Commit
•
13fd76c
1
Parent(s):
bb4ec00
Update README.md
Browse files
README.md
CHANGED
|
@@ -61,6 +61,21 @@ Through systematic experiments to determine the weights of different languages,
|
|
| 61 |
The approach boosts their performance on SEA languages while maintaining proficiency in English and Chinese without significant compromise.
|
| 62 |
Finally, we continually pre-train the Qwen1.5-0.5B model with 400 Billion tokens, and other models with 200 Billion tokens to obtain the Sailor models.
|
| 63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
### How to run with `llama.cpp`
|
| 65 |
|
| 66 |
```shell
|
|
|
|
| 61 |
The approach boosts their performance on SEA languages while maintaining proficiency in English and Chinese without significant compromise.
|
| 62 |
Finally, we continually pre-train the Qwen1.5-0.5B model with 400 Billion tokens, and other models with 200 Billion tokens to obtain the Sailor models.
|
| 63 |
|
| 64 |
+
### GGUF model list
|
| 65 |
+
| Name | Quant method | Bits | Size | Use case |
|
| 66 |
+
| ------------------------------------------------------------ | ------------ | ---- | -------- | -------------------------------------- |
|
| 67 |
+
| [ggml-model-Q2_K.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q2_K.gguf) | Q2_K | 2 | 3.10 GB | medium, significant quality loss |
|
| 68 |
+
| [ggml-model-Q3_K_L.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q3_K_L.gguf) | Q3_K_L | 3 | 4.22 GB | large, substantial quality loss |
|
| 69 |
+
| [ggml-model-Q3_K_M.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q3_K_M.gguf) | Q3_K_M | 3 | 3.92 GB | medium, balanced quality |
|
| 70 |
+
| [ggml-model-Q3_K_S.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q3_K_S.gguf) | Q3_K_S | 3 | 3.57 GB | medium, high quality loss |
|
| 71 |
+
| [ggml-model-Q4_K_M.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q4_K_M.gguf) | Q4_K_M | 4 | 4.77 GB | large, balanced quality |
|
| 72 |
+
| [ggml-model-Q4_K_S.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q4_K_S.gguf) | Q4_K_S | 4 | 4.54 GB | large, greater quality loss |
|
| 73 |
+
| [ggml-model-Q5_K_M.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q5_K_M.gguf) | Q5_K_M | 5 | 5.53 GB | large, balanced quality |
|
| 74 |
+
| [ggml-model-Q5_K_S.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q5_K_S.gguf) | Q5_K_S | 5 | 5.4 GB | large, very low quality loss |
|
| 75 |
+
| [ggml-model-Q6_K.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q6_K.gguf) | Q6_K | 6 | 6.34 GB | large, extremely low quality loss |
|
| 76 |
+
| [ggml-model-Q8_0.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-Q8_0.gguf) | Q8_0 | 8 | 8.21 GB | very large, extremely low quality loss |
|
| 77 |
+
| [ggml-model-f16.gguf](https://huggingface.co/sail/Sailor-7B-Chat-gguf/blob/main/ggml-model-f16.gguf) | f16 | 16 | 15.40 GB | very large, no quality loss |
|
| 78 |
+
|
| 79 |
### How to run with `llama.cpp`
|
| 80 |
|
| 81 |
```shell
|