|
{ |
|
"_name_or_path": "/tmp/models/tmpw0aio329/tmp2wqtcss5", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 128000, |
|
"eos_token_id": [ |
|
128001, |
|
128008, |
|
128009 |
|
], |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 3072, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 8192, |
|
"max_position_embeddings": 131072, |
|
"mlp_bias": false, |
|
"model_type": "llama", |
|
"num_attention_heads": 24, |
|
"num_hidden_layers": 28, |
|
"num_key_value_heads": 8, |
|
"pad_token_id": 128004, |
|
"pretraining_tp": 1, |
|
"quantization_config": { |
|
"mlp.down_proj": { |
|
"offload_meta": false, |
|
"scale_quant_params": null, |
|
"weight_quant_params": { |
|
"axis": 0, |
|
"channel_wise": true, |
|
"group_size": 64, |
|
"nbits": 8, |
|
"optimize": true, |
|
"round_zero": false, |
|
"view_as_float": false |
|
}, |
|
"zero_quant_params": { |
|
"channel_wise": false, |
|
"group_size": null, |
|
"nbits": 8, |
|
"optimize": false |
|
} |
|
}, |
|
"mlp.gate_proj": { |
|
"offload_meta": false, |
|
"scale_quant_params": null, |
|
"weight_quant_params": { |
|
"axis": 0, |
|
"channel_wise": true, |
|
"group_size": 64, |
|
"nbits": 8, |
|
"optimize": true, |
|
"round_zero": false, |
|
"view_as_float": false |
|
}, |
|
"zero_quant_params": { |
|
"channel_wise": false, |
|
"group_size": null, |
|
"nbits": 8, |
|
"optimize": false |
|
} |
|
}, |
|
"mlp.up_proj": { |
|
"offload_meta": false, |
|
"scale_quant_params": null, |
|
"weight_quant_params": { |
|
"axis": 0, |
|
"channel_wise": true, |
|
"group_size": 64, |
|
"nbits": 8, |
|
"optimize": true, |
|
"round_zero": false, |
|
"view_as_float": false |
|
}, |
|
"zero_quant_params": { |
|
"channel_wise": false, |
|
"group_size": null, |
|
"nbits": 8, |
|
"optimize": false |
|
} |
|
}, |
|
"self_attn.k_proj": { |
|
"offload_meta": false, |
|
"scale_quant_params": null, |
|
"weight_quant_params": { |
|
"axis": 0, |
|
"channel_wise": true, |
|
"group_size": 64, |
|
"nbits": 8, |
|
"optimize": true, |
|
"round_zero": false, |
|
"view_as_float": false |
|
}, |
|
"zero_quant_params": { |
|
"channel_wise": false, |
|
"group_size": null, |
|
"nbits": 8, |
|
"optimize": false |
|
} |
|
}, |
|
"self_attn.o_proj": { |
|
"offload_meta": false, |
|
"scale_quant_params": null, |
|
"weight_quant_params": { |
|
"axis": 0, |
|
"channel_wise": true, |
|
"group_size": 64, |
|
"nbits": 8, |
|
"optimize": true, |
|
"round_zero": false, |
|
"view_as_float": false |
|
}, |
|
"zero_quant_params": { |
|
"channel_wise": false, |
|
"group_size": null, |
|
"nbits": 8, |
|
"optimize": false |
|
} |
|
}, |
|
"self_attn.q_proj": { |
|
"offload_meta": false, |
|
"scale_quant_params": null, |
|
"weight_quant_params": { |
|
"axis": 0, |
|
"channel_wise": true, |
|
"group_size": 64, |
|
"nbits": 8, |
|
"optimize": true, |
|
"round_zero": false, |
|
"view_as_float": false |
|
}, |
|
"zero_quant_params": { |
|
"channel_wise": false, |
|
"group_size": null, |
|
"nbits": 8, |
|
"optimize": false |
|
} |
|
}, |
|
"self_attn.v_proj": { |
|
"offload_meta": false, |
|
"scale_quant_params": null, |
|
"weight_quant_params": { |
|
"axis": 0, |
|
"channel_wise": true, |
|
"group_size": 64, |
|
"nbits": 8, |
|
"optimize": true, |
|
"round_zero": false, |
|
"view_as_float": false |
|
}, |
|
"zero_quant_params": { |
|
"channel_wise": false, |
|
"group_size": null, |
|
"nbits": 8, |
|
"optimize": false |
|
} |
|
} |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": { |
|
"factor": 32.0, |
|
"high_freq_factor": 4.0, |
|
"low_freq_factor": 1.0, |
|
"original_max_position_embeddings": 8192, |
|
"rope_type": "llama3" |
|
}, |
|
"rope_theta": 500000.0, |
|
"tie_word_embeddings": true, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.44.0", |
|
"unsloth_version": "2024.12.8", |
|
"use_cache": true, |
|
"vocab_size": 128256 |
|
} |
|
|