Merge pull request #4 from laelhalawani/develop

Develop

.gitignore

@@ -166,3 +166,6 @@ cython_debug/
 *.gguf
 *.bin
 *.unfinished
+
+dev/
+.vscode/settings.json

gguf_modeldb/gguf_models/dolphin-2_6-phi-2.Q2_K.json

@@ -1,26 +1 @@
-{
-    "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/blob/main/dolphin-2_6-phi-2.Q2_K.gguf",
-    "gguf_file_path": "./gguf_modeldb/gguf_models/dolphin-2_6-phi-2.Q2_K.gguf",
-    "model_name": "dolphin-2_6-phi-2",
-    "model_quantization": "Q2_K",
-    "description": "Dolphin 2.6 phi 2 GGUF",
-    "keywords": [
-        "dolphin",
-        "phi2",
-        "uncesored",
-        "2.7B"
-    ],
-    "user_tags": {
-        "open": "<|im_start|>user\n",
-        "close": "<|im_end|>\n"
-    },
-    "ai_tags": {
-        "open": "<|im_start|>assistant",
-        "close": "<|im_end|>\n"
-    },
-    "system_tags": {
-        "open": "<|im_start|>system\n",
-        "close": "<|im_end|>\n"
-    },
-    "save_dir": "./gguf_modeldb/gguf_models/"
-}
+{"url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/blob/main/dolphin-2_6-phi-2.Q2_K.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/dolphin-2_6-phi-2.Q2_K.gguf", "model_name": "dolphin-2_6-phi-2", "model_quantization": "Q2_K", "description": "Dolphin 2.6 phi 2 GGUF", "keywords": ["dolphin", "phi2", "uncesored", "2.7B"], "user_tags": {"open": "<|im_start|>user\n", "close": "<|im_end|>\n"}, "ai_tags": {"open": "<|im_start|>assistant", "close": "<|im_end|>\n"}, "system_tags": {"open": "<|im_start|>system\n", "close": "<|im_end|>\n"}, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/dolphin-2_6-phi-2.Q3_K_L.json

