Commit
•
8f73fe1
1
Parent(s):
add6174
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,22 +39,4 @@ chat_ctx_size: `16384`
|
|
| 39 |
|
| 40 |
- Customize your node: https://docs.gaianet.ai/node-guide/customize
|
| 41 |
|
| 42 |
-
## Quantized GGUF Models
|
| 43 |
-
|
| 44 |
-
| Name | Quant method | Bits | Size | Use case |
|
| 45 |
-
| ---- | ---- | ---- | ---- | ----- |
|
| 46 |
-
| [Yi-1.5-9B-Chat-16K-Q2_K.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q2_K.gguf) | Q2_K | 2 |3.35 GB| smallest, significant quality loss - not recommended for most purposes |
|
| 47 |
-
| [Yi-1.5-9B-Chat-16K-Q3_K_L.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q3_K_L.gguf) | Q3_K_L | 3 | 3.24 GB| small, substantial quality loss |
|
| 48 |
-
| [Yi-1.5-9B-Chat-16K-Q3_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q3_K_M.gguf) | Q3_K_M | 3 | 2.99 GB| very small, high quality loss |
|
| 49 |
-
| [Yi-1.5-9B-Chat-16K-Q3_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q3_K_S.gguf) | Q3_K_S | 3 | 2.71 GB| very small, high quality loss |
|
| 50 |
-
| [Yi-1.5-9B-Chat-16K-Q4_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q4_0.gguf) | Q4_0 | 4 | 3.48 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 51 |
-
| [Yi-1.5-9B-Chat-16K-Q4_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q4_K_M.gguf) | Q4_K_M | 4 | 3.67 GB| medium, balanced quality - recommended |
|
| 52 |
-
| [Yi-1.5-9B-Chat-16K-Q4_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q4_K_S.gguf) | Q4_K_S | 4 | 3.50 GB| small, greater quality loss |
|
| 53 |
-
| [Yi-1.5-9B-Chat-16K-Q5_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q5_0.gguf) | Q5_0 | 5 | 4.20 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 54 |
-
| [Yi-1.5-9B-Chat-16K-Q5_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q5_K_M.gguf) | Q5_K_M | 5 | 4.30 GB| large, very low quality loss - recommended |
|
| 55 |
-
| [Yi-1.5-9B-Chat-16K-Q5_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q5_K_S.gguf) | Q5_K_S | 5 | 4.20 GB| large, low quality loss - recommended |
|
| 56 |
-
| [Yi-1.5-9B-Chat-16K-Q6_K.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q6_K.gguf) | Q6_K | 6 | 4.97 GB| very large, extremely low quality loss |
|
| 57 |
-
| [Yi-1.5-9B-Chat-16K-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q8_0.gguf) | Q8_0 | 8 | 6.44 GB| very large, extremely low quality loss - not recommended |
|
| 58 |
-
| [Yi-1.5-9B-Chat-16K-f16.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-f16.gguf) | f16 | 16 | 17.7 GB| |
|
| 59 |
-
|
| 60 |
*Quantized with llama.cpp b3135*
|
|
|
|
| 39 |
|
| 40 |
- Customize your node: https://docs.gaianet.ai/node-guide/customize
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
*Quantized with llama.cpp b3135*
|