Update README.md
Browse files
README.md
CHANGED
@@ -18,9 +18,11 @@ datasets:
|
|
18 |
- CopyleftCultivars/Natural-Farming-Real-QandA-Conversations-Q1-2024-Update
|
19 |
---
|
20 |
|
21 |
-
#
|
22 |
|
23 |
-
-
|
|
|
|
|
24 |
- **License:** apache-2.0
|
25 |
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit
|
26 |
|
@@ -35,7 +37,7 @@ Shout out to roger j (bhugxer) and Steve Raisner for help with currating the dat
|
|
35 |
|
36 |
Testing and further compiling to integrate into on-device app interfaces are ongoing. This project was done for Copyleft Cultivars, a nonprofit, in partnership with Open Nutrient Project and Evergreen State College. This project serves to democratize access to farming knowledge and support the protection of vulnerable plants.
|
37 |
|
38 |
-
This is
|
39 |
|
40 |
This mistral model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
41 |
|
|
|
18 |
- CopyleftCultivars/Natural-Farming-Real-QandA-Conversations-Q1-2024-Update
|
19 |
---
|
20 |
|
21 |
+
# Mistral 7B Natural Farmer V4
|
22 |
|
23 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/654527ce2a13610acc25d921/MVgmvf5Hzf1KZjQWzmUnu.png)
|
24 |
+
|
25 |
+
- **Developed by:** Caleb DeLeeuw, Copyleft Cultivars (a nonprofit, protecting and preserving vulnerable plants)
|
26 |
- **License:** apache-2.0
|
27 |
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit
|
28 |
|
|
|
37 |
|
38 |
Testing and further compiling to integrate into on-device app interfaces are ongoing. This project was done for Copyleft Cultivars, a nonprofit, in partnership with Open Nutrient Project and Evergreen State College. This project serves to democratize access to farming knowledge and support the protection of vulnerable plants.
|
39 |
|
40 |
+
This is V4 beta. It runs locally on Ollama with some expirimental configuring so you can use it off the grid and places where internet is not accessible (ie most farms I've been on.)
|
41 |
|
42 |
This mistral model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
43 |
|