Upload config.json with huggingface_hub
Browse files- config.json +48 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Glm4MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 151329,
|
| 8 |
+
"first_k_dense_replace": 1,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 10944,
|
| 14 |
+
"max_position_embeddings": 131072,
|
| 15 |
+
"model_type": "glm4_moe",
|
| 16 |
+
"moe_intermediate_size": 1408,
|
| 17 |
+
"n_group": 1,
|
| 18 |
+
"n_routed_experts": 96,
|
| 19 |
+
"n_shared_experts": 1,
|
| 20 |
+
"norm_topk_prob": true,
|
| 21 |
+
"num_attention_heads": 96,
|
| 22 |
+
"num_experts_per_tok": 8,
|
| 23 |
+
"num_hidden_layers": 46,
|
| 24 |
+
"num_key_value_heads": 8,
|
| 25 |
+
"num_nextn_predict_layers": 1,
|
| 26 |
+
"pad_token_id": 151365,
|
| 27 |
+
"partial_rotary_factor": 0.5,
|
| 28 |
+
"quantization": {
|
| 29 |
+
"group_size": 64,
|
| 30 |
+
"bits": 8
|
| 31 |
+
},
|
| 32 |
+
"quantization_config": {
|
| 33 |
+
"group_size": 64,
|
| 34 |
+
"bits": 8
|
| 35 |
+
},
|
| 36 |
+
"rms_norm_eps": 1e-05,
|
| 37 |
+
"rope_scaling": null,
|
| 38 |
+
"rope_theta": 1000000,
|
| 39 |
+
"routed_scaling_factor": 1.0,
|
| 40 |
+
"tie_word_embeddings": false,
|
| 41 |
+
"topk_group": 1,
|
| 42 |
+
"torch_dtype": "bfloat16",
|
| 43 |
+
"transformers_version": "4.56.2",
|
| 44 |
+
"unsloth_version": "2025.10.7",
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"use_qk_norm": false,
|
| 47 |
+
"vocab_size": 151552
|
| 48 |
+
}
|