Commit
•
a512bb5
1
Parent(s):
e546c8b
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,13 +25,18 @@ tags:
|
|
| 25 |
---
|
| 26 |
|
| 27 |
<p><h1> speechless-llama2-hermes-orca-platypus-wizardlm-13b </h1></p>
|
| 28 |
-
Needs an acronym... maybe
|
| 29 |
<p><h2> ExLlamaV2 Quantization </h2></p>
|
| 30 |
|
| 31 |
[5.00 bits per weight in main](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/main)
|
| 32 |
|
|
|
|
|
|
|
| 33 |
[4.00 bits per weight branch](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/4bpw)
|
| 34 |
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
[8.00 bits per weight branch](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/8bpw)
|
| 37 |
|
|
|
|
| 25 |
---
|
| 26 |
|
| 27 |
<p><h1> speechless-llama2-hermes-orca-platypus-wizardlm-13b </h1></p>
|
| 28 |
+
Needs an acronym... maybe PHLOWS or WOLPHS?
|
| 29 |
<p><h2> ExLlamaV2 Quantization </h2></p>
|
| 30 |
|
| 31 |
[5.00 bits per weight in main](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/main)
|
| 32 |
|
| 33 |
+
[3.00 bits per weight branch](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/3bpw)
|
| 34 |
+
|
| 35 |
[4.00 bits per weight branch](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/4bpw)
|
| 36 |
|
| 37 |
+
[4.65 bits per weight branch](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/4.65bpw)
|
| 38 |
+
|
| 39 |
+
[6.00 bits per weight branch](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/6bpw)
|
| 40 |
|
| 41 |
[8.00 bits per weight branch](https://huggingface.co/UnstableLlama/speechless-llama2-hermes-orca-platypus-wizardlm-13b-exl2/tree/8bpw)
|
| 42 |
|