TheBloke commited on
Commit
73d6e2b
1 Parent(s): 1b3937c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -12,6 +12,11 @@ This is GGML format quantised 4bit and 5bit models of [junlee's wizard-vicuna 13
12
 
13
  It is the result of quantising to 4bit and 5bit GGML for CPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp).
14
 
 
 
 
 
 
15
  ## Provided files
16
  | Name | Quant method | Bits | Size | RAM required | Use case |
17
  | ---- | ---- | ---- | ---- | ---- | ----- |
 
12
 
13
  It is the result of quantising to 4bit and 5bit GGML for CPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp).
14
 
15
+ ## Repositories available
16
+
17
+ * [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-GPTQ).
18
+ * [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-GGML).
19
+
20
  ## Provided files
21
  | Name | Quant method | Bits | Size | RAM required | Use case |
22
  | ---- | ---- | ---- | ---- | ---- | ----- |