Upload models.json

models.json

@@ -15,6 +15,7 @@
         "developer_url": "https://ai.meta.com/llama/",
         "file_size": 1430,
         "context" : 2048,
+        "max_context" : 2048,
         "temp" : 0.6,
         "prompt_format" : "<human>: {{prompt}}\n<bot>: ",
         "top_k" : 5,
@@ -49,6 +50,7 @@
          "developer_url": "https://huggingface.co/ahxt/LiteLlama-460M-1T",
          "file_size": 493,
          "context" : 1024,
+         "max_context" : 1024,
          "temp" : 0.6,
          "prompt_format" : "<human>: {{prompt}}\n<bot>:",
          "top_k" : 5,
@@ -83,6 +85,7 @@
          "developer_url": "https://github.com/jzhang38/TinyLlama",
          "file_size": 1170,
          "context" : 4096,
+         "max_context" : 4096,
          "temp" : 0.6,
          "prompt_format" : "<|system|>You are a friendly chatbot who always responds in the style of a pirate.</s><|user|>{{prompt}}</s><|assistant|>",
          "top_k" : 5,
@@ -117,6 +120,7 @@
         "developer_url": "https://mistral.ai/",
         "file_size": 7695,
         "context" : 4096,
+        "max_context" : 4096,
         "temp" : 0.6,
         "prompt_format" : "<s>[INST]{{prompt}}[/INST]</s>",
         "top_k" : 5,
@@ -151,6 +155,7 @@
         "developer_url": "https://openchat.team/",
         "file_size": 7695,
         "context" : 4096,
+        "max_context" : 4096,
         "temp" : 0.6,
         "prompt_format" : "<s>[INST]{{prompt}}[/INST]</s>",
         "top_k" : 5,
@@ -185,6 +190,7 @@
         "developer_url": "https://huggingface.co/microsoft/phi-2",
         "file_size": 2960,
         "context" : 4096,
+        "max_context" : 4096,
         "temp" : 0.6,
         "prompt_format" : "Instruct: {{prompt}}\nOutput:",
         "top_k" : 5,
@@ -219,6 +225,7 @@
         "developer_url": "https://01.ai/",
         "file_size": 6440,
         "context" : 200000,
+        "max_context" : 200000,
         "temp" : 0.6,
         "prompt_format" : "<|im_start|>user\n<|im_end|>\n{{prompt}}\n<|im_start|>assistant\n",
         "top_k" : 5,
@@ -253,6 +260,7 @@
         "developer_url": "https://huggingface.co/google",
         "file_size": 2669,
         "context" : 8192,
+        "max_context" : 8192,
         "temp" : 0.6,
         "prompt_format" : "<bos><start_of_turn>user\n{{prompt}}<end_of_turn>\n<start_of_turn>model\n",
         "top_k" : 5,
@@ -287,6 +295,7 @@
         "developer_url": "https://www.bigcode-project.org/",
         "file_size": 3220,
         "context" : 8192,
+        "max_context" : 8192,
         "temp" : 0.6,
         "prompt_format" : "### Instruction\n{{prompt}}### Response\n",
         "top_k" : 5,
@@ -321,6 +330,7 @@
         "developer_url": "https://m-a-p.ai/",
         "file_size": 2218,
         "context" : 4096,
+        "max_context" : 4096,
         "temp" : 0.6,
         "prompt_format" : "<|im_start|>user\n{{prompt}}\n<|im_end|>\n<|im_start|>assistant\n",
         "top_k" : 5,
@@ -355,6 +365,7 @@
         "developer_url": "https://erichartford.com/",
         "file_size": 2728,
         "context" : 16384,
+        "max_context" : 16384,
         "temp" : 0.6,
         "prompt_format" : "<|im_start|>user\n{{prompt}}\n<|im_end|>\n<|im_start|>assistant\n",
         "top_k" : 5,
@@ -372,5 +383,40 @@
         "add_bos_token": true,
         "add_eos_token": false,
         "parse_special_tokens": true
+   },
+   {
+        "id": "WizardLM-2-7B.Q3_K_M",
+        "model_title": "WizardLM-2 7B",
+        "model_file": "WizardLM-2-7B.Q3_K_M.gguf",
+        "model_url": "https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/WizardLM-2-7B.Q3_K_M.gguf?download=true",
+        "model_info_url": "https://huggingface.co/MaziyarPanahi/WizardLM-2-7B-GGUF",
+        "model_avatar": "logo_phi",
+        "model_intention": "It's a state-of-the-art large language model with improved performance on complex chat, multilingual, reasoning and agent.",
+        "model_license": "license_apache2.txt",
+        "model_license_info": "APACHE LICENSE, VERSION 2.0",
+        "model_license_url": "https://www.apache.org/licenses/LICENSE-2.0",
+        "model_description": "The WizardLM-2 is one of the next generation state-of-the-art large language models, which have improved performance on complex chat, multilingual, reasoning and agent.",
+        "developer": "Eric Hartford and Cognitive Computations",
+        "developer_url": "https://huggingface.co/collections/microsoft/wizardlm-661d403f71e6c8257dbd598a",
+        "file_size": 3519,
+        "context" : 32768,
+        "max_context" : 32768,
+        "temp" : 0.6,
+        "prompt_format" : "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. \nUSER: {{prompt}}\nASSISTANT: ",
+        "top_k" : 5,
+        "top_p" : 0.9,
+        "model_inference" : "llama",
+        "n_batch" : 10,
+        "template_name" : "chatml",
+        "is_ready": true,
+        "is_internal": false,
+        "use_metal": true,
+        "mlock": false,
+        "mmap": true,
+        "repeat_last_n": 64,
+        "repeat_penalty": 1.2,
+        "add_bos_token": true,
+        "add_eos_token": false,
+        "parse_special_tokens": true
    }
 ]