Update README.md
Browse files
README.md
CHANGED
@@ -13,3 +13,17 @@ model_name: TextBase-7B-v0.1
|
|
13 |
model_type: mistral
|
14 |
quantized_by: mgonzs13
|
15 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
model_type: mistral
|
14 |
quantized_by: mgonzs13
|
15 |
---
|
16 |
+
|
17 |
+
|
18 |
+
# Mistroll-7B-v2.2-GGUF
|
19 |
+
|
20 |
+
**Model creator:** [SF-Foundation](https://huggingface.co/SF-Foundation)<br>
|
21 |
+
**Original model**: [TextBase-7B-v0.1](https://huggingface.co/SF-Foundation/TextBase-7B-v0.1)<br>
|
22 |
+
**GGUF quantization:** `llama.cpp` commit [4bfe50f741479c1df1c377260c3ff5702586719e](https://github.com/ggerganov/llama.cpp/tree/4bfe50f741479c1df1c377260c3ff5702586719e)<br>
|
23 |
+
|
24 |
+
## Description
|
25 |
+
Finetuned version of Mistral-7B-Instruct. Details on development to be published soon.
|
26 |
+
|
27 |
+
TextBase-7B was fine-tuned from the open source Mistral-7B model using a novel and patent-pending learning technique. Our learning framework relies on efficiently combining supervised and Reinforcement learning methods leveraging human and AI labels over a combination of public and CRM task-specific datasets. Supervised finetuning allows the model to learn task-specific skills while RLHF imparts human judgement making the model able to generalize, reason and follow instructions efficiently.
|
28 |
+
|
29 |
+
Checkout more models developed by Salesforce under https://huggingface.co/Salesforce
|