From 05a553a55aea898c15325083cd1637e8217a5a84 Mon Sep 17 00:00:00 2001
From: SadPanda <1459500+OG-Sadpanda@users.noreply.github.com>
Date: Fri, 17 Jan 2025 14:13:12 -0500
Subject: [PATCH 1/9] Update launch.sh

---
 launch.sh | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/launch.sh b/launch.sh
index 236d816..5e23ec8 100755
--- a/launch.sh
+++ b/launch.sh
@@ -4,6 +4,9 @@
 cd ragnarok
 python3 -m venv venv
 source venv/bin/activate
+export LLAMA_CUBLAS=1
+CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip3 install llama-cpp-python==0.2.26
+export CUDA_VISIBLE_DEVICES=0,1
 pip3 install -r requirements.txt
 
 # kick off the main app

From 3d37681e2f0daa733d7b40c0eb41312bcea06131 Mon Sep 17 00:00:00 2001
From: SadPanda <1459500+OG-Sadpanda@users.noreply.github.com>
Date: Fri, 17 Jan 2025 14:13:46 -0500
Subject: [PATCH 2/9] Update requirements.txt

---
 ragnarok/requirements.txt | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/ragnarok/requirements.txt b/ragnarok/requirements.txt
index 019221c..c36bed7 100644
--- a/ragnarok/requirements.txt
+++ b/ragnarok/requirements.txt
@@ -3,7 +3,6 @@ sentence-transformers==2.2.2
 huggingface-hub==0.20.3
 langchain==0.1.2
 langchain-community==0.0.14
-llama-cpp-python==0.2.26
 streamlit==1.30.0
 streamlit-extras==0.3.6
-streamlit-cookies-manager==0.2.0
\ No newline at end of file
+streamlit-cookies-manager==0.2.0

From d37332329b7edd1c7bff39efeb32237dab1ab198 Mon Sep 17 00:00:00 2001
From: SadPanda <1459500+OG-Sadpanda@users.noreply.github.com>
Date: Fri, 17 Jan 2025 16:41:08 -0500
Subject: [PATCH 3/9] Update launch.sh

---
 launch.sh | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/launch.sh b/launch.sh
index 5e23ec8..a2ea306 100755
--- a/launch.sh
+++ b/launch.sh
@@ -4,9 +4,15 @@
 cd ragnarok
 python3 -m venv venv
 source venv/bin/activate
+# default llama-cpp-python does not support cuda, have to provide cmake_args.
 export LLAMA_CUBLAS=1
 CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip3 install llama-cpp-python==0.2.26
-export CUDA_VISIBLE_DEVICES=0,1
+
+# You can change the visible device values here to specify what GPU(s) that you want RAGnarok to use (or not use). 
+# For this example I'm only allowing RAGnarok to use GPU device 0.
+# See https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars for more details. 
+export CUDA_VISIBLE_DEVICES=0
+
 pip3 install -r requirements.txt
 
 # kick off the main app

From b384c31e6c4007c6cf0e5e2033b9050f31637ccb Mon Sep 17 00:00:00 2001
From: shadi <shadi.m.dibbini@aexp.com>
Date: Thu, 23 Jan 2025 14:12:07 -0500
Subject: [PATCH 4/9] adding deepseek-r1 and updating openchat

