Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,7 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- 4-bit
|
|
@@ -6,10 +9,67 @@ tags:
|
|
| 6 |
- text-generation
|
| 7 |
- autotrain_compatible
|
| 8 |
- endpoints_compatible
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
inference: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
quantized_by: Suparious
|
| 12 |
---
|
| 13 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
-
**UPLOAD IN PROGRESS**
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- 4-bit
|
|
|
|
| 9 |
- text-generation
|
| 10 |
- autotrain_compatible
|
| 11 |
- endpoints_compatible
|
| 12 |
+
- text-generation-inference
|
| 13 |
+
- transformers
|
| 14 |
+
- unsloth
|
| 15 |
+
- mistral
|
| 16 |
+
- trl
|
| 17 |
+
- code
|
| 18 |
+
- 'medical '
|
| 19 |
+
- farmer
|
| 20 |
+
- doctor
|
| 21 |
+
- Mega-Series
|
| 22 |
+
- Cyber-Series
|
| 23 |
+
- Role-Play
|
| 24 |
+
- Self-Rag
|
| 25 |
+
- ThinkingBot
|
| 26 |
+
- milestone
|
| 27 |
+
- mega-series
|
| 28 |
+
- SpydazWebAI
|
| 29 |
+
base_model: LeroyDyer/Mixtral_AI_CyberTron_Ultra
|
| 30 |
pipeline_tag: text-generation
|
| 31 |
inference: false
|
| 32 |
+
metrics:
|
| 33 |
+
- accuracy
|
| 34 |
+
- bertscore
|
| 35 |
+
- bleu
|
| 36 |
+
- brier_score
|
| 37 |
+
- cer
|
| 38 |
+
- character
|
| 39 |
+
- charcut_mt
|
| 40 |
+
- chrf
|
| 41 |
+
- code_eval
|
| 42 |
+
datasets:
|
| 43 |
+
- gretelai/synthetic_text_to_sql
|
| 44 |
+
- HuggingFaceTB/cosmopedia
|
| 45 |
+
- teknium/OpenHermes-2.5
|
| 46 |
+
- Open-Orca/SlimOrca
|
| 47 |
+
- Open-Orca/OpenOrca
|
| 48 |
+
- cognitivecomputations/dolphin-coder
|
| 49 |
+
- databricks/databricks-dolly-15k
|
| 50 |
+
- yahma/alpaca-cleaned
|
| 51 |
+
- uonlp/CulturaX
|
| 52 |
+
- mwitiderrick/SwahiliPlatypus
|
| 53 |
+
- swahili
|
| 54 |
+
- Rogendo/English-Swahili-Sentence-Pairs
|
| 55 |
+
- ise-uiuc/Magicoder-Evol-Instruct-110K
|
| 56 |
+
- meta-math/MetaMathQA
|
| 57 |
quantized_by: Suparious
|
| 58 |
---
|
| 59 |
+
# LeroyDyer/Mixtral_AI_CyberTron_Ultra AWQ
|
| 60 |
+
|
| 61 |
+
- Model creator: [LeroyDyer](https://huggingface.co/LeroyDyer)
|
| 62 |
+
- Original model: [Mixtral_AI_CyberTron_Ultra](https://huggingface.co/LeroyDyer/Mixtral_AI_CyberTron_Ultra)
|
| 63 |
+
|
| 64 |
+
## Model Summary
|
| 65 |
+
|
| 66 |
+
What does he NOT KNOW ! that is the question!
|
| 67 |
+
|
| 68 |
+
### MOTTO FOR MODEL!
|
| 69 |
+
|
| 70 |
+
## Models are the same as loras , take them with light weight they are like tablets of knowledge!
|
| 71 |
+
Exactly ! ( models / loras ? is there a difference ? only mega merges make a true difference !
|
| 72 |
+
the small merges are just applying an adapter lol - Its in there somewhere?)
|
| 73 |
+
|
| 74 |
+
### Ok Its a Great MODEL ! (My Favorite Goto Brain now ! - will be fine tuned even more ! (if i get cloud credits))
|
| 75 |
|
|
|