InferenceIllusionist commited on
Commit
1932bfa
1 Parent(s): 8ef16f0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -4
README.md CHANGED
@@ -7,16 +7,30 @@ tags:
7
  - transformers
8
  - unsloth
9
  - mistral
10
- - gguf
11
- base_model: mistral-community/Mistral-7B-v0.2
 
 
 
12
  ---
 
13
 
14
- # Uploaded model
 
 
 
 
 
 
 
 
 
 
 
15
 
16
  - **Developed by:** InferenceIllusionist
17
  - **License:** apache-2.0
18
  - **Finetuned from model :** mistral-community/Mistral-7B-v0.2
19
 
20
- This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
21
 
22
  [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
7
  - transformers
8
  - unsloth
9
  - mistral
10
+ - trl
11
+ - sft
12
+ base_model: unsloth/mistral-7b-v0.2-bnb-4bit
13
+ datasets:
14
+ - visheratin/realworldqa
15
  ---
16
+ # Mistral-RealworldQA-v0.2-7b SFT GGUF
17
 
18
+ <img src="https://i.imgur.com/Pf53ms5.jpeg" width="400"/>
19
+
20
+
21
+ An experiment with the goal of reducing halucinations in [VQA](https://huggingface.co/tasks/visual-question-answering)
22
+ First in of a series of projects centering around fine-tuning for image captioning.
23
+
24
+ Release Notes:
25
+ * v0.1 - Initial Release
26
+ * v0.2 (Current)- Updating base model to official Mistral-7b fp16 release, refinements to dataset and instruction formating
27
+
28
+
29
+ Mistral-7b-02 base model was fine-tuned using the [RealWorldQA dataset](https://huggingface.co/datasets/visheratin/realworldqa), originally provided by the X.Ai Team here: https://x.ai/blog/grok-1.5v
30
 
31
  - **Developed by:** InferenceIllusionist
32
  - **License:** apache-2.0
33
  - **Finetuned from model :** mistral-community/Mistral-7B-v0.2
34
 
 
35
 
36
  [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)