---
 ragnarok/RAGnarok_Settings.py     |  2 +-
 ragnarok/pages/1_RAGnarok_Chat.py | 12 ++++++++----
 ragnarok/pages/2_Free_Chat.py     | 12 ++++++++----
 3 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/ragnarok/RAGnarok_Settings.py b/ragnarok/RAGnarok_Settings.py
index 05aa72d..0528cf8 100755
--- a/ragnarok/RAGnarok_Settings.py
+++ b/ragnarok/RAGnarok_Settings.py
@@ -98,7 +98,7 @@ def wait_for_nemesis(nemesis_url, nemesis_user, nemesis_password, wait_timeout =
             default_index = 2
     llm_model = st.selectbox(
         label='LLM model to use',
-        options=('Intel/neural-chat-7b-v3-3', 'openchat-3.5-0106', 'Starling-LM-7B-alpha'),
+        options=('Intel/neural-chat-7b-v3-3', 'DeepSeek-R1-Distill-Llama-8B', 'openchat-3.5-1210', 'Starling-LM-7B-alpha'),
         help="The core LLM to use for chat over retrieved document snippets.",
         index=default_index
     )
diff --git a/ragnarok/pages/1_RAGnarok_Chat.py b/ragnarok/pages/1_RAGnarok_Chat.py
index 62b45ca..5ddba1e 100644
--- a/ragnarok/pages/1_RAGnarok_Chat.py
+++ b/ragnarok/pages/1_RAGnarok_Chat.py
@@ -102,8 +102,10 @@ def get_reranker(reranking_model, device):
 try:
     if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
         llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf", local_files_only=True)
-    elif cookies["llm_model"] == "openchat-3.5-0106":
-        llm_model_path = hf_hub_download("TheBloke/openchat-3.5-0106-GGUF", filename="openchat-3.5-0106.Q5_K_M.gguf", local_files_only=True)
+    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
+        llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf", local_files_only=True)
+    elif cookies["llm_model"] == "openchat-3.5-1210":
+        llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf", local_files_only=True)
     elif cookies["llm_model"] == "Starling-LM-7B-alpha":
         llm_model_path = hf_hub_download("TheBloke/Starling-LM-7B-alpha-GGUF", filename="starling-lm-7b-alpha.Q5_K_M.gguf", local_files_only=True)
     else:
@@ -113,8 +115,10 @@ def get_reranker(reranking_model, device):
     with st.spinner("Downloading LLM model (this will take some time)..."):
         if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
             llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf")
-        elif cookies["llm_model"] == "openchat-3.5-0106":
-            llm_model_path = hf_hub_download("TheBloke/openchat-3.5-0106-GGUF", filename="openchat-3.5-0106.Q5_K_M.gguf")
+        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
+            llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf")
+        elif cookies["llm_model"] == "openchat-3.5-1210":
+            llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf")
         elif cookies["llm_model"] == "Starling-LM-7B-alpha":
             llm_model_path = hf_hub_download("TheBloke/Starling-LM-7B-alpha-GGUF", filename="starling-lm-7b-alpha.Q5_K_M.gguf")
         else:
diff --git a/ragnarok/pages/2_Free_Chat.py b/ragnarok/pages/2_Free_Chat.py
index 4f2eced..c1734f8 100644
--- a/ragnarok/pages/2_Free_Chat.py
+++ b/ragnarok/pages/2_Free_Chat.py
@@ -52,8 +52,10 @@ def get_llm(llm_model_path, n_gpu_layers):
 try:
     if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
         llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf", local_files_only=True)
-    elif cookies["llm_model"] == "openchat-3.5-0106":
-        llm_model_path = hf_hub_download("TheBloke/openchat-3.5-0106-GGUF", filename="openchat-3.5-0106.Q5_K_M.gguf", local_files_only=True)
+    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
+        llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf", local_files_only=True)
+    elif cookies["llm_model"] == "openchat-3.5-1210":
+        llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf", local_files_only=True)
     elif cookies["llm_model"] == "Starling-LM-7B-alpha":
         llm_model_path = hf_hub_download("TheBloke/Starling-LM-7B-alpha-GGUF", filename="starling-lm-7b-alpha.Q5_K_M.gguf", local_files_only=True)
     else:
@@ -63,8 +65,10 @@ def get_llm(llm_model_path, n_gpu_layers):
     with st.spinner("Downloading LLM model (this will take some time)..."):
         if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
             llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf")
-        elif cookies["llm_model"] == "openchat-3.5-0106":
-            llm_model_path = hf_hub_download("TheBloke/openchat-3.5-0106-GGUF", filename="openchat-3.5-0106.Q5_K_M.gguf")
+        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
+            llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf")
+        elif cookies["llm_model"] == "openchat-3.5-1210":
+            llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf")
         elif cookies["llm_model"] == "Starling-LM-7B-alpha":
             llm_model_path = hf_hub_download("TheBloke/Starling-LM-7B-alpha-GGUF", filename="starling-lm-7b-alpha.Q5_K_M.gguf")
         else:

