Hugging Face's logo

TheBloke
/
Pygmalion-2-13B-GGUF

Text Generation
Transformers
GGUF
English
llama
text generation
instruct
text-generation-inference
Model card Files Community
1
TheBloke commited on
Commit
c2b0623
•
1 Parent(s): c37ec64

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -12
README.md CHANGED
@@ -1,6 +1,10 @@
1
  ---
2
  datasets:
3
  - PygmalionAI/PIPPA
 
 
 
 
4
  inference: false
5
  language:
6
  - en
@@ -114,18 +118,18 @@ Refer to the Provided Files table below to see what files use which methods, and
114
 
115
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
116
  | ---- | ---- | ---- | ---- | ---- | ----- |
117
- | pygmalion-2-13b.Q2_K.gguf | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
118
- | pygmalion-2-13b.Q3_K_S.gguf | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
119
- | pygmalion-2-13b.Q3_K_M.gguf | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
120
- | pygmalion-2-13b.Q3_K_L.gguf | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
121
- | pygmalion-2-13b.Q4_0.gguf | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
122
- | pygmalion-2-13b.Q4_K_S.gguf | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
123
- | pygmalion-2-13b.Q4_K_M.gguf | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
124
- | pygmalion-2-13b.Q5_0.gguf | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
125
- | pygmalion-2-13b.Q5_K_S.gguf | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
126
- | pygmalion-2-13b.Q5_K_M.gguf | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
127
- | pygmalion-2-13b.Q6_K.gguf | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
128
- | pygmalion-2-13b.Q8_0.gguf | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
129
 
130
  **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.
131
 
 
1
  ---
2
  datasets:
3
  - PygmalionAI/PIPPA
4
+ - Open-Orca/OpenOrca
5
+ - Norquinal/claude_multiround_chat_30k
6
+ - jondurbin/airoboros-gpt4-1.4.1
7
+ - databricks/databricks-dolly-15k
8
  inference: false
9
  language:
10
  - en
 
118
 
119
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
120
  | ---- | ---- | ---- | ---- | ---- | ----- |
121
+ | [pygmalion-2-13b.Q2_K.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
122
+ | [pygmalion-2-13b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
123
+ | [pygmalion-2-13b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
124
+ | [pygmalion-2-13b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
125
+ | [pygmalion-2-13b.Q4_0.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
126
+ | [pygmalion-2-13b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
127
+ | [pygmalion-2-13b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
128
+ | [pygmalion-2-13b.Q5_0.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
129
+ | [pygmalion-2-13b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
130
+ | [pygmalion-2-13b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
131
+ | [pygmalion-2-13b.Q6_K.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
132
+ | [pygmalion-2-13b.Q8_0.gguf](https://huggingface.co/TheBloke/Pygmalion-2-13B-GGUF/blob/main/pygmalion-2-13b.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
133
 
134
  **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.
135