Upload 2 files

.gitattributes

@@ -42,3 +42,4 @@ phi3-4k-it-nvidia-chat-q4-GGUF.gguf filter=lfs diff=lfs merge=lfs -text
 phi-3-medium-4k-instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 stablelm-2-12b-chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+vicuna-13b-v1.5-16k.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text

models3.json

@@ -1,11 +1,11 @@
 [
   {
-    "name": "StableLM 12B",
-    "filename": "stablelm-2-12b-chat-Q4_0.gguf",
-    "url": "https://huggingface.co/SHMIS/ABS_AI_Helper/resolve/main/stablelm-2-12b-chat-Q4_0.gguf?download=true",
-    "promptTemplate": "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n%2<|im_end|>\n",
-    "systemPrompt": "%1\n",
-    "stopWord": ["<|end|>"],
+    "name": "vicuna-13b-16k",
+    "filename": "vicuna-13b-v1.5-16k.Q4_0.gguf",
+    "url": "https://huggingface.co/TheBloke/vicuna-13B-v1.5-16K-GGUF/resolve/main/vicuna-13b-v1.5-16k.Q4_0.gguf?download=true",
+    "promptTemplate": "User:\n%1\nAssistant:\n%2\n",
+    "systemPrompt": "System:\n%1\n",
+    "stopWord": ["<s>","</s>"],
     "type": "model",
     "requireRam": 17
   },
@@ -20,14 +20,14 @@
     "requireRam": 17
   },
   {
-    "name": "vicuna-13b-16k",
-    "filename": "vicuna-13b-v1.5-16k.Q4_0.gguf",
-    "url": "https://huggingface.co/TheBloke/vicuna-13B-v1.5-16K-GGUF/resolve/main/vicuna-13b-v1.5-16k.Q4_0.gguf?download=true",
-    "promptTemplate": "User:\n%1\nAssistant:\n%2\n",
-    "systemPrompt": "System:\n%1\n",
-    "stopWord": ["<s>","</s>"],
+    "name": "Llama 3 8b",
+    "filename": "Meta-Llama-3-8B-Instruct.Q4_0.gguf",
+    "url": "https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.Q4_0.gguf?download=true",
+    "promptTemplate": "<|start_header_id|>user<|end_header_id|>\n%1\n<|eot_id|>\n<|start_header_id|>assistant<|end_header_id|>\n%2\n<|eot_id|>\n",
+    "systemPrompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n%1\n<|eot_id|>\n",
+    "stopWord": ["<|eot_id|>"],
     "type": "model",
-    "requireRam": 17
+    "requireRam": 12
   },
   {
     "name": "Llama 3 8b neural",
@@ -48,16 +48,6 @@
     "stopWord": ["<|eot_id|>"],
     "type": "model",
     "requireRam": 12
-  },
-    {
-    "name": "Llama 3 8b",
-    "filename": "Meta-Llama-3-8B-Instruct.Q4_0.gguf",
-    "url": "https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.Q4_0.gguf?download=true",
-    "promptTemplate": "<|start_header_id|>user<|end_header_id|>\n%1\n<|eot_id|>\n<|start_header_id|>assistant<|end_header_id|>\n%2\n<|eot_id|>\n",
-    "systemPrompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n%1\n<|eot_id|>\n",
-    "stopWord": ["<|eot_id|>"],
-    "type": "model",
-    "requireRam": 12
   },
   {
     "name": "QWen 2 7b",

vicuna-13b-v1.5-16k.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776a8dc92c9a1eaf2a5eb8fd5e88753bd438adf9c992df96ac514d49764fb2da
+size 7365834688