Qwen2.5-72b-BNK-FP8 / config.json
Imran1's picture
Upload folder using huggingface_hub
030c3a4 verified
raw
history blame
1.9 kB
{
"_name_or_path": "/root/.cache/huggingface/hub/models--Imran1--Qwen2.5-72b-bnk/snapshots/4e0746df5737db1601b631438a14f01c399a7eb2",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 29568,
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": "memoryless",
"observer_kwargs": {},
"strategy": "token",
"symmetric": true,
"type": "float"
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "minmax",
"observer_kwargs": {},
"strategy": "channel",
"symmetric": true,
"type": "float"
}
}
},
"format": "float-quantized",
"global_compression_ratio": 1.2405357506583745,
"ignore": [
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed"
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}