Update config.json
Browse files- config.json +28 -73
config.json
CHANGED
|
@@ -1,76 +1,31 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": true,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"eos_token_id": 200002,
|
| 8 |
-
"experts_per_token": 4,
|
| 9 |
-
"head_dim": 64,
|
| 10 |
-
"hidden_act": "silu",
|
| 11 |
-
"hidden_size": 2880,
|
| 12 |
-
"initial_context_length": 4096,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 2880,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"sliding_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"sliding_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"sliding_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"sliding_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"sliding_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"sliding_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"sliding_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"sliding_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"sliding_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"sliding_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"sliding_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"sliding_attention",
|
| 39 |
-
"full_attention"
|
| 40 |
-
],
|
| 41 |
-
"max_position_embeddings": 131072,
|
| 42 |
-
"model_type": "gpt_oss",
|
| 43 |
-
"num_attention_heads": 64,
|
| 44 |
-
"num_experts_per_tok": 4,
|
| 45 |
-
"num_hidden_layers": 24,
|
| 46 |
-
"num_key_value_heads": 8,
|
| 47 |
-
"num_local_experts": 32,
|
| 48 |
-
"output_router_logits": false,
|
| 49 |
-
"pad_token_id": 199999,
|
| 50 |
-
"quantization_config": {
|
| 51 |
-
"modules_to_not_convert": [
|
| 52 |
-
"model.layers.*.self_attn",
|
| 53 |
-
"model.layers.*.mlp.router",
|
| 54 |
-
"model.embed_tokens",
|
| 55 |
-
"lm_head"
|
| 56 |
],
|
| 57 |
-
"
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BitNetForCausalLM"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_bitnet.BitNetConfig",
|
| 7 |
+
"AutoModelForCausalLM": "modeling_bitnet.BitNetForCausalLM"
|
| 8 |
+
},
|
| 9 |
+
"bos_token_id": 128000,
|
| 10 |
+
"eos_token_id": 128001,
|
| 11 |
+
"hidden_act": "relu2",
|
| 12 |
+
"hidden_size": 2560,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 6912,
|
| 15 |
+
"max_position_embeddings": 4096,
|
| 16 |
+
"model_type": "bitnet",
|
| 17 |
+
"rms_norm_eps": 1e-05,
|
| 18 |
+
"num_attention_heads": 20,
|
| 19 |
+
"num_hidden_layers": 30,
|
| 20 |
+
"num_key_value_heads": 5,
|
| 21 |
+
"rope_theta": 500000.0,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 128256,
|
| 26 |
+
"quantization_config": {
|
| 27 |
+
"quant_method": "bitnet",
|
| 28 |
+
"linear_class": "autobitlinear",
|
| 29 |
+
"quantization_mode": "offline"
|
| 30 |
+
}
|
| 31 |
}
|