TheBloke commited on
Commit
b866c46
1 Parent(s): 2ca75d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -10,6 +10,21 @@ It was created by merging the deltas provided in the above repo with the origina
10
 
11
  It was then quantized to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ## Provided files
14
 
15
  Two model files are provided. Ideally use the `safetensors` file. Full details below:
 
10
 
11
  It was then quantized to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
12
 
13
+ ## My Vicuna 1.1 model repositories
14
+
15
+ I have the following Vicuna 1.1 repositories available:
16
+
17
+ **13B models:**
18
+ * [Unquantized 13B 1.1 model for GPU - HF format](https://huggingface.co/TheBloke/vicuna-13B-1.1-HF)
19
+ * [GPTQ quantized 4bit 13B 1.1 for GPU - `safetensors` and `pt` formats](https://huggingface.co/TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g)
20
+ * [GPTQ quantized 4bit 13B 1.1 for CPU - GGML format for `llama.cpp`](https://huggingface.co/TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g-GGML)
21
+
22
+ **7B models:**
23
+ * [Unquantized 7B 1.1 model for GPU - HF format](https://huggingface.co/TheBloke/vicuna-7B-1.1-HF)
24
+ * [GPTQ quantized 4bit 7B 1.1 for GPU - `safetensors` and `pt` formats](https://huggingface.co/TheBloke/vicuna-7B-1.1-GPTQ-4bit-128g)
25
+ * [GPTQ quantized 4bit 7B 1.1 for CPU - GGML format for `llama.cpp`](https://huggingface.co/TheBloke/vicuna-7B-1.1-GPTQ-4bit-128g-GGML)
26
+
27
+
28
  ## Provided files
29
 
30
  Two model files are provided. Ideally use the `safetensors` file. Full details below: