Xin Liu
commited on
Commit
•
dd8c1df
1
Parent(s):
470631e
Add `README`
Browse filesSigned-off-by: Xin Liu <[email protected]>
README.md
CHANGED
|
@@ -54,3 +54,19 @@ tags:
|
|
| 54 |
```bash
|
| 55 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-34B-Chat-ggml-model-q4_0.gguf llama-chat.wasm -p chatml -r '<|im_end|>'
|
| 56 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
```bash
|
| 55 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-34B-Chat-ggml-model-q4_0.gguf llama-chat.wasm -p chatml -r '<|im_end|>'
|
| 56 |
```
|
| 57 |
+
|
| 58 |
+
## Quantized GGUF Models
|
| 59 |
+
|
| 60 |
+
| Name | Quant method | Bits | Size | Use case |
|
| 61 |
+
| ---- | ---- | ---- | ---- | ----- |
|
| 62 |
+
| [Yi-34Bx2-MoE-60B-Q2_K.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q2_K.gguf) | Q2_K | 2 | 22.4 GB| smallest, significant quality loss - not recommended for most purposes |
|
| 63 |
+
| [Yi-34Bx2-MoE-60B-Q3_K_L.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q3_K_L.gguf) | Q3_K_L | 3 | 31.8 GB| small, substantial quality loss |
|
| 64 |
+
| [Yi-34Bx2-MoE-60B-Q3_K_M.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q3_K_M.gguf) | Q3_K_M | 3 | 29.2 GB| very small, high quality loss |
|
| 65 |
+
| [Yi-34Bx2-MoE-60B-Q3_K_S.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q3_K_S.gguf) | Q3_K_S | 3 | 26.3 GB| very small, high quality loss |
|
| 66 |
+
| [Yi-34Bx2-MoE-60B-Q4_0.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q4_0.gguf) | Q4_0 | 4 | 34.3 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 67 |
+
| [Yi-34Bx2-MoE-60B-Q4_K_M.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q4_K_M.gguf) | Q4_K_M | 4 | 36.7 GB| medium, balanced quality - recommended |
|
| 68 |
+
| [Yi-34Bx2-MoE-60B-Q4_K_S.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q4_K_S.gguf) | Q4_K_S | 4 | 34.6 GB| small, greater quality loss |
|
| 69 |
+
| [Yi-34Bx2-MoE-60B-Q5_0.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q5_0.gguf) | Q5_0 | 5 | 41.9 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 70 |
+
| [Yi-34Bx2-MoE-60B-Q5_K_M.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q5_K_M.gguf) | Q5_K_M | 5 | 43.1 GB| large, very low quality loss - recommended |
|
| 71 |
+
| [Yi-34Bx2-MoE-60B-Q5_K_S.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q5_K_S.gguf) | Q5_K_S | 5 | 41.9 GB| large, low quality loss - recommended |
|
| 72 |
+
| [Yi-34Bx2-MoE-60B-Q6_K.gguf](https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF/blob/main/Yi-34Bx2-MoE-60B-Q6_K.gguf) | Q6_K | 6 | 49.9 GB| very large, extremely low quality loss |
|