From 3f706d3ea9090cd24a395316c32e5dc41a58fc33 Mon Sep 17 00:00:00 2001
From: shadi <shadi.m.dibbini@aexp.com>
Date: Fri, 24 Jan 2025 11:42:44 -0500
Subject: [PATCH 5/9] fixing deepseek settings

---
 ragnarok/RAGnarok_Settings.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/ragnarok/RAGnarok_Settings.py b/ragnarok/RAGnarok_Settings.py
index 0528cf8..14930ef 100755
--- a/ragnarok/RAGnarok_Settings.py
+++ b/ragnarok/RAGnarok_Settings.py
@@ -92,8 +92,10 @@ def wait_for_nemesis(nemesis_url, nemesis_user, nemesis_password, wait_timeout =
     if "llm_model" in cookies:
         if "neural-chat" in cookies["llm_model"].lower():
             default_index = 0
+        elif "deepseek" in cookies["llm_model"].lower():
+            default_index = 1   
         elif "openchat" in cookies["llm_model"].lower():
-            default_index = 1
+            default_index = 2
         elif "starling" in cookies["llm_model"].lower():
             default_index = 2
     llm_model = st.selectbox(

From ab828253e53ab98978a3c7e09d374a0ea6ab9be0 Mon Sep 17 00:00:00 2001
From: shadi <shadi.m.dibbini@aexp.com>
Date: Fri, 24 Jan 2025 13:02:20 -0500
Subject: [PATCH 6/9] fixing deepseek settings

