Spaces:

broadfield-dev
/

node_search

Sleeping

App Files Files Community

broadfield-dev commited on Jun 6

Commit

ad4a63a

verified ·

1 Parent(s): e38b58b

Update model_logic.py

Browse files

Files changed (1) hide show

model_logic.py +139 -65

model_logic.py CHANGED Viewed

@@ -38,7 +38,7 @@ API_URLS = {
 }
 # Structure: provider_key: { "default": "model_id", "models": {"Display Name": "model_id", ...} }
-MODELS_BY_PROVIDER = {
     "groq": {
         "default": "llama3-8b-8192",
         "models": {
@@ -46,75 +46,149 @@ MODELS_BY_PROVIDER = {
             "Llama 3 70B (Groq)": "llama3-70b-8192",
             "Mixtral 8x7B (Groq)": "mixtral-8x7b-32768",
             "Gemma 7B (Groq)": "gemma-7b-it",
         }
     },
     "openrouter": {
-         "default": "nousresearch/llama-3-8b-instruct", # Updated default
-         "models": {
-            "Nous Llama-3 8B Instruct (OpenRouter)": "nousresearch/llama-3-8b-instruct",
-            "Mistral 7B Instruct v0.3 (OpenRouter)": "mistralai/mistral-7b-instruct-v0.3", # v0.3 is newer
-            "Mistral 7B Instruct (Free/OpenRouter)": "mistralai/mistral-7b-instruct:free", # Keep free tier if distinct
-            "Gemma 2 9B Instruct (OpenRouter)": "google/gemma-2-9b-it", # Gemma 2
             "Gemma 7B Instruct (Free/OpenRouter)": "google/gemma-7b-it:free",
-            "Llama 3.1 8B Instruct (OpenRouter)": "meta-llama/llama-3.1-8b-instruct", # Llama 3.1
-            "Llama 3.1 70B Instruct (OpenRouter)": "meta-llama/llama-3.1-70b-instruct",
-            "OpenAI GPT-4o mini (OpenRouter)": "openai/gpt-4o-mini",
-            "OpenAI GPT-4o (OpenRouter)": "openai/gpt-4o",
-            "Claude 3.5 Sonnet (OpenRouter)": "anthropic/claude-3.5-sonnet",
-            "Mixtral 8x7B Instruct v0.1 (OpenRouter)": "mistralai/mixtral-8x7b-instruct", # Older Mixtral
-            "Qwen 2 72B Instruct (OpenRouter)": "qwen/qwen-2-72b-instruct",
-         }
     },
-     "togetherai": {
-         "default": "meta-llama/Llama-3-8b-chat-hf",
-         "models": {
-             "Llama 3 8B Chat (TogetherAI)": "meta-llama/Llama-3-8b-chat-hf",
-             "Llama 3 70B Chat (TogetherAI)": "meta-llama/Llama-3-70b-chat-hf",
-             "Mixtral 8x7B Instruct (TogetherAI)": "mistralai/Mixtral-8x7B-Instruct-v0.1",
-             "Gemma 7B Instruct (TogetherAI)": "google/gemma-7b-it",
-             "Qwen1.5-72B-Chat (TogetherAI)": "qwen/Qwen1.5-72B-Chat",
-         }
-     },
-     "google": {
-          "default": "gemini-1.5-flash-latest",
-          "models": {
-              "Gemini 1.5 Flash (Latest)": "gemini-1.5-flash-latest",
-              "Gemini 1.5 Pro (Latest)": "gemini-1.5-pro-latest",
-              # "Gemini 1.0 Pro": "gemini-pro" # Older model example
-          }
-     },
-     "cohere": {
-         "default": "command-r", # command-r is generally better than light
-         "models": {
-             "Command R (Cohere)": "command-r",
-             "Command R+ (Cohere)": "command-r-plus",
-             "Command Light (Cohere)": "command-light",
-         }
-     },
-     "huggingface": { # Direct HF Inference API is tricky for chat, often better via OpenRouter/TogetherAI
-         "default": "mistralai/Mistral-7B-Instruct-v0.2", # A common TGI compatible model
-         "models": {
-             "Mistral 7B Instruct v0.2 (HF Inf.)": "mistralai/Mistral-7B-Instruct-v0.2",
-             "Llama 3 8B Instruct (HF Inf.)": "meta-llama/Meta-Llama-3-8B-Instruct", # Ensure this specific ID is for TGI
-             # "Zephyr 7B Beta (H4/HF Inf.)": "HuggingFaceH4/zephyr-7b-beta", # Older model
-         }
-     },
-     "openai": {
-          "default": "gpt-4o-mini", # New default
-          "models": {
-              "GPT-4o (OpenAI)": "gpt-4o",
-              "GPT-4o mini (OpenAI)": "gpt-4o-mini",
-              "GPT-4 Turbo (OpenAI)": "gpt-4-turbo", # Refers to latest gpt-4-turbo variant
-              "GPT-3.5 Turbo (OpenAI)": "gpt-3.5-turbo", # Refers to latest gpt-3.5-turbo variant
-          }
-     },
-     "xai": { # Assuming xAI might expand model list
-          "default": "grok-1.5-flash", # Assuming Grok 1.5 flash is available
-          "models": {
-              "Grok 1.5 Flash (xAI)": "grok-1.5-flash",
-              # "Grok-1 (xAI)": "grok-1", # Older model
-          }
-     }
 }
 def _get_api_key(provider: str, ui_api_key_override: str = None) -> str | None:

