Upload config.json with huggingface_hub
Browse files- config.json +45 -0
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Glm4MoeLiteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"pad_token_id": 154820,
|
| 8 |
+
"eos_token_id": [
|
| 9 |
+
154820,
|
| 10 |
+
154827,
|
| 11 |
+
154829
|
| 12 |
+
],
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 2048,
|
| 15 |
+
"intermediate_size": 10240,
|
| 16 |
+
"max_position_embeddings": 202752,
|
| 17 |
+
"model_type": "glm4_moe_lite",
|
| 18 |
+
"moe_intermediate_size": 1536,
|
| 19 |
+
"topk_method": "noaux_tc",
|
| 20 |
+
"norm_topk_prob": true,
|
| 21 |
+
"num_attention_heads": 20,
|
| 22 |
+
"n_group": 1,
|
| 23 |
+
"topk_group": 1,
|
| 24 |
+
"n_routed_experts": 64,
|
| 25 |
+
"n_shared_experts": 1,
|
| 26 |
+
"routed_scaling_factor": 1.8,
|
| 27 |
+
"num_experts_per_tok": 4,
|
| 28 |
+
"first_k_dense_replace": 1,
|
| 29 |
+
"num_hidden_layers": 47,
|
| 30 |
+
"num_key_value_heads": 20,
|
| 31 |
+
"num_nextn_predict_layers": 1,
|
| 32 |
+
"partial_rotary_factor": 1.0,
|
| 33 |
+
"rms_norm_eps": 1e-05,
|
| 34 |
+
"rope_scaling": null,
|
| 35 |
+
"rope_theta": 1000000,
|
| 36 |
+
"tie_word_embeddings": false,
|
| 37 |
+
"dtype": "bfloat16",
|
| 38 |
+
"transformers_version": "5.0.0rc0",
|
| 39 |
+
"q_lora_rank": 768,
|
| 40 |
+
"kv_lora_rank": 512,
|
| 41 |
+
"qk_nope_head_dim": 192,
|
| 42 |
+
"qk_rope_head_dim": 64,
|
| 43 |
+
"v_head_dim": 256,
|
| 44 |
+
"vocab_size": 154880
|
| 45 |
+
}
|