TheMelonGod commited on
Commit
af0f271
·
verified ·
1 Parent(s): 84bb1d4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -3
README.md CHANGED
@@ -1,3 +1,45 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ quantized_by: TheMelonGod
6
+ pipeline_tag: text-generation
7
+ tags:
8
+ - quantized
9
+ - safetensors
10
+ - exllamav3
11
+ - qwen3
12
+ - conversational
13
+ base_model:
14
+ - Qwen/Qwen3-14B
15
+ base_model_relation: quantized
16
+ ---
17
+ **Orignal Model by:** [Qwen](https://huggingface.co/Qwen)
18
+ **Orignal Model:** [Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B)
19
+
20
+ For more information about the model, I highly recommend checking out the original model page and the creator while you're at it.
21
+
22
+ **ExLlamaV3 v0.0.6 Quantizations:**
23
+ **8.0bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-8.0bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-8.0bpw)
24
+ **7.5bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-7.5bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-7.5bpw)
25
+ **7.0bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-7.0bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-7.0bpw)
26
+ **6.5bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-6.5bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-6.5bpw)
27
+ **6.0bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-6.0bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-6.0bpw)
28
+ **5.5bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-5.5bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-5.5bpw)
29
+ **5.0bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-5.0bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-5.0bpw)
30
+ **4.5bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-4.5bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-4.5bpw)
31
+ **4.25bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-4.25bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-4.25bpw)
32
+ **4.0bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-4.0bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-4.0bpw)
33
+ **3.75bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-3.75bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-3.75bpw)
34
+ **3.5bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-3.5bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-3.5bpw)
35
+ **3.0bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-3.0bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-3.0bpw)
36
+ **2.75bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-2.75bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-2.75bpw)
37
+ **2.5bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-2.5bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-2.5bpw)
38
+ **2.25bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-2.25bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-2.25bpw)
39
+ **2.0bpw**: [8hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/8hb-2.0bpw) | [6hb](https://huggingface.co/TheMelonGod/Qwen3-14B-exl3/tree/6hb-2.0bpw)
40
+
41
+ If you need a specific model quantized or particular bits per weight, please let me know. I’m happy to help.
42
+
43
+ This is my first Exllamav3 Quantization! Your feedback and suggestions are always welcome! They help me improve and make quantizations better for everyone.
44
+
45
+ Special thanks to [turboderp](https://huggingface.co/turboderp) for developing the tools that made these quantizations possible. Your contributions are greatly appreciated!