 }
 # Structure: provider_key: { "default": "model_id", "models": {"Display Name": "model_id", ...} }
+{
     "groq": {
         "default": "llama3-8b-8192",
         "models": {
             "Llama 3 70B (Groq)": "llama3-70b-8192",
             "Mixtral 8x7B (Groq)": "mixtral-8x7b-32768",
             "Gemma 7B (Groq)": "gemma-7b-it",
+            "Gemma 2 9B (Groq)": "gemma-2-9b-it",
+            "Llama 3.1 8B (Groq)": "llama-3.1-8b-instruct",
+            "Llama 3.1 70B (Groq)": "llama-3.1-70b-instruct",
+            "Qwen 2 7B (Groq)": "qwen-2-7b-instruct",
+            "Qwen 2 72B (Groq)": "qwen-2-72b-instruct",
+            "Mistral 7B Instruct v0.3 (Groq)": "mistral-7b-instruct-v0.3",
+            "Falcon 7B (Groq)": "falcon-7b-instruct",
+            "Falcon 40B (Groq)": "falcon-40b-instruct",
+            "Grok 1.5 Flash (Groq) $": "grok-1.5-flash",
+            "Grok 3 (Groq) $$": "grok-3",
+            "DeepSeek R-1 7B (Groq)": "deepseek-r-1-7b-instruct"
         }
     },
     "openrouter": {
+        "default": "mistralai/mistral-7b-instruct:free",
+        "models": {
+            "Mistral 7B Instruct (Free/OpenRouter)": "mistralai/mistral-7b-instruct:free",
             "Gemma 7B Instruct (Free/OpenRouter)": "google/gemma-7b-it:free",
+            "Llama 3 8B Instruct (Free/OpenRouter)": "meta-llama/llama-3-8b-instruct:free",
+            "Nous Llama 3 8B Instruct (OpenRouter)": "nousresearch/llama-3-8b-instruct",
+            "Mistral 7B Instruct v0.3 (OpenRouter)": "mistralai/mistral-7b-instruct-v0.3",
+            "Gemma 2 9B Instruct (OpenRouter)": "google/gemma-2-9b-it",
+            "Llama 3.1 8B Instruct (OpenRouter)": "meta-llama/llama-3.1-8b-instruct",
+            "Qwen 2 7B Instruct (OpenRouter)": "qwen/qwen-2-7b-instruct",
+            "Falcon 7B Instruct (OpenRouter)": "tiiuae/falcon-7b-instruct",
+            "DeepSeek R-1 7B (OpenRouter)": "deepseek/r-1-7b-instruct",
+            "Llama 3.1 70B Instruct (OpenRouter) $": "meta-llama/llama-3.1-70b-instruct",
+            "Mixtral 8x7B Instruct v0.1 (OpenRouter) $": "mistralai/mixtral-8x7b-instruct",
+            "Qwen 2 72B Instruct (OpenRouter) $": "qwen/qwen-2-72b-instruct",
+            "OpenAI GPT-4o mini (OpenRouter) $$": "openai/gpt-4o-mini",
+            "OpenAI GPT-4o (OpenRouter) $$$": "openai/gpt-4o",
+            "Claude 3.5 Sonnet (OpenRouter) $$$": "anthropic/claude-3.5-sonnet"
+        }
+    },
+    "togetherai": {
+        "default": "meta-llama/Llama-3-8b-chat-hf",
+        "models": {
+            "Llama 3 8B Chat (TogetherAI)": "meta-llama/Llama-3-8b-chat-hf",
+            "Gemma 7B Instruct (TogetherAI)": "google/gemma-7b-it",
+            "Mistral 7B Instruct v0.2 (TogetherAI)": "mistralai/Mistral-7B-Instruct-v0.2",
+            "Qwen 2 7B Chat (TogetherAI)": "qwen/Qwen-2-7B-Chat",
+            "Falcon 7B Instruct (TogetherAI)": "tiiuae/falcon-7b-instruct",
