SpiridonSunRotator's picture
Uploaded Phi-3-mini-128k-instruct with AQLM 1x16 quantization
fdcdceb verified
{
"_name_or_path": "/slot/sandbox/j/_tmp/dataf4a0rh67",
"architectures": [
"Phi3ForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"model_type": "phi3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"quantization_config": {
"in_group_size": 8,
"linear_weights_not_to_quantize": [
"model.layers.0.input_layernorm.weight",
"model.layers.0.post_attention_layernorm.weight",
"model.layers.1.input_layernorm.weight",
"model.layers.1.post_attention_layernorm.weight",
"model.layers.2.input_layernorm.weight",
"model.layers.2.post_attention_layernorm.weight",
"model.layers.3.input_layernorm.weight",
"model.layers.3.post_attention_layernorm.weight",
"model.layers.4.input_layernorm.weight",
"model.layers.4.post_attention_layernorm.weight",
"model.layers.5.input_layernorm.weight",
"model.layers.5.post_attention_layernorm.weight",
"model.layers.6.input_layernorm.weight",
"model.layers.6.post_attention_layernorm.weight",
"model.layers.7.input_layernorm.weight",
"model.layers.7.post_attention_layernorm.weight",
"model.layers.8.input_layernorm.weight",
"model.layers.8.post_attention_layernorm.weight",
"model.layers.9.input_layernorm.weight",
"model.layers.9.post_attention_layernorm.weight",
"model.layers.10.input_layernorm.weight",
"model.layers.10.post_attention_layernorm.weight",
"model.layers.11.input_layernorm.weight",
"model.layers.11.post_attention_layernorm.weight",
"model.layers.12.input_layernorm.weight",
"model.layers.12.post_attention_layernorm.weight",
"model.layers.13.input_layernorm.weight",
"model.layers.13.post_attention_layernorm.weight",
"model.layers.14.input_layernorm.weight",
"model.layers.14.post_attention_layernorm.weight",
"model.layers.15.input_layernorm.weight",
"model.layers.15.post_attention_layernorm.weight",
"model.layers.16.input_layernorm.weight",
"model.layers.16.post_attention_layernorm.weight",
"model.layers.17.input_layernorm.weight",
"model.layers.17.post_attention_layernorm.weight",
"model.layers.18.input_layernorm.weight",
"model.layers.18.post_attention_layernorm.weight",
"model.layers.19.input_layernorm.weight",
"model.layers.19.post_attention_layernorm.weight",
"model.layers.20.input_layernorm.weight",
"model.layers.20.post_attention_layernorm.weight",
"model.layers.21.input_layernorm.weight",
"model.layers.21.post_attention_layernorm.weight",
"model.layers.22.input_layernorm.weight",
"model.layers.22.post_attention_layernorm.weight",
"model.layers.23.input_layernorm.weight",
"model.layers.23.post_attention_layernorm.weight",
"model.layers.24.input_layernorm.weight",
"model.layers.24.post_attention_layernorm.weight",
"model.layers.25.input_layernorm.weight",
"model.layers.25.post_attention_layernorm.weight",
"model.layers.26.input_layernorm.weight",
"model.layers.26.post_attention_layernorm.weight",
"model.layers.27.input_layernorm.weight",
"model.layers.27.post_attention_layernorm.weight",
"model.layers.28.input_layernorm.weight",
"model.layers.28.post_attention_layernorm.weight",
"model.layers.29.input_layernorm.weight",
"model.layers.29.post_attention_layernorm.weight",
"model.layers.30.input_layernorm.weight",
"model.layers.30.post_attention_layernorm.weight",
"model.layers.31.input_layernorm.weight",
"model.layers.31.post_attention_layernorm.weight",
"model.embed_tokens.weight",
"model.norm.weight",
"lm_head.weight"
],
"nbits_per_codebook": 16,
"num_codebooks": 1,
"out_group_size": 1,
"quant_method": "aqlm"
},
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"long_factor": [
1.0299999713897705,
1.0499999523162842,
1.0499999523162842,
1.0799999237060547,
1.2299998998641968,
1.2299998998641968,
1.2999999523162842,
1.4499999284744263,
1.5999999046325684,
1.6499998569488525,
1.8999998569488525,
2.859999895095825,
3.68999981880188,
5.419999599456787,
5.489999771118164,
5.489999771118164,
9.09000015258789,
11.579999923706055,
15.65999984741211,
15.769999504089355,
15.789999961853027,
18.360000610351562,
21.989999771118164,
23.079999923706055,
30.009998321533203,
32.35000228881836,
32.590003967285156,
35.56000518798828,
39.95000457763672,
53.840003967285156,
56.20000457763672,
57.95000457763672,
59.29000473022461,
59.77000427246094,
59.920005798339844,
61.190006256103516,
61.96000671386719,
62.50000762939453,
63.3700065612793,
63.48000717163086,
63.48000717163086,
63.66000747680664,
63.850006103515625,
64.08000946044922,
64.760009765625,
64.80001068115234,
64.81001281738281,
64.81001281738281
],
"short_factor": [
1.05,
1.05,
1.05,
1.1,
1.1,
1.1500000000000001,
1.2000000000000002,
1.2500000000000002,
1.3000000000000003,
1.3500000000000003,
1.5000000000000004,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.0500000000000007,
2.0500000000000007,
2.0500000000000007,
2.1000000000000005,
2.1000000000000005,
2.1000000000000005,
2.1500000000000004,
2.1500000000000004,
2.3499999999999996,
2.549999999999999,
2.5999999999999988,
2.5999999999999988,
2.7499999999999982,
2.849999999999998,
2.849999999999998,
2.9499999999999975
],
"type": "su"
},
"rope_theta": 10000.0,
"sliding_window": 262144,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.40.0.dev0",
"use_cache": true,
"vocab_size": 32064
}