---
 ragnarok/RAGnarok_Settings.py     | 2 +-
 ragnarok/pages/1_RAGnarok_Chat.py | 8 ++++----
 ragnarok/pages/2_Free_Chat.py     | 8 ++++----
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/ragnarok/RAGnarok_Settings.py b/ragnarok/RAGnarok_Settings.py
index 14930ef..d9dc2dc 100755
--- a/ragnarok/RAGnarok_Settings.py
+++ b/ragnarok/RAGnarok_Settings.py
@@ -100,7 +100,7 @@ def wait_for_nemesis(nemesis_url, nemesis_user, nemesis_password, wait_timeout =
             default_index = 2
     llm_model = st.selectbox(
         label='LLM model to use',
-        options=('Intel/neural-chat-7b-v3-3', 'DeepSeek-R1-Distill-Llama-8B', 'openchat-3.5-1210', 'Starling-LM-7B-alpha'),
+        options=('Intel/neural-chat-7b-v3-3', 'DeepSeek-R1-Distill-Qwen-7B', 'openchat-3.5-1210', 'Starling-LM-7B-alpha'),
         help="The core LLM to use for chat over retrieved document snippets.",
         index=default_index
     )
diff --git a/ragnarok/pages/1_RAGnarok_Chat.py b/ragnarok/pages/1_RAGnarok_Chat.py
index 5ddba1e..72a2770 100644
--- a/ragnarok/pages/1_RAGnarok_Chat.py
+++ b/ragnarok/pages/1_RAGnarok_Chat.py
@@ -102,8 +102,8 @@ def get_reranker(reranking_model, device):
 try:
     if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
         llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf", local_files_only=True)
-    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
-        llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf", local_files_only=True)
+    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Qwen-7B":
+        llm_model_path = hf_hub_download("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF", filename="DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf", local_files_only=True)
     elif cookies["llm_model"] == "openchat-3.5-1210":
         llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf", local_files_only=True)
     elif cookies["llm_model"] == "Starling-LM-7B-alpha":
@@ -115,8 +115,8 @@ def get_reranker(reranking_model, device):
     with st.spinner("Downloading LLM model (this will take some time)..."):
         if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
             llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf")
-        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
-            llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf")
+        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Qwen-7B":
+            llm_model_path = hf_hub_download("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF", filename="DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf")
         elif cookies["llm_model"] == "openchat-3.5-1210":
             llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf")
         elif cookies["llm_model"] == "Starling-LM-7B-alpha":
diff --git a/ragnarok/pages/2_Free_Chat.py b/ragnarok/pages/2_Free_Chat.py
index c1734f8..0f4ed36 100644
--- a/ragnarok/pages/2_Free_Chat.py
+++ b/ragnarok/pages/2_Free_Chat.py
@@ -52,8 +52,8 @@ def get_llm(llm_model_path, n_gpu_layers):
 try:
     if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
         llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf", local_files_only=True)
-    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
-        llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf", local_files_only=True)
+    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Qwen-7B":
+        llm_model_path = hf_hub_download("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF", filename="DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf", local_files_only=True)
     elif cookies["llm_model"] == "openchat-3.5-1210":
         llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf", local_files_only=True)
     elif cookies["llm_model"] == "Starling-LM-7B-alpha":
@@ -65,8 +65,8 @@ def get_llm(llm_model_path, n_gpu_layers):
     with st.spinner("Downloading LLM model (this will take some time)..."):
         if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
             llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf")
-        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
-            llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf")
+        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Qwen-7B":
+            llm_model_path = hf_hub_download("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF", filename="DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf")
         elif cookies["llm_model"] == "openchat-3.5-1210":
             llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf")
         elif cookies["llm_model"] == "Starling-LM-7B-alpha":

From 28febcb0380506e15100fd180ac8fb2ed0a25460 Mon Sep 17 00:00:00 2001
From: shadi <shadi.m.dibbini@aexp.com>
Date: Mon, 27 Jan 2025 09:40:48 -0500
Subject: [PATCH 7/9] fixing settings

---
 ragnarok/RAGnarok_Settings.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ragnarok/RAGnarok_Settings.py b/ragnarok/RAGnarok_Settings.py
index d9dc2dc..e4f528f 100755
--- a/ragnarok/RAGnarok_Settings.py
+++ b/ragnarok/RAGnarok_Settings.py
@@ -97,7 +97,7 @@ def wait_for_nemesis(nemesis_url, nemesis_user, nemesis_password, wait_timeout =
         elif "openchat" in cookies["llm_model"].lower():
             default_index = 2
         elif "starling" in cookies["llm_model"].lower():
-            default_index = 2
+            default_index = 3
     llm_model = st.selectbox(
         label='LLM model to use',
         options=('Intel/neural-chat-7b-v3-3', 'DeepSeek-R1-Distill-Qwen-7B', 'openchat-3.5-1210', 'Starling-LM-7B-alpha'),

From a521e932e6b15c2fe829ac5059f5301001b3d424 Mon Sep 17 00:00:00 2001
From: shadi <shadi.m.dibbini@aexp.com>
Date: Mon, 27 Jan 2025 09:44:41 -0500
Subject: [PATCH 8/9] fixing deepseek model

