i
|
|
62 |
The fastest way to get started with BLING is through direct import in transformers:
|
63 |
|
64 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
65 |
-
tokenizer = AutoTokenizer.from_pretrained("
|
66 |
-
model = AutoModelForCausalLM.from_pretrained("
|
67 |
|
68 |
|
69 |
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
@@ -85,7 +95,7 @@ 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 |
|
|
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
+
dragon-llama-7b-0.1 part of the dRAGon ("Delivering RAG On Private Cloud") model series, RAG-instruct trained on top of a LLama-2 base model.
|
10 |
|
11 |
+
DRAGON models are fine-tuned with high-quality custom instruct datasets, designed for production quality use in RAG scenarios.
|
|
|
|
|
12 |
|
13 |
|
14 |
+
### Benchmark Tests
|
15 |
+
|
16 |
+
Evaluated against the benchmark test: [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester)
|
17 |
+
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.
|
18 |
+
|
19 |
+
--**Accuracy Score**: **99.0** correct out of 100
|
20 |
+
--Not Found Classification: 95.0%
|
21 |
+
--Boolean: 82.5%
|
22 |
+
--Math/Logic: 70.0%
|
23 |
+
--Complex Questions (1-5): 4 (Low-Medium)
|
24 |
+
--Summarization Quality (1-5): 4 (Coherent, extractive)
|
25 |
+
--Hallucinations: No hallucinations observed in test runs.
|
26 |
+
|
27 |
+
For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).
|
28 |
+
|
29 |
### Model Description
|
30 |
|
31 |
<!-- Provide a longer summary of what this model is. -->
|
32 |
|
33 |
- **Developed by:** llmware
|
34 |
+
- **Model type:** LLama-2
|
35 |
- **Language(s) (NLP):** English
|
36 |
- **License:** Apache 2.0
|
37 |
+
- **Finetuned from model:** Llama-2-7B-Base
|
38 |
|
39 |
## Uses
|
40 |
|
41 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
42 |
|
43 |
+
The intended use of DRAGON models is two-fold:
|
44 |
+
|
45 |
+
1. Provide high-quality RAG-Instruct models designed for fact-based, no "hallucination" question-answering in connection with an enterprise RAG workflow.
|
46 |
|
47 |
+
2. DRAGON models are fine-tuned on top of leading base foundation models, generally in the 6-7B+ range, and purposefully rolled-out across multiple base models to provide choices and "drop-in" replacements for RAG specific use cases.
|
|
|
48 |
|
49 |
+
3. DRAGON models were trained on the same principles as the BLING models, so generally, it should be easy to "upgrade" from a BLING model in testing to a DRAGON model in production.
|
|
|
50 |
|
51 |
|
52 |
### Direct Use
|
53 |
|
54 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
55 |
|
56 |
+
DRAGON is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,
|
57 |
+
legal and regulatory industries with complex information sources.
|
|
|
|
|
|
|
58 |
|
59 |
+
DRAGON models have been trained for common RAG scenarios, specifically: question-answering, key-value extraction, and basic summarization as the core instruction types
|
60 |
without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
|
61 |
|
62 |
|
|
|
72 |
The fastest way to get started with BLING is through direct import in transformers:
|
73 |
|
74 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
75 |
+
tokenizer = AutoTokenizer.from_pretrained("dragon-llama-7b-0.1")
|
76 |
+
model = AutoModelForCausalLM.from_pretrained("dragon-llama-7b-0.1")
|
77 |
|
78 |
|
79 |
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
|
|
95 |
|
96 |
Darren Oberst & llmware team
|
97 |
|
98 |
+
Please reach out anytime if you are interested in this project!
|
99 |
|
100 |
|
101 |
|