Update README.md
Browse files
README.md
CHANGED
@@ -44,11 +44,11 @@ No GQA - VRAM requirements will be higher
|
|
44 |
|
45 |
| Branch | Bits | lm_head bits | Size (4k) | Size (16k) | Description |
|
46 |
| -------------------------------------------------------------- | ---- | ------------ | --------- | ---------- | ----------- |
|
47 |
-
| [8_0](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/8_0) | 8.0 | 8.0 | 9.
|
48 |
-
| [6_5](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/6_5) | 6.5 | 8.0 | 8.
|
49 |
-
| [5_0](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/5_0) | 5.0 | 6.0 |
|
50 |
-
| [4_25](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/4_25) | 4.25 | 6.0 | 6.
|
51 |
-
| [3_5](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/3_5) | 3.5 | 6.0 | 5.
|
52 |
|
53 |
## Download instructions
|
54 |
|
|
|
44 |
|
45 |
| Branch | Bits | lm_head bits | Size (4k) | Size (16k) | Description |
|
46 |
| -------------------------------------------------------------- | ---- | ------------ | --------- | ---------- | ----------- |
|
47 |
+
| [8_0](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/8_0) | 8.0 | 8.0 | 9.0 GB | 15.2 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
|
48 |
+
| [6_5](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/6_5) | 6.5 | 8.0 | 8.2 GB | 14.4 GB | Near unquantized performance at vastly reduced size, **recommended**. |
|
49 |
+
| [5_0](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/5_0) | 5.0 | 6.0 | 6.8 GB | 13.0 GB | Slightly lower quality vs 6.5, but usable on 8GB cards with 4k context. |
|
50 |
+
| [4_25](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/4_25) | 4.25 | 6.0 | 6.1 GB | 12.3 GB | GPTQ equivalent bits per weight. |
|
51 |
+
| [3_5](https://huggingface.co/bartowski/wavecoder-ultra-1.1-6.7b-exl2/tree/3_5) | 3.5 | 6.0 | 5.5 GB | 11.7 GB | Lower quality, not recommended. |
|
52 |
|
53 |
## Download instructions
|
54 |
|