Merge pull request #1829 from janhq/chore/update-hub

chore: update models

extensions/model-extension/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@janhq/model-extension",
-  "version": "1.0.23",
+  "version": "1.0.24",
   "description": "Model Management Extension provides model exploration and seamless downloads",
   "main": "dist/index.js",
   "module": "dist/module.js",

models/dolphin-phi-2/model.json

@@ -0,0 +1,32 @@
+{
+    "source": [
+      {
+        "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/resolve/main/dolphin-2_6-phi-2.Q8_0.gguf",
+        "filename": "dolphin-2_6-phi-2.Q8_0.gguf"
+      }
+    ],
+    "id": "dolphin-phi-2",
+    "object": "model",
+    "name": "Dolphin Phi-2 2.7B Q8",
+    "version": "1.0",
+    "description": "Dolphin Phi-2 is a 2.7B model, fine-tuned for chat, excelling in common sense and logical reasoning benchmarks.",
+    "format": "gguf",
+    "settings": {
+      "ctx_len": 4096,
+      "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant",
+      "llama_model_path": "dolphin-2_6-phi-2.Q8_0.gguf"
+    },
+    "parameters": {
+      "max_tokens": 4096,
+      "stop": ["<|im_end|>"]
+    },
+    "metadata": {
+      "author": "Cognitive Computations, Microsoft",
+      "tags": [
+        "3B",
+        "Finetuned"
+      ],
+      "size": 2960000000
+    },
+    "engine": "nitro"
+  }

models/llamacorn-1.1b/model.json

@@ -0,0 +1,37 @@
+{
+    "source": [
+        {
+            "url":"https://huggingface.co/janhq/llamacorn-1.1b-chat-GGUF/resolve/main/llamacorn-1.1b-chat.Q8_0.gguf",
+            "filename": "llamacorn-1.1b-chat.Q8_0.gguf"
+        }
+    ],
+    "id": "llamacorn-1.1b",
+    "object": "model",
+    "name": "LlamaCorn 1.1B Q8",
+    "version": "1.0",
+    "description": "LlamaCorn is designed to improve chat functionality from TinyLlama.",
+    "format": "gguf",
+    "settings": {
+      "ctx_len": 2048,
+      "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant",
+      "llama_model_path": "llamacorn-1.1b-chat.Q8_0.gguf"
+    },
+    "parameters": {
+      "temperature": 0.7,
+      "top_p": 0.95,
+      "stream": true,
+      "max_tokens": 2048,
+      "stop": [],
+      "frequency_penalty": 0,
+      "presence_penalty": 0
+    },
+    "metadata": {
+      "author": "Jan",
+      "tags": [
+        "Tiny",
+        "Finetuned"
+      ],
+      "size": 1170000000
+    },
+    "engine": "nitro"
+  }

models/openchat-3.5-7b/model.json

@@ -1,8 +1,8 @@
 {
   "sources": [
     {
-      "filename": "openchat-3.5-1210.Q4_K_M.gguf",
+      "filename": "openchat-3.5-0106.Q4_K_M.gguf",
-      "url": "https://huggingface.co/TheBloke/openchat-3.5-1210-GGUF/resolve/main/openchat-3.5-1210.Q4_K_M.gguf"
+      "url": "https://huggingface.co/TheBloke/openchat-3.5-0106-GGUF/resolve/main/openchat-3.5-0106.Q4_K_M.gguf"
     }
   ],
   "id": "openchat-3.5-7b",
@@ -14,7 +14,7 @@
   "settings": {
     "ctx_len": 4096,
     "prompt_template": "GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:",
-    "llama_model_path": "openchat-3.5-1210.Q4_K_M.gguf"
+    "llama_model_path": "openchat-3.5-0106.Q4_K_M.gguf"
   },
   "parameters": {
     "temperature": 0.7,

models/stable-zephyr-3b/model.json

@@ -0,0 +1,34 @@
+{
+    "source": [
+      {
+        "url": "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q8_0.gguf",
+        "filename": "stablelm-zephyr-3b.Q8_0.gguf"
+      }
+    ],
+    "id": "stable-zephyr-3b",
+    "object": "model",
+    "name": "Stable Zephyr 3B Q8",
+    "version": "1.0",
+    "description": "StableLM Zephyr 3B is trained for safe and reliable chatting.",
+    "format": "gguf",
+    "settings": {
+      "ctx_len": 4096,
+      "prompt_template": "<|user|>\n{prompt}<|endoftext|>\n<|assistant|>",
+      "llama_model_path": "stablelm-zephyr-3b.Q8_0.gguf"
+    },
+    "parameters": {
+      "temperature": 0.7,
+      "top_p": 0.95,
+      "stream": true,
+      "max_tokens": 4096,
+      "stop": ["<|endoftext|>"],
+      "frequency_penalty": 0,
+      "presence_penalty": 0
+    },
+    "metadata": {
+      "author": "StabilityAI",
+      "tags": ["3B", "Finetuned"],
+      "size": 2970000000
+    },
+    "engine": "nitro"
+  }

models/yarn-mistral-7b/model.json

@@ -1,31 +0,0 @@
-{
-  "sources": [
-    {
-      "url": "https://huggingface.co/TheBloke/Yarn-Mistral-7B-128k-GGUF/resolve/main/yarn-mistral-7b-128k.Q4_K_M.gguf"
-    }
-  ],
-  "id": "yarn-mistral-7b",
-  "object": "model",
-  "name": "Yarn Mistral 7B Q4",
-  "version": "1.0",
-  "description": "Yarn Mistral 7B is a language model for long context and supports a 128k token context window.",
-  "format": "gguf",
-  "settings": {
-    "ctx_len": 4096,
-    "prompt_template": "{prompt}"
-  },
-  "parameters": {
-    "temperature": 0.7,
-    "top_p": 0.95,
-    "stream": true,
-    "max_tokens": 4096,
-    "frequency_penalty": 0,
-    "presence_penalty": 0
-  },
-  "metadata": {
-    "author": "NousResearch, The Bloke",
-    "tags": ["7B", "Finetuned"],
-    "size": 4370000000
-  },
-  "engine": "nitro"
-}