Upload config.json with huggingface_hub
Browse files- config.json +137 -0
config.json
ADDED
|
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 4,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Cohere2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 5,
|
| 9 |
+
"cache_implementation": "hybrid",
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 255001,
|
| 12 |
+
"head_dim": 128,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 12288,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 36864,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"sliding_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"sliding_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"sliding_attention",
|
| 68 |
+
"sliding_attention",
|
| 69 |
+
"sliding_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"sliding_attention",
|
| 72 |
+
"sliding_attention",
|
| 73 |
+
"sliding_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"sliding_attention",
|
| 76 |
+
"sliding_attention",
|
| 77 |
+
"sliding_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"sliding_attention",
|
| 80 |
+
"sliding_attention",
|
| 81 |
+
"sliding_attention",
|
| 82 |
+
"full_attention"
|
| 83 |
+
],
|
| 84 |
+
"logit_scale": 0.25,
|
| 85 |
+
"max_position_embeddings": 262144,
|
| 86 |
+
"model_type": "cohere2",
|
| 87 |
+
"num_attention_heads": 96,
|
| 88 |
+
"num_hidden_layers": 64,
|
| 89 |
+
"num_key_value_heads": 8,
|
| 90 |
+
"order_of_interleaved_layers": "local_attn_first",
|
| 91 |
+
"pad_token_id": 0,
|
| 92 |
+
"position_embedding_type": "rope_gptj",
|
| 93 |
+
"rope_scaling": null,
|
| 94 |
+
"rope_theta": 50000,
|
| 95 |
+
"rotary_pct": 1.0,
|
| 96 |
+
"sliding_window": 4096,
|
| 97 |
+
"sliding_window_pattern": 4,
|
| 98 |
+
"transformers_version": "4.57.6",
|
| 99 |
+
"unsloth_fixed": true,
|
| 100 |
+
"unsloth_version": "2025.3.19",
|
| 101 |
+
"use_cache": false,
|
| 102 |
+
"use_embedding_sharing": true,
|
| 103 |
+
"use_gated_activation": true,
|
| 104 |
+
"use_parallel_block": true,
|
| 105 |
+
"use_parallel_embedding": true,
|
| 106 |
+
"vocab_size": 256000,
|
| 107 |
+
"quantization_config": {
|
| 108 |
+
"config_groups": {
|
| 109 |
+
"group_0": {
|
| 110 |
+
"input_activations": {
|
| 111 |
+
"dynamic": true,
|
| 112 |
+
"num_bits": 4,
|
| 113 |
+
"type": "float",
|
| 114 |
+
"group_size": 16
|
| 115 |
+
},
|
| 116 |
+
"weights": {
|
| 117 |
+
"dynamic": false,
|
| 118 |
+
"num_bits": 4,
|
| 119 |
+
"type": "float",
|
| 120 |
+
"group_size": 16
|
| 121 |
+
},
|
| 122 |
+
"targets": [
|
| 123 |
+
"Linear"
|
| 124 |
+
]
|
| 125 |
+
}
|
| 126 |
+
},
|
| 127 |
+
"ignore": [
|
| 128 |
+
"lm_head"
|
| 129 |
+
],
|
| 130 |
+
"quant_algo": "NVFP4",
|
| 131 |
+
"producer": {
|
| 132 |
+
"name": "modelopt",
|
| 133 |
+
"version": "0.43.0"
|
| 134 |
+
},
|
| 135 |
+
"quant_method": "modelopt"
|
| 136 |
+
}
|
| 137 |
+
}
|