Upload README.md
Browse files
README.md
CHANGED
@@ -1,20 +1,28 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
---
|
4 |
|
5 |
# Model Card for Model ID
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
-
**dragon-
|
10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
Load in your favorite GGUF inference engine, or try with llmware as follows:
|
13 |
|
14 |
-
from llmware.models import ModelCatalog
|
|
|
|
|
15 |
|
16 |
-
|
17 |
-
response = qa_tool.inference(question, text_sample)
|
18 |
|
19 |
|
20 |
### Model Description
|
@@ -24,17 +32,9 @@ Load in your favorite GGUF inference engine, or try with llmware as follows:
|
|
24 |
- **Developed by:** llmware
|
25 |
- **Model type:** GGUF
|
26 |
- **Language(s) (NLP):** English
|
27 |
-
- **License:**
|
28 |
-
- **Quantized from model:** llmware/dragon-
|
29 |
-
|
30 |
-
## Uses
|
31 |
-
|
32 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
33 |
-
|
34 |
-
All of the DRAGON models use the following prompt template:
|
35 |
-
|
36 |
-
"<human> " + text + "\n" + question + "\n<bot>: "
|
37 |
-
|
38 |
|
39 |
## Model Card Contact
|
40 |
|
|
|
1 |
---
|
2 |
+
license: llama2
|
3 |
---
|
4 |
|
5 |
# Model Card for Model ID
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
+
**dragon-llama-answer-tool** is a quantized version of DRAGON Llama 7B, with 4_K_M GGUF quantization, providing a fast, small inference implementation for use on CPUs.
|
10 |
|
11 |
+
[**DRAGON LLama 7B**](https://huggingface.co/llmware/dragon-llama-7b-v0) is a fact-based question-answering model, optimized for complex business documents.
|
12 |
+
|
13 |
+
We are providing as a separate repository that can be pulled directly:
|
14 |
+
|
15 |
+
from huggingface_hub import snapshot_download
|
16 |
+
snapshot_download("llmware/dragon-llama-answer-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
|
17 |
+
|
18 |
|
19 |
Load in your favorite GGUF inference engine, or try with llmware as follows:
|
20 |
|
21 |
+
from llmware.models import ModelCatalog
|
22 |
+
model = ModelCatalog().load_model("llmware/dragon-llama-answer-tool")
|
23 |
+
response = model.inference(query, text_sample)
|
24 |
|
25 |
+
Note: please review [**config.json**](https://huggingface.co/llmware/dragon-llama-answer-tool/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
|
|
|
26 |
|
27 |
|
28 |
### Model Description
|
|
|
32 |
- **Developed by:** llmware
|
33 |
- **Model type:** GGUF
|
34 |
- **Language(s) (NLP):** English
|
35 |
+
- **License:** Llama 2 Community License
|
36 |
+
- **Quantized from model:** [llmware/dragon-llama](https://huggingface.co/llmware/dragon-llama-7b-v0/)
|
37 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
|
39 |
## Model Card Contact
|
40 |
|