Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,13 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
3 |
---
|
4 |
|
5 |
-
#
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
-
**dragon-yi-
|
10 |
-
|
11 |
-
[**dragon-yi-6b**](https://huggingface.co/llmware/dragon-yi-6b-v0) is a fact-based question-answering model, optimized for complex business documents.
|
12 |
|
13 |
|
14 |
## Benchmark Tests
|
@@ -30,16 +29,16 @@ For test run results (and good indicator of target use cases), please see the fi
|
|
30 |
To pull the model via API:
|
31 |
|
32 |
from huggingface_hub import snapshot_download
|
33 |
-
snapshot_download("llmware/dragon-yi-
|
34 |
|
35 |
|
36 |
Load in your favorite GGUF inference engine, or try with llmware as follows:
|
37 |
|
38 |
from llmware.models import ModelCatalog
|
39 |
-
model = ModelCatalog().load_model("dragon-yi-
|
40 |
response = model.inference(query, add_context=text_sample)
|
41 |
|
42 |
-
Note: please review [**config.json**](https://huggingface.co/llmware/dragon-yi-
|
43 |
|
44 |
|
45 |
### Model Description
|
@@ -49,9 +48,8 @@ Note: please review [**config.json**](https://huggingface.co/llmware/dragon-yi-a
|
|
49 |
- **Developed by:** llmware
|
50 |
- **Model type:** GGUF
|
51 |
- **Language(s) (NLP):** English
|
52 |
-
- **License:**
|
53 |
-
|
54 |
-
|
55 |
|
56 |
## Model Card Contact
|
57 |
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
inference: false
|
4 |
---
|
5 |
|
6 |
+
# DRAGON-YI-9B-GGUF
|
7 |
|
8 |
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
|
10 |
+
**dragon-yi-9b-gguf** is a fact-based question-answering model, optimized for complex business documents, finetuned on top of 01-ai/yi-v1.5-9b base and quantizedwith 4_K_M GGUF quantization, providing an inference implementation for use on CPUs.
|
|
|
|
|
11 |
|
12 |
|
13 |
## Benchmark Tests
|
|
|
29 |
To pull the model via API:
|
30 |
|
31 |
from huggingface_hub import snapshot_download
|
32 |
+
snapshot_download("llmware/dragon-yi-9b-gguf", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
|
33 |
|
34 |
|
35 |
Load in your favorite GGUF inference engine, or try with llmware as follows:
|
36 |
|
37 |
from llmware.models import ModelCatalog
|
38 |
+
model = ModelCatalog().load_model("dragon-yi-9b-gguf")
|
39 |
response = model.inference(query, add_context=text_sample)
|
40 |
|
41 |
+
Note: please review [**config.json**](https://huggingface.co/llmware/dragon-yi-9b-gguf/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
|
42 |
|
43 |
|
44 |
### Model Description
|
|
|
48 |
- **Developed by:** llmware
|
49 |
- **Model type:** GGUF
|
50 |
- **Language(s) (NLP):** English
|
51 |
+
- **License:** Apache 2.0
|
52 |
+
|
|
|
53 |
|
54 |
## Model Card Contact
|
55 |
|