+            "DeepSeek R-1 7B (TogetherAI)": "deepseek/r-1-7b-instruct",
+            "Llama 3.1 8B Instruct (TogetherAI)": "meta-llama/Llama-3.1-8b-instruct",
+            "Gemma 2 9B Instruct (TogetherAI)": "google/gemma-2-9b-it",
+            "Llama 3 70B Chat (TogetherAI) $": "meta-llama/Llama-3-70b-chat-hf",
+            "Mixtral 8x7B Instruct (TogetherAI) $": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+            "Qwen 2 72B Chat (TogetherAI) $": "qwen/Qwen-2-72B-Chat",
+            "Falcon 40B Instruct (TogetherAI) $": "tiiuae/falcon-40b-instruct",
+            "Llama 3.1 70B Instruct (TogetherAI) $$": "meta-llama/Llama-3.1-70b-instruct",
+            "Mistral 8x22B Instruct (TogetherAI) $$": "mistralai/Mixtral-8x22B-Instruct-v0.1",
+            "DeepSeek R-2 72B (TogetherAI) $$": "deepseek/r-2-72b-instruct",
+            "CodeLlama 34B Instruct (TogetherAI) $": "codellama/CodeLlama-34b-Instruct-hf"
+        }
     },
+    "google": {
+        "default": "gemini-1.5-flash-latest",
+        "models": {
+            "Gemini 1.5 Flash (Latest)": "gemini-1.5-flash-latest",
+            "Gemini 1.0 Pro": "gemini-pro",
+            "Gemma 7B Instruct": "gemma-7b-it",
+            "Gemma 2 9B Instruct": "gemma-2-9b-it",
+            "CodeGemma 7B": "codegemma-7b",
+            "Gemini 1.5 Pro (Latest) $": "gemini-1.5-pro-latest",
+            "Gemini 1.5 Flash 8B $": "gemini-1.5-flash-8b",
+            "Gemini 1.0 Ultra $$": "gemini-ultra",
+            "Gemini 1.5 Pro Experimental $$": "gemini-1.5-pro-exp",
+            "Gemini 1.5 Flash Experimental $$": "gemini-1.5-flash-exp",
+            "Gemini 1.5 Pro Reasoning $$": "gemini-1.5-pro-reasoning",
+            "Gemini 1.5 Flash Reasoning $$": "gemini-1.5-flash-reasoning",
+            "Gemini 1.5 Pro Vision $$": "gemini-1.5-pro-vision",
+            "Gemini 1.5 Flash Vision $$": "gemini-1.5-flash-vision",
+            "CodeGemma 7B Instruct $$": "codegemma-7b-instruct"
+        }
+    },
+    "cohere": {
+        "default": "command-r",
+        "models": {
+            "Command Light (Cohere)": "command-light",
+            "Command (Cohere)": "command",
+            "Command R (Cohere)": "command-r",
+            "Command R+ (Cohere) $": "command-r-plus",
+            "Classify (Cohere) $": "classify",
+            "Embed English v3.0 (Cohere) $": "embed-english-v3.0",
+            "Embed Multilingual v3.0 (Cohere) $": "embed-multilingual-v3.0",
+            "Command Nightly (Cohere) $": "command-nightly",
+            "Command R 08-2024 (Cohere) $": "command-r-08-2024",
+            "Command R+ 08-2024 (Cohere) $$": "command-r-plus-08-2024",
+            "Embed English Light v3.0 (Cohere) $": "embed-english-light-v3.0",
+            "Embed Multilingual Light v3.0 (Cohere) $": "embed-multilingual-light-v3.0",
+            "Command R 03-2024 (Cohere) $": "command-r-03-2024",
