diff --git a/backends/c_transformers/models.yaml b/backends/c_transformers/models.yaml
index 68fd7335..462aafe3 100644
--- a/backends/c_transformers/models.yaml
+++ b/backends/c_transformers/models.yaml
@@ -22,10 +22,6 @@
   owner: TheBloke
   server: https://huggingface.co/TheBloke/koala-7b-ggml-unquantized/resolve/main/
   sha256: c478ceced3b38800cb768225b1e759a32c9e89bd33606fb38eeff3b811e28371
-
-
-
-  
 - MPT-7B: 'true'
   description: MPT-7B
   filename: mpt-7b.ggmlv3.q5_1.bin
@@ -43,7 +39,15 @@
   server: https://huggingface.co/TheBloke/MPT-7B-Instruct-GGML/resolve/main/
   sha256: a4d17a39ac277d48a3d55aa74b36a4e6e1b891b58937a838243fad549d26c686
 - MPT-7B-Storywriter: 'true'
-  description: MPT-7B-Storywriter
+  description: MPT-7B-Storywriter 4 Bits
+  filename: mpt-7b-storywriter.ggmlv3.q4_0.bin
+  license: Apache-2.0
+  owner_link: https://huggingface.co/TheBloke/
+  owner: TheBloke
+  server: https://huggingface.co/TheBloke/MPT-7B-Storywriter-GGML/resolve/main/
+  sha256: 357a536464982987e49fb2660fe3f3f53226eaa047f42b31f04d21629aab94fb
+- MPT-7B-Storywriter: 'true'
+  description: MPT-7B-Storywriter 5.1 Bits
   filename: mpt-7b-storywriter.ggmlv3.q5_1.bin
   license: Apache-2.0
   owner_link: https://huggingface.co/TheBloke/
diff --git a/backends/llama_cpp_official/models.yaml b/backends/llama_cpp_official/models.yaml
index 92e3404e..54edb544 100644
--- a/backends/llama_cpp_official/models.yaml
+++ b/backends/llama_cpp_official/models.yaml
@@ -16,7 +16,44 @@
   server: https://huggingface.co/TheBloke/Manticore-13B-GGML/resolve/main/
   sha256: 910f3e73dc5797753313a950989c54a30342780311d64c3d4b8a37b12dd50336
 
-  
+- bestLlama: 'true'
+  description: 'Project-Baize Quantized on 4 bits '
+  filename: baize-v2-13b.ggmlv3.q4_0.bin
+  license: Non commercial
+  owner_link: https://huggingface.co/TheBloke
+  owner: TheBloke
+  server: https://huggingface.co/TheBloke/Project-Baize-v2-13B-GGML/resolve/main/
+  sha256: 5994f92f3cc8d3fe2d09a44c174ed8c0f4f32819597feaafc9d6bd06208d3df6
+
+- bestLlama: 'true'
+  description: 'MedAlpaca 13B Quantized on 4 bits: model specifically fine-tuned for medical domain tasks'
+  filename: medalpaca-13B.ggmlv3.q4_0.bin
+  license: Non commercial
+  owner_link: https://huggingface.co/TheBloke
+  owner: TheBloke
+  server: https://huggingface.co/TheBloke/medalpaca-13B-GGML/resolve/main/
+  sha256: 24060342f7649f5609a90932b88604f90eb34ee490f7c22403ff47b9b8547c58
+
+- bestLlama: 'true'
+  description: 'MedAlpaca 13B Quantized on 5 bits: model specifically fine-tuned for medical domain tasks'
+  filename: medalpaca-13B.ggmlv3.q5_1.bin
+  license: Non commercial
+  owner_link: https://huggingface.co/TheBloke
+  owner: TheBloke
+  server: https://huggingface.co/TheBloke/medalpaca-13B-GGML/resolve/main/
+  sha256: eeae440fd56fe8cb05632f22d73725914c6ef803dbb468c3ab6d4d2a78ff9ad5
+
+
+- bestLlama: 'true'
+  description: 'Wizard-Vicuna-13B-Uncensored-GGML Quantized on 4 bits'
+  filename: Wizard-Vicuna-13B-Uncensored.ggmlv3.q4_0.bin
+  license: Non commercial
+  owner_link: https://huggingface.co/TheBloke
+  owner: TheBloke
+  server: https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-GGML/resolve/main/
+  sha256: 1f08b147a5bce41cfcbb3fd5d51ba765dea1786e15b5655ab69ba3a337a893b7
+
+
 - bestLlama: 'true'
   description: Legacy version of Vicuna 7B v 1.1 Quantized on 4 bits
   filename: legacy-ggml-vicuna-7B-1.1-q4_0.bin
@@ -25,6 +62,7 @@
   owner: CRD716
   server: https://huggingface.co/CRD716/ggml-vicuna-1.1-quantized/resolve/main/
   sha256: 67efec973a81151a55e55f8e747b455354979492978b2f9f22a342c6d841e6b7
+  
 - bestLlama: 'true'
   description: 'WizardLM - uncensored: An Instruction-following LLM Using Evol-Instruct'
   filename: WizardLM-7B-uncensored.ggml.q4_0.bin
@@ -34,3 +72,12 @@
   server: https://huggingface.co/TheBloke/WizardLM-7B-uncensored-GGML/resolve/previous_llama_ggmlv2/
   sha256: 67efec973a81151a55e55f8e747b455354979492978b2f9f22a342c6d841e6b7
 
+  
+- description: Koala 7B model produced at Berkeley
+  filename: koala-7B.ggmlv3.q4_0.bin
+  license: Non commercial
+  owner_link: https://huggingface.co/TheBloke
+  owner: TheBloke
+  server: https://huggingface.co/TheBloke/koala-7B-GGML/resolve/previous_llama_ggmlv2/
+  sha256: 14bcd51fbc09bcc456c79f9f0e4d070ad536e9d9e03811232e037b62580fe5e7
+
diff --git a/backends/py_llama_cpp/models.yaml b/backends/py_llama_cpp/models.yaml
index c8ed6a2b..e69de29b 100644
--- a/backends/py_llama_cpp/models.yaml
+++ b/backends/py_llama_cpp/models.yaml
@@ -1,11 +0,0 @@
-- bestLlama: 'true'
-  description: The official open assistant 30B model finally here
-  filename: OpenAssistant-SFT-7-Llama-30B.ggml.q4_0.bin
-  md5sum: 91f886b68fbce697e9a3cd501951e455
-  server: https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GGML/resolve/main/
-
-- bestLlama: 'true'
-  description: Stable vicuna 13B
-  filename: stable-vicuna-13B.ggml.q5_1.bin
-  md5sum: 91f886b68fbce697e9a3cd501951e455
-  server: https://huggingface.co/TheBloke/stable-vicuna-13B-GGML/resolve/main/