Upload README.md
Browse files
README.md
CHANGED
@@ -1,37 +1,29 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
inference: false
|
4 |
-
tags: [green, llmware-rag,
|
5 |
---
|
6 |
|
7 |
-
#
|
8 |
|
9 |
-
|
10 |
-
|
11 |
-
**dragon-llama-2-ov** is an OpenVino int4 quantized version of Dragon Llama-2, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.
|
12 |
-
|
13 |
-
[**dragon-llama-2**](https://huggingface.co/llmware/dragon-llama-2-7b-v0) is a fact-based question-answering model, optimized for complex business documents.
|
14 |
-
|
15 |
-
Get started right away with [OpenVino](https://github.com/openvinotoolkit/openvino)
|
16 |
-
|
17 |
-
Looking for AI PC solutions and demos, contact us at [llmware](https://www.llmware.ai)
|
18 |
|
|
|
19 |
|
20 |
### Model Description
|
21 |
|
22 |
- **Developed by:** llmware
|
23 |
-
- **Model type:**
|
24 |
-
- **Parameters:**
|
25 |
-
- **
|
|
|
26 |
- **Language(s) (NLP):** English
|
27 |
-
- **License:**
|
28 |
-
- **Uses:** Fact-based question-answering
|
29 |
-
- **RAG Benchmark Accuracy Score:**
|
30 |
-
- **Quantization:** int4
|
31 |
-
|
32 |
|
33 |
-
## Model Card Contact
|
34 |
|
|
|
|
|
35 |
[llmware on hf](https://www.huggingface.co/llmware)
|
36 |
-
|
37 |
-
[llmware website](https://www.llmware.ai)
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
inference: false
|
4 |
+
tags: [green, llmware-rag, p1, ov]
|
5 |
---
|
6 |
|
7 |
+
# bling-tiny-llama-ov
|
8 |
|
9 |
+
**bling-tiny-llama-ov** is a very small, very fast fact-based question-answering model, designed for retrieval augmented generation (RAG) with complex business documents, quantized and packaged in OpenVino int4 for AI PCs using Intel GPU, CPU and NPU.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
+
This model is one of the smallest and fastest in the series. For higher accuracy, look at larger models in the BLING/DRAGON series.
|
12 |
|
13 |
### Model Description
|
14 |
|
15 |
- **Developed by:** llmware
|
16 |
+
- **Model type:** tinyllama
|
17 |
+
- **Parameters:** 1.1 billion
|
18 |
+
- **Quantization:** int4
|
19 |
+
- **Model Parent:** [llmware/bling-tiny-llama-v0](https://www.huggingface.co/llmware/bling-tiny-llama-v0)
|
20 |
- **Language(s) (NLP):** English
|
21 |
+
- **License:** Apache 2.0
|
22 |
+
- **Uses:** Fact-based question-answering, RAG
|
23 |
+
- **RAG Benchmark Accuracy Score:** 86.5
|
|
|
|
|
24 |
|
|
|
25 |
|
26 |
+
## Model Card Contact
|
27 |
+
[llmware on github](https://www.github.com/llmware-ai/llmware)
|
28 |
[llmware on hf](https://www.huggingface.co/llmware)
|
29 |
+
[llmware website](https://www.llmware.ai)
|
|