+            "Command Light Nightly (Cohere) $": "command-light-nightly",
+            "Classify v2 (Cohere) $$": "classify-v2"
+        }
+    },
+    "huggingface": {
+        "default": "mistralai/Mistral-7B-Instruct-v0.2",
+        "models": {
+            "Mistral 7B Instruct v0.2 (HF Inf.)": "mistralai/Mistral-7B-Instruct-v0.2",
+            "Llama 3 8B Instruct (HF Inf.)": "meta-llama/Meta-Llama-3-8B-Instruct",
+            "Gemma 7B Instruct (HF Inf.)": "google/gemma-7b-it",
+            "Zephyr 7B Beta (HF Inf.)": "HuggingFaceH4/zephyr-7b-beta",
+            "Qwen 2 7B Instruct (HF Inf.)": "qwen/Qwen-2-7B-Instruct",
+            "Falcon 7B Instruct (HF Inf.)": "tiiuae/falcon-7b-instruct",
+            "Mixtral 8x7B Instruct (HF Inf.)": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+            "Gemma 2 9B Instruct (HF Inf.)": "google/gemma-2-9b-it",
+            "Llama 3.1 8B Instruct (HF Inf.)": "meta-llama/Llama-3.1-8B-Instruct",
+            "DeepSeek R-1 7B (HF Inf.)": "deepseek/r-1-7b-instruct",
+            "Mistral 7B Instruct v0.3 (HF Inf.) $": "mistralai/Mistral-7B-Instruct-v0.3",
+            "Llama 3 70B Instruct (HF Inf.) $$": "meta-llama/Meta-Llama-3-70B-Instruct",
+            "Mixtral 8x22B Instruct (HF Inf.) $$": "mistralai/Mixtral-8x22B-Instruct-v0.1",
+            "Qwen 2 72B Instruct (HF Inf.) $$": "qwen/Qwen-2-72B-Instruct",
+            "Falcon 40B Instruct (HF Inf.) $$": "tiiuae/falcon-40b-instruct",
+            "CodeLlama 34B Instruct (HF Inf.) $": "codellama/CodeLlama-34b-Instruct-hf"
+        }
+    },
+    "openai": {
+        "default": "gpt-4o-mini",
+        "models": {
+            "GPT-3.5 Turbo (OpenAI)": "gpt-3.5-turbo",
+            "GPT-4o mini (OpenAI) $": "gpt-4o-mini",
+            "GPT-4 Turbo (OpenAI) $$": "gpt-4-turbo",
+            "GPT-4o (OpenAI) $$$": "gpt-4o",
+            "GPT-4 (OpenAI) $$$": "gpt-4",
+            "GPT-3.5 Turbo 0125 (OpenAI) $": "gpt-3.5-turbo-0125",
+            "GPT-4o 2024-05-13 (OpenAI) $$$": "gpt-4o-2024-05-13",
+            "GPT-4 Turbo Preview (OpenAI) $$": "gpt-4-turbo-preview",
+            "GPT-3.5 Turbo Instruct (OpenAI) $": "gpt-3.5-turbo-instruct",
+            "GPT-4 32k (OpenAI) $$$": "gpt-4-32k",
+            "GPT-4o mini 2024-07-18 (OpenAI) $": "gpt-4o-mini-2024-07-18",
+            "GPT-4 Vision Preview (OpenAI) $$$": "gpt-4-vision-preview",
+            "GPT-3.5 Turbo 1106 (OpenAI) $": "gpt-3.5-turbo-1106",
+            "GPT-4 0613 (OpenAI) $$$": "gpt-4-0613",
+            "GPT-4o 2024-08-08 (OpenAI) $$$": "gpt-4o-2024-08-08"
+        }
+    },
+    "xai": {
+        "default": "grok-1.5-flash",
+        "models": {
+            "Grok 1.5 Flash (xAI) $": "grok-1.5-flash",
+            "Grok 3 (xAI) $$": "grok-3"
+        }
+    }
 }
 def _get_api_key(provider: str, ui_api_key_override: str = None) -> str | None: