File size: 4,802 Bytes
4537ca2
57f49ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4537ca2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45a40b2
4537ca2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45a40b2
4537ca2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
[
  {
    "id": "mlc-ai/Llama-3.1-8B-Instruct-q4f32_1-MLC",
    "name": "Llama 3.1 8B Instruct q4f32",
    "model_type": "llama",
    "architectures": ["llama"],
    "classification": "gen",
    "confidence": "high",
    "size_hint": "58Mb",
    "fetchStatus": "ok",
    "hasTokenizer": true,
    "hasOnnxModel": true,
    "isTransformersJsReady": true
  },
  {
    "id": "mlc-ai/gemma-2-9b-it-q4f16_1-MLC",
    "name": "Gemma 2 9B IT q4f16",
    "model_type": "gemma",
    "architectures": ["gemma"],
    "classification": "gen",
    "confidence": "high",
    "size_hint": "5Gb",
    "fetchStatus": "ok",
    "hasTokenizer": true,
    "hasOnnxModel": true,
    "isTransformersJsReady": true
  },
  {
    "id": "Xenova/llama2.c-stories15M",
    "name": "Llama2.c Stories 15M",
    "model_type": "llama",
    "architectures": ["llama"],
    "classification": "gen",
    "confidence": "high",
    "fetchStatus": "ok",
    "hasTokenizer": true,
    "hasOnnxModel": true,
    "isTransformersJsReady": true,
    "info": {
      "display_name": "Llama2.c Stories 15M (Xenova)",
      "params": "15M",
      "params_count": 15000000,
      "architecture": "LLaMA-family (tiny conversion for stories use via Xenova toolchain)",
      "context_window": 2048,
      "quantization": "likely float16/uint8/packed formats supported by Xenova runtime",
      "hf_url": "https://huggingface.co/Xenova/llama2.c-stories15M",
      "recommended_runtime": "transformers.js / Xenova runtime (wasm/webgpu)",
      "is_mobile_capable": true,
      "verified": false,
      "assumed": true,
      "notes": "Original curated metadata preserved; tokenizer/ONNX flags assumed for Xenova-converted tiny model."
    }
  },
  {
    "id": "Xenova/phi-3-mini-4k-instruct",
    "name": "phi-3-mini-4k-instruct",
    "model_type": "phi3",
    "architectures": ["phi3"],
    "classification": "gen",
    "confidence": "high",
    "fetchStatus": "ok",
    "hasTokenizer": true,
    "hasOnnxModel": true,
    "isTransformersJsReady": true,
    "info": {
      "display_name": "Phi-3 Mini 4k Instruct (Xenova)",
      "params": "mini (estimate)",
      "params_count": null,
      "architecture": "Phi family (Phi-3 mini conversion)",
      "context_window": 4096,
      "hf_url": "https://huggingface.co/Xenova/phi-3-mini-4k-instruct",
      "recommended_runtime": "transformers.js / Xenova runtime (wasm/webgpu)",
      "is_mobile_capable": true,
      "verified": false,
      "assumed": true,
      "notes": "Parameter count and asset layout should be verified against HF API."
    }
  },
  {
    "id": "Xenova/distilgpt2",
    "name": "distilgpt2",
    "model_type": "gpt2",
    "architectures": ["gpt2"],
    "classification": "gen",
    "confidence": "high",
    "fetchStatus": "ok",
    "hasTokenizer": true,
    "hasOnnxModel": true,
    "isTransformersJsReady": true,
    "info": {
      "display_name": "DistilGPT-2 (Xenova mirror)",
      "params": "≈82M",
      "params_count": 82000000,
      "architecture": "GPT-2 distilled",
      "context_window": 1024,
      "hf_url": "https://huggingface.co/Xenova/distilgpt2",
      "recommended_runtime": "transformers.js",
      "is_mobile_capable": true,
      "verified": false,
      "assumed": true
    }
  },
  {
    "id": "Xenova/gpt2",
    "name": "gpt2",
    "model_type": "gpt2",
    "architectures": ["gpt2"],
    "classification": "gen",
    "confidence": "high",
    "fetchStatus": "ok",
    "hasTokenizer": true,
    "hasOnnxModel": true,
    "size_hint": "500Mb",
    "isTransformersJsReady": true,
    "info": {
      "display_name": "GPT-2 (Xenova mirror)",
      "params": "117M (base)",
      "params_count": 117000000,
      "architecture": "GPT-2",
      "context_window": 1024,
      "hf_url": "https://huggingface.co/Xenova/gpt2",
      "recommended_runtime": "transformers.js",
      "is_mobile_capable": true,
      "verified": false,
      "assumed": true
    }
  },
  {
    "id": "Xenova/qwen-2.5-small-instruct",
    "name": "qwen-2.5-small-instruct",
    "model_type": "qwen",
    "architectures": ["qwen"],
    "classification": "gen",
    "confidence": "medium",
    "fetchStatus": "ok",
    "hasTokenizer": true,
    "hasOnnxModel": false,
    "isTransformersJsReady": false,
    "requiresAuth": true,
    "info": {
      "display_name": "Qwen-2.5 Small Instruct (Xenova mirror)",
      "params": "≈2.5B (estimate)",
      "params_count": null,
      "architecture": "Qwen family",
      "context_window": 8192,
      "hf_url": "https://huggingface.co/Xenova/qwen-2.5-small-instruct",
      "recommended_runtime": "Xenova runtime / transformers.js (quantized)",
      "is_mobile_capable": false,
      "verified": false,
      "assumed": true,
      "notes": "Marked conservatively as not transformers.js-ready / no ONNX in HF assets."
    }
  }
]