diff --git a/models/capybara-34b/model.json b/models/capybara-34b/model.json
index e4263f957..e337191a9 100644
--- a/models/capybara-34b/model.json
+++ b/models/capybara-34b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "USER:\n",
-      "ai_prompt": "ASSISTANT:\n"
+      "prompt_template": "USER:\n{prompt}\nASSISTANT:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/deepseek-coder-1.3b/model.json b/models/deepseek-coder-1.3b/model.json
index 70f86ec89..77fa2d1f7 100644
--- a/models/deepseek-coder-1.3b/model.json
+++ b/models/deepseek-coder-1.3b/model.json
@@ -9,9 +9,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "### Instruction:\n",
-      "ai_prompt": "### Response:\n"
+      "prompt_template": "### Instruction:\n{prompt}\n### Response:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/deepseek-coder-34b/model.json b/models/deepseek-coder-34b/model.json
index 402419357..80b224691 100644
--- a/models/deepseek-coder-34b/model.json
+++ b/models/deepseek-coder-34b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "### Instruction:\n",
-      "ai_prompt": "### Response:\n"
+      "prompt_template": "### Instruction:\n{prompt}\n### Response:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/llama2-chat-70b-q4/model.json b/models/llama2-chat-70b-q4/model.json
index 07886aed5..abe44ddad 100644
--- a/models/llama2-chat-70b-q4/model.json
+++ b/models/llama2-chat-70b-q4/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "[INST] <<SYS>>\n",
-      "user_prompt": "<</SYS>>\n",
-      "ai_prompt": "[/INST]"
+      "prompt_template": "[INST] <<SYS>>\n{system_message}<</SYS>>\n{prompt}[/INST]"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/llama2-chat-7b-q4/model.json b/models/llama2-chat-7b-q4/model.json
index 2d1a67236..9ec601429 100644
--- a/models/llama2-chat-7b-q4/model.json
+++ b/models/llama2-chat-7b-q4/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "[INST] <<SYS>>\n",
-      "user_prompt": "<</SYS>>\n",
-      "ai_prompt": "[/INST]"
+      "prompt_template": "[INST] <<SYS>>\n{system_message}<</SYS>>\n{prompt}[/INST]"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/llama2-chat-7b-q5/model.json b/models/llama2-chat-7b-q5/model.json
index 96c652ab2..1e999003f 100644
--- a/models/llama2-chat-7b-q5/model.json
+++ b/models/llama2-chat-7b-q5/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "[INST] <<SYS>>\n",
-      "user_prompt": "<</SYS>>\n",
-      "ai_prompt": "[/INST]"
+      "prompt_template": "[INST] <<SYS>>\n{system_message}<</SYS>>\n{prompt}[/INST]"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/lzlv-70b/model.json b/models/lzlv-70b/model.json
index ca6af617e..cb2387432 100644
--- a/models/lzlv-70b/model.json
+++ b/models/lzlv-70b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "USER:\n",
-      "ai_prompt": "ASSISTANT:\n"
+      "prompt_template": "USER:\n{prompt}\nASSISTANT:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/mistral-ins-7b-q4/model.json b/models/mistral-ins-7b-q4/model.json
index 9fc86f1be..9f2c22a03 100644
--- a/models/mistral-ins-7b-q4/model.json
+++ b/models/mistral-ins-7b-q4/model.json
@@ -10,7 +10,8 @@
       "ctx_len": 2048,
       "system_prompt": "",
       "user_prompt": "<s>[INST]",
-      "ai_prompt": "[/INST]"
+      "ai_prompt": "[/INST]",
+      "prompt_template": "<s>[INST]{prompt}\n[/INST]"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/mistral-ins-7b-q5/model.json b/models/mistral-ins-7b-q5/model.json
index 291f2ad0e..328ba2926 100644
--- a/models/mistral-ins-7b-q5/model.json
+++ b/models/mistral-ins-7b-q5/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "<s>[INST]",
-      "ai_prompt": "[/INST]"
+      "prompt_template": "<s>[INST]{prompt}\n[/INST]"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/neural-chat-7b/model.json b/models/neural-chat-7b/model.json
index 1d6271469..20c14c507 100644
--- a/models/neural-chat-7b/model.json
+++ b/models/neural-chat-7b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "### System:\n",
-      "user_prompt": "### User:\n",
-      "ai_prompt": "### Assistant:\n"
+      "prompt_template": "### System:\n{system_message}### User:\n{prompt}### Assistant:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/noromaid-20b/model.json b/models/noromaid-20b/model.json
index 5c937a831..961c4bd25 100644
--- a/models/noromaid-20b/model.json
+++ b/models/noromaid-20b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "### Instruction:\n",
-      "ai_prompt": "### Response:\n"
