Update README.md

Added IQ1_S, IQ2_XXS, IQ2_XS, IQ3_XXS, and IQ4_XS imatrix GGUF quants (20k_random_data/100 chunks)

README.md

@@ -18,9 +18,9 @@ tags:
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6303ca537373aacccd85d8a7/vmCAhJCpF0dITtCVxlYET.jpeg)
 
 - HF: [wolfram/miquliz-120b-v2.0](https://huggingface.co/wolfram/miquliz-120b-v2.0)
-- GGUF: Q2_K | IQ3_XXS | Q4_K_M | Q5_K_M
-  - [dranger003's IQ2_XS | IQ2_XXS | IQ3_XXS | Q8_0](https://huggingface.co/dranger003/miquliz-120b-v2.0-iMat.GGUF)
-  - [KnutJaegersberg's IQ2_XS](https://huggingface.co/KnutJaegersberg/2-bit-LLMs)
+- GGUF: IQ1_S* | IQ2_XXS* | IQ2_XS* | Q2_K | IQ3_XXS* | IQ3_XXS.old | IQ4_XS* | Q4_K_M | Q5_K_M (*: imatrix=20k_random_data/100 chunks)
+  - [dranger003's IQ2_XS | IQ2_XXS | IQ3_XXS | Q8_0](https://huggingface.co/dranger003/miquliz-120b-v2.0-iMat.GGUF) (imatrix=100K wiki.train.raw/200 chunks)
+  - [KnutJaegersberg's IQ2_XS](https://huggingface.co/KnutJaegersberg/2-bit-LLMs) (imatrix=20k_random_data/100 chunks)
   - [mradermacher's i1-IQ1_S – i1-Q5_K_M](https://huggingface.co/mradermacher/miquliz-120b-v2.0-i1-GGUF)
   - [mradermacher's Q2_K – Q8_0](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF)
 - EXL2: [2.4bpw](https://huggingface.co/wolfram/miquliz-120b-v2.0-2.4bpw-h6-exl2) | [2.65bpw](https://huggingface.co/wolfram/miquliz-120b-v2.0-2.65bpw-h6-exl2) | [3.0bpw](https://huggingface.co/wolfram/miquliz-120b-v2.0-3.0bpw-h6-exl2) | [3.5bpw](https://huggingface.co/wolfram/miquliz-120b-v2.0-3.5bpw-h6-exl2) | [4.0bpw](https://huggingface.co/wolfram/miquliz-120b-v2.0-4.0bpw-h6-exl2) | [5.0bpw](https://huggingface.co/wolfram/miquliz-120b-v2.0-5.0bpw-h6-exl2)
@@ -35,11 +35,18 @@ Thanks for the additional quants, [DAN™](https://huggingface.co/dranger003), [
 
 Also available: [miqu-1-120b](https://huggingface.co/wolfram/miqu-1-120b) – Miquliz's older, purer sister; only Miqu, inflated to 120B.
 
-### ❗ Q4_K_M and Q5_K_M files are split and require joining
+### ❗ IQ4_XS, Q4_K_M, and Q5_K_M files are split and require joining
 
-**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q4_K_M and Q5_K_M files as split files.
+**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the IQ4_XS, Q4_K_M, and Q5_K_M files as split files.
 
-<details><summary>Click for instructions regarding Q4_K_M and Q5_K_M files</summary>
+<details><summary>Click for instructions regarding IQ4_XS, Q4_K_M, and Q5_K_M files</summary>
+
+#### IQ4_XS
+
+Please download:
+
+- `miquliz-120b-v2.0.IQ4_XS.gguf-split-a`
+- `miquliz-120b-v2.0.IQ4_XS.gguf-split-b`
 
 #### Q4_K_M
 
@@ -60,6 +67,8 @@ To join the files, do the following:
 Linux and macOS:
 
 ```sh
+cat miquliz-120b-v2.0.IQ4_XS.gguf-split-* > miquliz-120b-v2.0.IQ4_XS.gguf && rm miquliz-120b-v2.0.IQ4_XS.gguf-split-*
+
 cat miquliz-120b-v2.0.Q4_K_M.gguf-split-* > miquliz-120b-v2.0.Q4_K_M.gguf && rm miquliz-120b-v2.0.Q4_K_M.gguf-split-*
 
 cat miquliz-120b-v2.0.Q5_K_M.gguf-split-* > miquliz-120b-v2.0.Q5_K_M.gguf && rm miquliz-120b-v2.0.Q5_K_M.gguf-split-*
@@ -68,6 +77,9 @@ cat miquliz-120b-v2.0.Q5_K_M.gguf-split-* > miquliz-120b-v2.0.Q5_K_M.gguf && rm
 Windows command line:
 
 ```cmd
+COPY /B miquliz-120b-v2.0.IQ4_XS.gguf-split-a + miquliz-120b-v2.0.IQ4_XS.gguf-split-b miquliz-120b-v2.0.IQ4_XS.gguf
+DEL miquliz-120b-v2.0.IQ4_XS.gguf-split-a miquliz-120b-v2.0.IQ4_XS.gguf-split-b
+
 COPY /B miquliz-120b-v2.0.Q4_K_M.gguf-split-a + miquliz-120b-v2.0.Q4_K_M.gguf-split-b miquliz-120b-v2.0.Q4_K_M.gguf
 DEL miquliz-120b-v2.0.Q4_K_M.gguf-split-a miquliz-120b-v2.0.Q4_K_M.gguf-split-b