Update README.md
Browse files
README.md
CHANGED
@@ -80,11 +80,11 @@ Original model: https://huggingface.co/bigcode/starcoder2-7b
|
|
80 |
|
81 |
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|
82 |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
|
83 |
-
| [8_0](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.
|
84 |
-
| [6_5](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/6_5) | 6.5 | 8.0 | 7.
|
85 |
-
| [5_0](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/5_0) | 5.0 | 6.0 |
|
86 |
-
| [4_25](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/4_25) | 4.25 | 6.0 | 5.
|
87 |
-
| [3_5](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/3_5) | 3.5 | 6.0 | 4.
|
88 |
|
89 |
## Download instructions
|
90 |
|
|
|
80 |
|
81 |
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|
82 |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
|
83 |
+
| [8_0](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.2 GB | 10.2 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
|
84 |
+
| [6_5](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/6_5) | 6.5 | 8.0 | 7.1 GB | 7.9 GB | 8.9 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
|
85 |
+
| [5_0](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/5_0) | 5.0 | 6.0 | 5.8 GB | 6.6 GB | 7.6 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
|
86 |
+
| [4_25](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/4_25) | 4.25 | 6.0 | 5.1 GB | 5.9 GB | 6.9 GB | GPTQ equivalent bits per weight, slightly higher quality. |
|
87 |
+
| [3_5](https://huggingface.co/bartowski/starcoder2-7b-exl2/tree/3_5) | 3.5 | 6.0 | 4.5 GB | 5.3 GB | 6.3 GB | Lower quality, only use if you have to. |
|
88 |
|
89 |
## Download instructions
|
90 |
|