Update readme with new model + update util scripts

scripts/convert_and_quantize.sh

@@ -9,15 +9,22 @@ if [[ ! -d "./models/$MODEL_NAME" ]]; then
     exit -1
 fi
 
+if [ -f "./models/$MODEL_NAME/gguf_overrides.json" ]; then
+    OVERRIDES="--metadata ./models/$MODEL_NAME/gguf_overrides.json"
+    echo "Using metadata from ./models/$MODEL_NAME/gguf_overrides.json"
+else
+    OVERRIDES=""
+fi
+
 echo "Converting to GGUF..."
 if [ ! -f "./models/$MODEL_NAME/$MODEL_NAME.f16.gguf" ]; then
-    $LLAMA_CPP/convert_hf_to_gguf.py --outfile ./models/$MODEL_NAME/$MODEL_NAME.f16.gguf --outtype f16 ./models/$MODEL_NAME/
+    $LLAMA_CPP/convert_hf_to_gguf.py --outfile ./models/$MODEL_NAME/$MODEL_NAME.f16.gguf --outtype f16 ./models/$MODEL_NAME/ $OVERRIDES
 else
     echo "Converted model for already exists. Skipping..."
 fi
 
 
-DESIRED_QUANTS=("Q8_0" "Q5_K_M" "Q4_K_M" "Q3_K_M" "Q2_K")
+DESIRED_QUANTS=("Q8_0" "Q5_K_M" "Q4_0" "Q4_1" "Q4_K_M")
 for QUANT in "${DESIRED_QUANTS[@]}"
 do
     QUANT_LOWER=$(echo "$QUANT" | awk '{print tolower($0)}')

scripts/upload_to_hf.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+set -e
+
+MODEL_NAME=$1
+
+huggingface-cli upload $MODEL_NAME models/$MODEL_NAME \
+    --repo-type model --commit-message "Upload model" \
+    --exclude "runs/" "training_args.bin" "gguf_overrides.json"