+      "prompt_template": "### Instruction:{prompt}\n### Response:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/openhermes-neural-7b/model.json b/models/openhermes-neural-7b/model.json
index 8dcb51ad7..bc4a4e315 100644
--- a/models/openhermes-neural-7b/model.json
+++ b/models/openhermes-neural-7b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "<|im_start|>system\n",
-      "user_prompt": "<|im_end|>\n<|im_start|>user\n",
-      "ai_prompt": "<|im_end|>\n<|im_start|>assistant\n"
+      "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/openorca-13b/model.json b/models/openorca-13b/model.json
index 42c8bd96e..3478ad528 100644
--- a/models/openorca-13b/model.json
+++ b/models/openorca-13b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "<|im_start|>system\n",
-      "user_prompt": "<|im_end|>\n<|im_start|>user\n",
-      "ai_prompt": "<|im_end|>\n<|im_start|>assistant\n"
+      "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/phind-34b/model.json b/models/phind-34b/model.json
index eb3c1a18a..d3fc6664a 100644
--- a/models/phind-34b/model.json
+++ b/models/phind-34b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "### System Prompt\n",
-      "user_prompt": "### User Message\n",
-      "ai_prompt": "### Assistant\n"
+      "prompt_template": "### System Prompt\n{system_message}\n### User Message\n{prompt}\n### Assistant"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/rocket-3b/model.json b/models/rocket-3b/model.json
index 8d4fc76bf..02335a0ed 100644
--- a/models/rocket-3b/model.json
+++ b/models/rocket-3b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 4096,
-      "system_prompt": "<|im_start|>system\n",
-      "user_prompt": "<|im_end|>\n<|im_start|>user\n",
-      "ai_prompt": "<|im_end|>\n<|im_start|>assistant\n"
+      "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/starling-7b/model.json b/models/starling-7b/model.json
index 52b03f8b1..cdb06c2c7 100644
--- a/models/starling-7b/model.json
+++ b/models/starling-7b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "GPT4 User: ",
-      "ai_prompt": "<|end_of_turn|>\nGPT4 Assistant: "
+      "prompt_template": "GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/tiefighter-13b/model.json b/models/tiefighter-13b/model.json
index 20075777c..3f5abe3e3 100644
--- a/models/tiefighter-13b/model.json
+++ b/models/tiefighter-13b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "### Instruction: ",
-      "ai_prompt": "\n### Response: "
+      "prompt_template": "### Instruction:\n{prompt}\n### Response:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/tinyllama-1.1b/model.json b/models/tinyllama-1.1b/model.json
index bb6aeaf5c..d924be046 100644
--- a/models/tinyllama-1.1b/model.json
+++ b/models/tinyllama-1.1b/model.json
@@ -8,9 +8,7 @@
   "format": "gguf",
   "settings": {
       "ctx_len": 2048,
-      "system_prompt": "<|system|>\n",
-      "user_prompt": "<|user|>\n",
-      "ai_prompt": "<|assistant|>\n"
+      "prompt_template": "<|system|>\n{system_message}<|user|>\n{prompt}<|assistant|>"
   },
   "parameters": {
       "max_tokens": 2048
diff --git a/models/wizardcoder-13b/model.json b/models/wizardcoder-13b/model.json
index 40f275037..774c1a424 100644
--- a/models/wizardcoder-13b/model.json
+++ b/models/wizardcoder-13b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "",
-      "user_prompt": "### Instruction:\n",
-      "ai_prompt": "### Response:\n"
+      "prompt_template": "### Instruction:\n{prompt}\n### Response:"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/yi-34b/model.json b/models/yi-34b/model.json
index ab111591c..6a570b4de 100644
--- a/models/yi-34b/model.json
+++ b/models/yi-34b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "<|im_start|>system\n",
-      "user_prompt": "<|im_end|>\n<|im_start|>user\n",
-      "ai_prompt": "<|im_end|>\n<|im_start|>assistant\n"
+      "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
     },
     "parameters": {
       "max_tokens": 2048
diff --git a/models/zephyr-beta-7b/model.json b/models/zephyr-beta-7b/model.json
index 4993366fd..b12f03c67 100644
--- a/models/zephyr-beta-7b/model.json
+++ b/models/zephyr-beta-7b/model.json
@@ -8,9 +8,7 @@
     "format": "gguf",
     "settings": {
       "ctx_len": 2048,
-      "system_prompt": "<|system|>\n",
-      "user_prompt": "</s>\n<|user|>\n",
-      "ai_prompt": "</s>\n<|assistant|>\n"
+      "prompt_template": "<|system|>\n{system_message}</s>\n<|user|>\n{prompt}</s>\n<|assistant|>"
     },
     "parameters": {
       "max_tokens": 2048