Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
---
|
4 |
+
|
5 |
+
# Model Card for Model ID
|
6 |
+
|
7 |
+
bling-sheared-llama-1.3b-0.1 is part of the BLING ("Best Little Instruction-following No-GPU-required") model series, instruct trained on top of a Sheared-LLaMA-1.3B base model.
|
8 |
+
|
9 |
+
BLING models are fine-tuned with distilled high-quality custom instruct datasets, targeted at a specific subset of instruct tasks with
|
10 |
+
the objective of providing a high-quality Instruct model that is 'inference-ready' on a CPU laptop even
|
11 |
+
without using any advanced quantization optimizations.
|
12 |
+
|
13 |
+
### Model Description
|
14 |
+
|
15 |
+
- **Developed by:** llmware
|
16 |
+
- **Model type:** Instruct-trained decoder
|
17 |
+
- **Language(s) (NLP):** English
|
18 |
+
- **License:** Apache 2.0
|
19 |
+
- **Finetuned from model [optional]:** princeton-nlp/Sheared-LLaMA-1.3B
|
20 |
+
|
21 |
+
|
22 |
+
## Uses
|
23 |
+
|
24 |
+
The intended use of BLING models is two-fold:
|
25 |
+
|
26 |
+
1. Provide high-quality Instruct models that can run on a laptop for local testing. We have found it extremely useful when building a
|
27 |
+
proof-of-concept, or working with sensitive enterprise data that must be closely guarded, especially in RAG use cases.
|
28 |
+
|
29 |
+
2. Push the state of the art for smaller Instruct-following models in the sub-7B parameter range, especially 1B-3B, as single-purpose
|
30 |
+
automation tools for specific tasks through targeted fine-tuning datasets and focused "instruction" tasks.
|
31 |
+
|
32 |
+
|
33 |
+
### Direct Use
|
34 |
+
|
35 |
+
BLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,
|
36 |
+
legal and regulatory industries with complex information sources. Rather than try to be "all things to all people," BLING models try to focus on a narrower set of Instructions more suitable to a ~1B parameter GPT model.
|
37 |
+
|
38 |
+
BLING is ideal for rapid prototyping, testing, and the ability to perform an end-to-end workflow locally on a laptop without
|
39 |
+
having to send sensitive information over an Internet-based API.
|
40 |
+
|
41 |
+
The first BLING models have been trained for common RAG scenarios, specifically: question-answering, key-value extraction, and basic summarization as the core instruction types
|
42 |
+
without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
|
43 |
+
|
44 |
+
|
45 |
+
## Bias, Risks, and Limitations
|
46 |
+
|
47 |
+
Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.
|
48 |
+
|