---
 ragnarok/RAGnarok_Settings.py     | 2 +-
 ragnarok/pages/1_RAGnarok_Chat.py | 8 ++++----
 ragnarok/pages/2_Free_Chat.py     | 8 ++++----
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/ragnarok/RAGnarok_Settings.py b/ragnarok/RAGnarok_Settings.py
index e4f528f..80dcc3b 100755
--- a/ragnarok/RAGnarok_Settings.py
+++ b/ragnarok/RAGnarok_Settings.py
@@ -100,7 +100,7 @@ def wait_for_nemesis(nemesis_url, nemesis_user, nemesis_password, wait_timeout =
             default_index = 3
     llm_model = st.selectbox(
         label='LLM model to use',
-        options=('Intel/neural-chat-7b-v3-3', 'DeepSeek-R1-Distill-Qwen-7B', 'openchat-3.5-1210', 'Starling-LM-7B-alpha'),
+        options=('Intel/neural-chat-7b-v3-3', 'DeepSeek-R1-Distill-Llama-8B', 'openchat-3.5-1210', 'Starling-LM-7B-alpha'),
         help="The core LLM to use for chat over retrieved document snippets.",
         index=default_index
     )
diff --git a/ragnarok/pages/1_RAGnarok_Chat.py b/ragnarok/pages/1_RAGnarok_Chat.py
index 72a2770..413b71f 100644
--- a/ragnarok/pages/1_RAGnarok_Chat.py
+++ b/ragnarok/pages/1_RAGnarok_Chat.py
@@ -102,8 +102,8 @@ def get_reranker(reranking_model, device):
 try:
     if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
         llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf", local_files_only=True)
-    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Qwen-7B":
-        llm_model_path = hf_hub_download("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF", filename="DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf", local_files_only=True)
+    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
+        llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf", local_files_only=True)
     elif cookies["llm_model"] == "openchat-3.5-1210":
         llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf", local_files_only=True)
     elif cookies["llm_model"] == "Starling-LM-7B-alpha":
@@ -115,8 +115,8 @@ def get_reranker(reranking_model, device):
     with st.spinner("Downloading LLM model (this will take some time)..."):
         if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
             llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf")
-        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Qwen-7B":
-            llm_model_path = hf_hub_download("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF", filename="DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf")
+        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
+            llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf")
         elif cookies["llm_model"] == "openchat-3.5-1210":
             llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf")
         elif cookies["llm_model"] == "Starling-LM-7B-alpha":
diff --git a/ragnarok/pages/2_Free_Chat.py b/ragnarok/pages/2_Free_Chat.py
index 0f4ed36..2a10975 100644
--- a/ragnarok/pages/2_Free_Chat.py
+++ b/ragnarok/pages/2_Free_Chat.py
@@ -52,8 +52,8 @@ def get_llm(llm_model_path, n_gpu_layers):
 try:
     if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
         llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf", local_files_only=True)
-    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Qwen-7B":
-        llm_model_path = hf_hub_download("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF", filename="DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf", local_files_only=True)
+    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
+        llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf", local_files_only=True)
     elif cookies["llm_model"] == "openchat-3.5-1210":
         llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf", local_files_only=True)
     elif cookies["llm_model"] == "Starling-LM-7B-alpha":
@@ -65,8 +65,8 @@ def get_llm(llm_model_path, n_gpu_layers):
     with st.spinner("Downloading LLM model (this will take some time)..."):
         if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
             llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf")
-        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Qwen-7B":
-            llm_model_path = hf_hub_download("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF", filename="DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf")
+        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
+            llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf")
         elif cookies["llm_model"] == "openchat-3.5-1210":
             llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf")
         elif cookies["llm_model"] == "Starling-LM-7B-alpha":

From 7cfc83d1cd7fe1f8d4434a11b5bc09ca3fafebc6 Mon Sep 17 00:00:00 2001
From: shadi <shadi.m.dibbini@aexp.com>
Date: Mon, 27 Jan 2025 10:24:48 -0500
Subject: [PATCH 9/9] removing deepseek