@@ -1,26 +1 @@
-{
-    "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/blob/main/dolphin-2_6-phi-2.Q3_K_L.gguf",
-    "gguf_file_path": "./gguf_modeldb/gguf_models/dolphin-2_6-phi-2.Q3_K_L.gguf",
-    "model_name": "dolphin-2_6-phi-2",
-    "model_quantization": "Q3_K_L",
-    "description": "Dolphin 2.6 phi 2 GGUF",
-    "keywords": [
-        "dolphin",
-        "phi2",
-        "uncesored",
-        "2.7B"
-    ],
-    "user_tags": {
-        "open": "<|im_start|>user\n",
-        "close": "<|im_end|>\n"
-    },
-    "ai_tags": {
-        "open": "<|im_start|>assistant",
-        "close": "<|im_end|>\n"
-    },
-    "system_tags": {
-        "open": "<|im_start|>system\n",
-        "close": "<|im_end|>\n"
-    },
-    "save_dir": "./gguf_modeldb/gguf_models/"
-}
+{"url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/blob/main/dolphin-2_6-phi-2.Q3_K_L.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/dolphin-2_6-phi-2.Q3_K_L.gguf", "model_name": "dolphin-2_6-phi-2", "model_quantization": "Q3_K_L", "description": "Dolphin 2.6 phi 2 GGUF", "keywords": ["dolphin", "phi2", "uncesored", "2.7B"], "user_tags": {"open": "<|im_start|>user\n", "close": "<|im_end|>\n"}, "ai_tags": {"open": "<|im_start|>assistant", "close": "<|im_end|>\n"}, "system_tags": {"open": "<|im_start|>system\n", "close": "<|im_end|>\n"}, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q2_K.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q2_K.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q2_K.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q2_K", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q3_K_L.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q3_K_L.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q3_K_L.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q3_K_L", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q3_K_M.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q3_K_M.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q3_K_M.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q3_K_M", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q3_K_S.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q3_K_S.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q3_K_S.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q3_K_S", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q4_0.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q4_0.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q4_0.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q4_0", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q4_K_M.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q4_K_M.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q4_K_M.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q4_K_M", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q4_K_S.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q4_K_S.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q4_K_S.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q4_K_S", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q5_0.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q5_0.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q5_0.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q5_0", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q5_K_M.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q5_K_M.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q5_K_M.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q5_K_M", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q5_K_S.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q5_K_S.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q5_K_S.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q5_K_S", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q6_K.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q6_K.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q6_K.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q6_K", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q8_0.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/LLaMA-Pro-8B-Instruct-GGUF/blob/main/llama-pro-8b-instruct.Q8_0.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/llama-pro-8b-instruct.Q8_0.gguf", "model_name": "llama-pro-8b-instruct", "model_quantization": "Q8_0", "description": "LLaMA-PRO-Instruct, an enhanced version of the LLaMA2-7B model with 8.3 billion parameters, stands out for its specialization in programming, coding, and mathematical reasoning while retaining versatility in general language tasks. Developed by the Tencent ARC team, this model utilizes innovative block expansion techniques and undergoes meticulous training on a diverse dataset exceeding 80 billion tokens, encompassing coding and mathematical contexts.", "keywords": ["LLaMA PRO Instruct", "8B", "programming", "coding", "mathematical", "versatility", "Tencent ARC", "block expansion"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>", "close": ""}, "system_tags": null, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q2_K.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/blob/main/tinyllama-1.1b-chat-v1.0.Q2_K.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q2_K.gguf", "model_name": "tinyllama-1.1b-chat-v1.0", "model_quantization": "Q2_K", "description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens.", "keywords": ["TinyLlama", "1.1B", "instruct", "tiny", "v1.0"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>\n", "close": "\n"}, "system_tags": {"open": "<|system|>\n", "close": "\n"}, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q3_K_L.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/blob/main/tinyllama-1.1b-chat-v1.0.Q3_K_L.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q3_K_L.gguf", "model_name": "tinyllama-1.1b-chat-v1.0", "model_quantization": "Q3_K_L", "description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens.", "keywords": ["TinyLlama", "1.1B", "instruct", "tiny", "v1.0"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>\n", "close": "\n"}, "system_tags": {"open": "<|system|>\n", "close": "\n"}, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q3_K_M.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/blob/main/tinyllama-1.1b-chat-v1.0.Q3_K_M.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q3_K_M.gguf", "model_name": "tinyllama-1.1b-chat-v1.0", "model_quantization": "Q3_K_M", "description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens.", "keywords": ["TinyLlama", "1.1B", "instruct", "tiny", "v1.0"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>\n", "close": "\n"}, "system_tags": {"open": "<|system|>\n", "close": "\n"}, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q3_K_S.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/blob/main/tinyllama-1.1b-chat-v1.0.Q3_K_S.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q3_K_S.gguf", "model_name": "tinyllama-1.1b-chat-v1.0", "model_quantization": "Q3_K_S", "description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens.", "keywords": ["TinyLlama", "1.1B", "instruct", "tiny", "v1.0"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>\n", "close": "\n"}, "system_tags": {"open": "<|system|>\n", "close": "\n"}, "save_dir": "./gguf_modeldb/gguf_models/"}

gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q4_0.json

@@ -0,0 +1,27 @@
+{
+    "url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/blob/main/tinyllama-1.1b-chat-v1.0.Q4_0.gguf",
+    "gguf_file_path": "./gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q4_0.gguf",
+    "model_name": "tinyllama-1.1b-chat-v1.0",
+    "model_quantization": "Q4_0",
+    "description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens.",
+    "keywords": [
+        "TinyLlama",
+        "1.1B",
+        "instruct",
+        "tiny",
+        "v1.0"
+    ],
+    "user_tags": {
+        "open": "<|user|>\n",
+        "close": "\n"
+    },
+    "ai_tags": {
+        "open": "<|assistant|>\n",
+        "close": "\n"
+    },
+    "system_tags": {
+        "open": "<|system|>\n",
+        "close": "\n"
+    },
+    "save_dir": "./gguf_modeldb/gguf_models/"
+}

gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q4_K_M.json

@@ -0,0 +1 @@
+{"url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/blob/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf", "gguf_file_path": "./gguf_modeldb/gguf_models/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf", "model_name": "tinyllama-1.1b-chat-v1.0", "model_quantization": "Q4_K_M", "description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens.", "keywords": ["TinyLlama", "1.1B", "instruct", "tiny", "v1.0"], "user_tags": {"open": "<|user|>\n", "close": "\n"}, "ai_tags": {"open": "<|assistant|>\n", "close": "\n"}, "system_tags": {"open": "<|system|>\n", "close": "\n"}, "save_dir": "./gguf_modeldb/gguf_models/"}