GLM-4.7-Flash-FP8 / config.json
mratsim's picture
Upload folder using huggingface_hub
3dffbf6 verified
{
"architectures": [
"Glm4MoeLiteForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": [
154820,
154827,
154829
],
"first_k_dense_replace": 1,
"hidden_act": "silu",
"hidden_size": 2048,
"intermediate_size": 10240,
"kv_lora_rank": 512,
"max_position_embeddings": 202752,
"model_type": "glm4_moe_lite",
"moe_intermediate_size": 1536,
"n_group": 1,
"n_routed_experts": 64,
"n_shared_experts": 1,
"norm_topk_prob": true,
"num_attention_heads": 20,
"num_experts_per_tok": 4,
"num_hidden_layers": 47,
"num_key_value_heads": 20,
"num_nextn_predict_layers": 1,
"pad_token_id": 154820,
"partial_rotary_factor": 1.0,
"q_lora_rank": 768,
"qk_nope_head_dim": 192,
"qk_rope_head_dim": 64,
"quantization_config": {
"config_groups": {
"FP8_BLOCK": {
"format": "float-quantized",
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": 128,
"num_bits": 8,
"observer": null,
"observer_kwargs": {},
"strategy": "group",
"symmetric": true,
"type": "float"
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"block_structure": [
128,
128
],
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "static_minmax",
"observer_kwargs": {},
"strategy": "block",
"symmetric": true,
"type": "float"
}
}
},
"format": "float-quantized",
"global_compression_ratio": null,
"ignore": [
"lm_head",
"re:.*mlp\\.gate$",
"re:.*kv_a_proj_with_mqa$",
"re:.*q_a_proj$",
"model.embed_tokens"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {},
"transform_config": {},
"version": "0.13.0"
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"routed_scaling_factor": 1.8,
"tie_word_embeddings": false,
"topk_group": 1,
"topk_method": "noaux_tc",
"transformers_version": "5.0.0rc0",
"v_head_dim": 256,
"vocab_size": 154880
}