---
 ragnarok/RAGnarok_Settings.py     | 10 ++++------
 ragnarok/pages/1_RAGnarok_Chat.py |  4 ----
 ragnarok/pages/2_Free_Chat.py     |  4 ----
 3 files changed, 4 insertions(+), 14 deletions(-)

diff --git a/ragnarok/RAGnarok_Settings.py b/ragnarok/RAGnarok_Settings.py
index 80dcc3b..20e79bb 100755
--- a/ragnarok/RAGnarok_Settings.py
+++ b/ragnarok/RAGnarok_Settings.py
@@ -91,16 +91,14 @@ def wait_for_nemesis(nemesis_url, nemesis_user, nemesis_password, wait_timeout =
     default_index = 0
     if "llm_model" in cookies:
         if "neural-chat" in cookies["llm_model"].lower():
-            default_index = 0
-        elif "deepseek" in cookies["llm_model"].lower():
-            default_index = 1   
+            default_index = 0  
         elif "openchat" in cookies["llm_model"].lower():
-            default_index = 2
+            default_index = 1
         elif "starling" in cookies["llm_model"].lower():
-            default_index = 3
+            default_index = 2
     llm_model = st.selectbox(
         label='LLM model to use',
-        options=('Intel/neural-chat-7b-v3-3', 'DeepSeek-R1-Distill-Llama-8B', 'openchat-3.5-1210', 'Starling-LM-7B-alpha'),
+        options=('Intel/neural-chat-7b-v3-3', 'openchat-3.5-1210', 'Starling-LM-7B-alpha'),
         help="The core LLM to use for chat over retrieved document snippets.",
         index=default_index
     )
diff --git a/ragnarok/pages/1_RAGnarok_Chat.py b/ragnarok/pages/1_RAGnarok_Chat.py
index 413b71f..3b1d176 100644
--- a/ragnarok/pages/1_RAGnarok_Chat.py
+++ b/ragnarok/pages/1_RAGnarok_Chat.py
@@ -102,8 +102,6 @@ def get_reranker(reranking_model, device):
 try:
     if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
         llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf", local_files_only=True)
-    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
-        llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf", local_files_only=True)
     elif cookies["llm_model"] == "openchat-3.5-1210":
         llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf", local_files_only=True)
     elif cookies["llm_model"] == "Starling-LM-7B-alpha":
@@ -115,8 +113,6 @@ def get_reranker(reranking_model, device):
     with st.spinner("Downloading LLM model (this will take some time)..."):
         if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
             llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf")
-        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
-            llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf")
         elif cookies["llm_model"] == "openchat-3.5-1210":
             llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf")
         elif cookies["llm_model"] == "Starling-LM-7B-alpha":
diff --git a/ragnarok/pages/2_Free_Chat.py b/ragnarok/pages/2_Free_Chat.py
index 2a10975..643b6e5 100644
--- a/ragnarok/pages/2_Free_Chat.py
+++ b/ragnarok/pages/2_Free_Chat.py
@@ -52,8 +52,6 @@ def get_llm(llm_model_path, n_gpu_layers):
 try:
     if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
         llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf", local_files_only=True)
-    elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
-        llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf", local_files_only=True)
     elif cookies["llm_model"] == "openchat-3.5-1210":
         llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf", local_files_only=True)
     elif cookies["llm_model"] == "Starling-LM-7B-alpha":
@@ -65,8 +63,6 @@ def get_llm(llm_model_path, n_gpu_layers):
     with st.spinner("Downloading LLM model (this will take some time)..."):
         if cookies["llm_model"] == "Intel/neural-chat-7b-v3-3":
             llm_model_path = hf_hub_download("TheBloke/neural-chat-7B-v3-3-GGUF", filename="neural-chat-7b-v3-3.Q5_K_M.gguf")
-        elif cookies["llm_model"] == "DeepSeek-R1-Distill-Llama-8B":
-            llm_model_path = hf_hub_download("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF", filename="DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf")
         elif cookies["llm_model"] == "openchat-3.5-1210":
             llm_model_path = hf_hub_download("TheBloke/openchat-3.5-1210-GGUF", filename="openchat-3.5-1210.Q8_0.gguf")
         elif cookies["llm_model"] == "Starling-LM-7B-alpha":