Spaces:
Sleeping
Sleeping
File size: 6,704 Bytes
0efb0d1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 | """
Priority Models List - 70 high-signal models for initial registry
This list is used programmatically by the ingestion pipeline
"""
# Tier 1: Frontier Closed Models
FRONTIER_CLOSED = {
"OpenAI": [
"GPT-3",
"GPT-3.5",
"GPT-4",
"GPT-4 Turbo",
"GPT-4o",
"GPT-4.1",
"GPT-4.1 Preview",
"GPT-4.1 Mini",
"o1",
"o3",
],
"Anthropic": [
"Claude 1",
"Claude 2",
"Claude 2.1",
"Claude 3 Haiku",
"Claude 3 Sonnet",
"Claude 3 Opus",
"Claude 3.5 Haiku",
"Claude 3.5 Sonnet",
"Claude 3.5 Opus",
],
"Google DeepMind": [
"PaLM",
"PaLM-2",
"Gemini 1.0 Nano",
"Gemini 1.0 Pro",
"Gemini 1.0 Ultra",
"Gemini 1.5 Flash",
"Gemini 1.5 Pro",
"Gemini 1.5 Ultra",
"Gemini 2.0",
"Gemini Next",
],
}
# Tier 1B: Major Open-Weight Models
OPEN_WEIGHT = {
"Meta": [
"Llama-1-7B",
"Llama-1-13B",
"Llama-1-30B",
"Llama-1-65B",
"Llama-2-7B",
"Llama-2-13B",
"Llama-2-70B",
"Llama-3-8B",
"Llama-3-70B",
"Llama-3.1-8B",
"Llama-3.1-70B",
"Llama-3.1-405B",
],
"Mistral AI": [
"Mistral-7B",
"Mixtral-8x7B",
"Mixtral-8x22B",
"Mistral Nemo",
"Mistral Small",
"Mistral Medium",
"Mistral Large",
],
"xAI": [
"Grok-1",
"Grok-1.5",
"Grok-1.5 Vision",
"Grok-2",
],
}
# Tier 2: Chinese Frontier Labs
CHINESE_FRONTIER = {
"Alibaba / Qwen": [
"Qwen-1",
"Qwen-1.5",
"Qwen-2-7B",
"Qwen-2-57B",
"Qwen-2-70B",
"Qwen-2.5",
"Qwen-VL",
],
"DeepSeek": [
"DeepSeek LLM",
"DeepSeek V2",
"DeepSeek V3",
"DeepSeek Coder",
],
"Baidu / ERNIE": [
"ERNIE 3.0",
"ERNIE 4.0",
"ERNIE 4.0 Turbo",
],
"SenseTime": [
"SenseNova 5.0",
],
"Other Chinese": [
"Baichuan-2-7B",
"Baichuan-2-13B",
"Baichuan-3",
"Yi-34B",
"Yi-1.5",
],
}
# Tier 3: Regional Open Models
REGIONAL_OPEN = {
"Middle East": [
"Falcon-7B",
"Falcon-40B",
"Falcon-180B",
],
"Korea": [
"Exaone-2.0",
],
"Japan": [
"NICT LLM",
"Sakana",
],
"EU / UK": [
"BLOOM-560B",
"BLOOMZ",
"T5-XXL",
"OPT-175B",
"Gopher",
"Chinchilla",
"U-PALM",
],
}
def get_all_priority_models() -> list[dict]:
"""
Returns a flat list of all priority models with provider information
Returns:
List of dicts with 'model_id', 'provider', 'tier', 'family' keys
"""
models = []
# Tier 1: Frontier Closed
for provider, model_list in FRONTIER_CLOSED.items():
for model in model_list:
models.append({
"model_id": model,
"provider": provider,
"tier": "Tier 1: Frontier Closed",
"family": _extract_family(model, provider),
})
# Tier 1B: Open Weight
for provider, model_list in OPEN_WEIGHT.items():
for model in model_list:
models.append({
"model_id": model,
"provider": provider,
"tier": "Tier 1B: Open Weight",
"family": _extract_family(model, provider),
})
# Tier 2: Chinese Frontier
for provider, model_list in CHINESE_FRONTIER.items():
for model in model_list:
models.append({
"model_id": model,
"provider": provider,
"tier": "Tier 2: Chinese Frontier",
"family": _extract_family(model, provider),
})
# Tier 3: Regional Open
for provider, model_list in REGIONAL_OPEN.items():
for model in model_list:
models.append({
"model_id": model,
"provider": provider,
"tier": "Tier 3: Regional Open",
"family": _extract_family(model, provider),
})
return models
def _extract_family(model_id: str, provider: str) -> str:
"""Extract model family from model ID"""
# GPT family
if "GPT" in model_id:
if "GPT-4" in model_id:
return "GPT-4"
elif "GPT-3" in model_id:
return "GPT-3"
return "GPT"
# Claude family
if "Claude" in model_id:
if "3.5" in model_id:
return "Claude 3.5"
elif "3" in model_id:
return "Claude 3"
elif "2" in model_id:
return "Claude 2"
return "Claude"
# Gemini family
if "Gemini" in model_id:
if "2.0" in model_id or "Next" in model_id:
return "Gemini 2.0"
elif "1.5" in model_id:
return "Gemini 1.5"
return "Gemini 1.0"
# Llama family
if "Llama" in model_id:
if "3.1" in model_id:
return "Llama 3.1"
elif "3" in model_id:
return "Llama 3"
elif "2" in model_id:
return "Llama 2"
return "Llama 1"
# Qwen family
if "Qwen" in model_id:
if "2.5" in model_id:
return "Qwen 2.5"
elif "2" in model_id:
return "Qwen 2"
elif "1.5" in model_id:
return "Qwen 1.5"
return "Qwen 1"
# Mistral/Mixtral
if "Mixtral" in model_id:
return "Mixtral"
if "Mistral" in model_id:
return "Mistral"
# Grok
if "Grok" in model_id:
return "Grok"
# DeepSeek
if "DeepSeek" in model_id:
return "DeepSeek"
# ERNIE
if "ERNIE" in model_id:
return "ERNIE"
# Falcon
if "Falcon" in model_id:
return "Falcon"
# Default: use provider as family
return provider
def get_model_count() -> int:
"""Get total count of priority models"""
return len(get_all_priority_models())
if __name__ == "__main__":
models = get_all_priority_models()
print(f"Total priority models: {len(models)}")
print("\nBreakdown by tier:")
from collections import Counter
tier_counts = Counter(m["tier"] for m in models)
for tier, count in tier_counts.items():
print(f" {tier}: {count}")
print("\nBreakdown by provider:")
provider_counts = Counter(m["provider"] for m in models)
for provider, count in provider_counts.most_common():
print(f" {provider}: {count}")
|