Hugging Face's logo

Zoyd
/
Delcos_Velara-11B-v3-4_0bpw_exl2

Text Generation
Transformers
Safetensors
English
llama
starling
mistral
llama-2
conversational
Inference Endpoints
text-generation-inference
4-bit precision
exl2
Model card Files Community
Zoyd commited on
Commit
4b0335a
•
1 Parent(s): 4834ba7

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +17 -0
README.md CHANGED
@@ -9,6 +9,23 @@ tags:
9
  - mistral
10
  - llama-2
11
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
 
13
  <h1 style="font-size: 36px;">Velara-11b-v3</h1>
14
 
 
9
  - mistral
10
  - llama-2
11
  ---
12
+ **Exllamav2** quant (**exl2** / **4.0 bpw**) made with ExLlamaV2 v0.0.21
13
+
14
+ Other EXL2 quants:
15
+ | **Quant** | **Model Size** | **lm_head** |
16
+ | ----- | ---------- | ------- |
17
+ |<center>**[2.2](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-2_2bpw_exl2)**</center> | <center>4176 MB</center> | <center>6</center> |
18
+ |<center>**[2.5](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-2_5bpw_exl2)**</center> | <center>4518 MB</center> | <center>6</center> |
19
+ |<center>**[3.0](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-3_0bpw_exl2)**</center> | <center>5143 MB</center> | <center>6</center> |
20
+ |<center>**[3.5](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-3_5bpw_exl2)**</center> | <center>5767 MB</center> | <center>6</center> |
21
+ |<center>**[3.75](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-3_75bpw_exl2)**</center> | <center>6077 MB</center> | <center>6</center> |
22
+ |<center>**[4.0](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-4_0bpw_exl2)**</center> | <center>6390 MB</center> | <center>6</center> |
23
+ |<center>**[4.25](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-4_25bpw_exl2)**</center> | <center>6703 MB</center> | <center>6</center> |
24
+ |<center>**[5.0](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-5_0bpw_exl2)**</center> | <center>7639 MB</center> | <center>6</center> |
25
+ |<center>**[6.0](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-6_0bpw_exl2)**</center> | <center>8988 MB</center> | <center>8</center> |
26
+ |<center>**[6.5](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-6_5bpw_exl2)**</center> | <center>9607 MB</center> | <center>8</center> |
27
+ |<center>**[8.0](https://huggingface.co/Zoyd/Delcos_Velara-11B-v3-8_0bpw_exl2)**</center> | <center>11359 MB</center> | <center>8</center> |
28
+
29
 
30
  <h1 style="font-size: 36px;">Velara-11b-v3</h1>
31