GGUF
English
Indonesian
asyafiqe commited on
Commit
0628ee2
1 Parent(s): b51e4e1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -9
README.md CHANGED
@@ -62,7 +62,7 @@ The new methods available are:
62
  ## Provided files
63
 
64
  | Name | Quant method | Bits | Use case |
65
- | ---- | ---- | ---- | ---- | ---- | ----- |
66
  | Merak-7B-v3-Mini-Orca-Indo.gguf | Q2_K | 2 | smallest, significant quality loss - not recommended for most purposes |
67
  | Merak-7B-v3-Mini-Orca-Indo.q3_K_S.gguf | Q3_K_S | 3 | very small, high quality loss |
68
  | Merak-7B-v3-Mini-Orca-Indo.q3_K_M.gguf | Q3_K_M | 3 | very small, high quality loss |
@@ -78,23 +78,17 @@ The new methods available are:
78
 
79
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
80
 
81
- readme adapted from [TheBloke](https://huggingface.co/TheBloke)
82
-
83
  ## How to run in `text-generation-webui`
84
 
85
  Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
86
 
 
87
  # Original model card: 🦚Merak-7B-v3-Mini-Orca🐳
88
 
89
  **Merak-7B-v3-Mini-Orca** is Ichsan2895's [Merak-7B-v3](https://huggingface.co/Ichsan2895/Merak-7B-v3) fine-tuned
90
  on Bahasa Indonesia translated psmathur's [orca_mini_v1_dataset](https://huggingface.co/datasets/psmathur/orca_mini_v1_dataset).
91
 
92
 
93
- ## Usage
94
- This model fit on 16GB VRAM GPU (Google Collab T4 wil do), by using BitsandBytes it can run on 6GB VRAM GPU.
95
-
96
- [![Open in Google Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/11xmPcRNirGwZcpgmNPNpUioJUG4PQBuh)
97
-
98
  **Quantized** versions is available:
99
 
100
  GPTQ: https://huggingface.co/asyafiqe/Merak-7B-v3-Mini-Orca-Indo-GPTQ
@@ -188,4 +182,7 @@ Please see the Responsible Use Guide available at https://ai.meta.com/llama/resp
188
  journal={CoRR},
189
  year={2021}
190
  }
191
- ```
 
 
 
 
62
  ## Provided files
63
 
64
  | Name | Quant method | Bits | Use case |
65
+ | ---- | ---- | ---- | ---- |
66
  | Merak-7B-v3-Mini-Orca-Indo.gguf | Q2_K | 2 | smallest, significant quality loss - not recommended for most purposes |
67
  | Merak-7B-v3-Mini-Orca-Indo.q3_K_S.gguf | Q3_K_S | 3 | very small, high quality loss |
68
  | Merak-7B-v3-Mini-Orca-Indo.q3_K_M.gguf | Q3_K_M | 3 | very small, high quality loss |
 
78
 
79
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
80
 
 
 
81
  ## How to run in `text-generation-webui`
82
 
83
  Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
84
 
85
+
86
  # Original model card: 🦚Merak-7B-v3-Mini-Orca🐳
87
 
88
  **Merak-7B-v3-Mini-Orca** is Ichsan2895's [Merak-7B-v3](https://huggingface.co/Ichsan2895/Merak-7B-v3) fine-tuned
89
  on Bahasa Indonesia translated psmathur's [orca_mini_v1_dataset](https://huggingface.co/datasets/psmathur/orca_mini_v1_dataset).
90
 
91
 
 
 
 
 
 
92
  **Quantized** versions is available:
93
 
94
  GPTQ: https://huggingface.co/asyafiqe/Merak-7B-v3-Mini-Orca-Indo-GPTQ
 
182
  journal={CoRR},
183
  year={2021}
184
  }
185
+ ```
186
+
187
+
188
+ readme adapted from [TheBloke](https://huggingface.co/TheBloke)