75 lines
2.0 KiB
JSON
75 lines
2.0 KiB
JSON
{
|
|
"_name_or_path": "/root/.cache/huggingface/hub/models--google--gemma-2-9b-it/snapshots/4efc01a1a58107f8c7f68027f5d8e475dfc34a6f",
|
|
"architectures": [
|
|
"Gemma2ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"attn_logit_softcapping": 50.0,
|
|
"bos_token_id": 2,
|
|
"cache_implementation": "hybrid",
|
|
"eos_token_id": 1,
|
|
"final_logit_softcapping": 30.0,
|
|
"head_dim": 256,
|
|
"hidden_act": "gelu_pytorch_tanh",
|
|
"hidden_activation": "gelu_pytorch_tanh",
|
|
"hidden_size": 3584,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 14336,
|
|
"max_position_embeddings": 8192,
|
|
"model_type": "gemma2",
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 42,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 0,
|
|
"query_pre_attn_scalar": 256,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_theta": 10000.0,
|
|
"sliding_window": 4096,
|
|
"sliding_window_size": 4096,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.44.0",
|
|
"use_cache": true,
|
|
"vocab_size": 256000,
|
|
"quantization_config": {
|
|
"config_groups": {
|
|
"group_0": {
|
|
"input_activations": {
|
|
"block_structure": null,
|
|
"dynamic": true,
|
|
"group_size": null,
|
|
"num_bits": 8,
|
|
"observer": "memoryless",
|
|
"observer_kwargs": {},
|
|
"strategy": "token",
|
|
"symmetric": true,
|
|
"type": "int"
|
|
},
|
|
"output_activations": null,
|
|
"targets": [
|
|
"Linear"
|
|
],
|
|
"weights": {
|
|
"block_structure": null,
|
|
"dynamic": false,
|
|
"group_size": null,
|
|
"num_bits": 8,
|
|
"observer": "minmax",
|
|
"observer_kwargs": {},
|
|
"strategy": "channel",
|
|
"symmetric": true,
|
|
"type": "int"
|
|
}
|
|
}
|
|
},
|
|
"format": "int-quantized",
|
|
"global_compression_ratio": 1.2111813093687274,
|
|
"ignore": [
|
|
"lm_head"
|
|
],
|
|
"kv_cache_scheme": null,
|
|
"quant_method": "compressed-tensors",
|
|
"quantization_status": "compressed"
|
|
}
|
|
}
|