Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-BF16-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-BF16-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-F32-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-F32-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-F32-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-27b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,93 @@
+---
+license: gemma
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- conversational
+- gguf
+- llamacpp
+---
+
+
+
+# Gemma 2 27b Instruction Tuned - GGUF
+
+These are GGUF quants of [google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it)
+
+Details about the model can be found at the above model page.
+
+## Llamacpp Version
+
+These quants were made with llamacpp tag b3408.
+
+If you have problems loading these models, please update your software to se the latest llamacpp version.
+
+
+## Perplexity Scoring
+
+Below are the perplexity scores for the GGUF models. A lower score is better. 
+
+| Quant Level | Perplexity Score | Standard Deviation |
+|-------------|------------------|--------------------|
+| F32 | 7.1853 | 0.04922 |
+| BF16 | 7.1853 | 0.04922 |
+| Q8_0 | 7.1879 | 0.04924 |
+| Q6_K | 7.2182 | 0.04948 |
+| Q5_K_M | 7.2333 | 0.04953 |
+| Q5_K_S | 7.2204 | 0.04931 |
+| Q4_K_M | 7.4192 | 0.05149 |
+| Q4_K_S | 7.5403 | 0.05231 |
+| Q3_K_L | 7.4623 | 0.05128 |
+| Q3_K_M | 7.7375 | 0.05362 |
+| Q3_K_S | 8.0426 | 0.05546 |
+
+
+## Quant Details
+
+This is the script used for quantization.
+
+```bash
+#!/bin/bash
+
+# Define MODEL_NAME above the loop
+MODEL_NAME="gemma-2-27b-it"
+
+# Define the output directory
+outputDir="${MODEL_NAME}-GGUF"
+
+# Create the output directory if it doesn't exist
+mkdir -p "${outputDir}"
+
+# Make the F32 quant
+f32file="${outputDir}/${MODEL_NAME}-F32.gguf"
+if [ -f "${f32file}" ]; then
+    echo "Skipping f32 as ${f32file} already exists."
+else
+    python convert_hf_to_gguf.py "~/src/models/${MODEL_NAME}" --outfile "${f32file}" --outtype "f32"
+fi
+
+# Abort out if the F32 didn't work
+if [ ! -f "${f32file}" ]; then
+   echo "No ${f32file} found."
+   exit 1
+fi
+
+# Define the array of quantization strings
+quants=("Q8_0" "Q6_K" "Q5_K_M" "Q5_K_S" "Q4_K_M" "Q4_K_S" "Q3_K_L" "Q3_K_M" "Q3_K_S")
+
+
+# Loop through the quants array
+for quant in "${quants[@]}"; do
+    outfile="${outputDir}/${MODEL_NAME}-${quant}.gguf"
+    
+    # Check if the outfile already exists
+    if [ -f "${outfile}" ]; then
+        echo "Skipping ${quant} as ${outfile} already exists."
+    else
+        # Run the command with the current quant string
+        ./llama-quantize "${f32file}" "${outfile}" "${quant}"
+        
+        echo "Processed ${quant} and generated ${outfile}"
+    fi
+done
+```

gemma-2-27b-it-BF16-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c661a821eeae60935de25496a866d5a3828b83e0d30b37e48c35042f343913e0
+size 29885957344

gemma-2-27b-it-BF16-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377ca838eea7965ff525b16f7bbdbe54ded8c4bcfdbc8cbe81e99f4a2651767d
+size 24576063776

gemma-2-27b-it-F32-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a695b7d965d5d6474fdadc54b4a9436b0554f18e292e1320f71ab522cb9d70
+size 39605587584

gemma-2-27b-it-F32-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1299b5d2d728b578c7d9e309ff87d13b4701dd01a7b268c4d2393e128e881a
+size 39864004064

gemma-2-27b-it-F32-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c97c2904b8af2f09fa1d83304f6b6d3640f3b00474685e994b49fed6c31e8f
+size 29444981280

gemma-2-27b-it-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f733ba602927488de0ed6cf4f2fe6b9de2827034840c79a8cf5cc37586de3da
+size 14519360800

gemma-2-27b-it-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c15ce2450a199e61156be5b8a138975cd52df9f21f3ffc447756e2464675cc
+size 13424647456

gemma-2-27b-it-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679b79cae38d33fdc310524994f63b13ec1daef1c3cc749858f42da0fa3ae404
+size 12169059616

gemma-2-27b-it-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecac990a76e7ae24360ebd42879a9b0850b683ada4e2caa676c68e790f14fc0e
+size 16645381408

gemma-2-27b-it-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d976b24ee5d73b6906463da84da1f7463fc808c75a8926088c0e3b98131815
+size 15739264288

gemma-2-27b-it-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72c7113e5a2064b24c0bb59c2d9a47cc8bb731259bb617df24f17b270f97826
+size 19408117024

gemma-2-27b-it-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1a4ee1d3b06f027baa653fdb23bdfc0dd73f6e94ef5011513ea128f5e31ee9
+size 18884205856

gemma-2-27b-it-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08e22a5be47dff774a42ecdda11e5de5bf1dcb088a621506093290a58c2c91d
+size 22343523616

gemma-2-27b-it-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219fdccce6f40298436319b581c2bbd47df0f9f5df8d8cbc73641ed12ff4daf1
+size 28937387296