75 lines
2.0 KiB
JSON
75 lines
2.0 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "/nm/drive0/alexandre/cache/hub/models--meta-llama--Llama-2-7b-chat-hf/snapshots/f5db02db724555f92da89c216ac04704f23d4590",
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 4096,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 11008,
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 32,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float16",
|
||
|
|
"transformers_version": "4.42.3",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 32000,
|
||
|
|
"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": 1.2397987000162187,
|
||
|
|
"ignore": [
|
||
|
|
"lm_head"
|
||
|
|
],
|
||
|
|
"kv_cache_scheme": null,
|
||
|
|
"quant_method": "compressed-tensors",
|
||
|
|
"quantization_status": "frozen",
|
||
|
|
"sparsity_config": {
|
||
|
|
"format": "dense",
|
||
|
|
"global_sparsity": 1.2853574777183943,
|
||
|
|
"registry_requires_subclass": false,
|
||
|
|
"sparsity_structure": "unstructured"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|