jerryzh168 commited on
Commit
6c7a204
·
verified ·
1 Parent(s): 038b223

Upload Phi3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +12 -7
  2. generation_config.json +1 -1
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -5,9 +5,9 @@
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "auto_map": {
8
- "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
9
- "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
10
- "AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
11
  },
12
  "bos_token_id": 199999,
13
  "embd_pdrop": 0.0,
@@ -29,12 +29,14 @@
29
  "pad_token_id": 199999,
30
  "partial_rotary_factor": 0.75,
31
  "quantization_config": {
 
32
  "modules_to_not_convert": null,
33
  "quant_method": "torchao",
34
  "quant_type": {
35
  "default": {
36
  "_data": {
37
  "group_size": 128,
 
38
  "layout": {
39
  "_data": {
40
  "inner_k_tiles": 8
@@ -42,18 +44,21 @@
42
  "_type": "TensorCoreTiledLayout",
43
  "_version": 1
44
  },
 
 
45
  "set_inductor_config": true,
46
- "use_hqq": true,
47
  "zero_point_domain": {
48
  "_data": "NONE",
49
  "_type": "ZeroPointDomain"
50
  }
51
  },
52
  "_type": "Int4WeightOnlyConfig",
53
- "_version": 1
54
  }
55
  },
56
- "quant_type_kwargs": {}
 
57
  },
58
  "resid_pdrop": 0.0,
59
  "rms_norm_eps": 1e-05,
@@ -164,7 +169,7 @@
164
  "sliding_window": 262144,
165
  "tie_word_embeddings": true,
166
  "torch_dtype": "bfloat16",
167
- "transformers_version": "4.52.0.dev0",
168
  "use_cache": true,
169
  "vocab_size": 200064
170
  }
 
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "auto_map": {
8
+ "AutoConfig": "configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
10
+ "AutoTokenizer": "Xenova/gpt-4o"
11
  },
12
  "bos_token_id": 199999,
13
  "embd_pdrop": 0.0,
 
29
  "pad_token_id": 199999,
30
  "partial_rotary_factor": 0.75,
31
  "quantization_config": {
32
+ "include_input_output_embeddings": false,
33
  "modules_to_not_convert": null,
34
  "quant_method": "torchao",
35
  "quant_type": {
36
  "default": {
37
  "_data": {
38
  "group_size": 128,
39
+ "int4_choose_qparams_algorithm": "hqq",
40
  "layout": {
41
  "_data": {
42
  "inner_k_tiles": 8
 
44
  "_type": "TensorCoreTiledLayout",
45
  "_version": 1
46
  },
47
+ "packing_format": "tile_packed_to_4d",
48
+ "preserve_zero": null,
49
  "set_inductor_config": true,
50
+ "use_hqq": false,
51
  "zero_point_domain": {
52
  "_data": "NONE",
53
  "_type": "ZeroPointDomain"
54
  }
55
  },
56
  "_type": "Int4WeightOnlyConfig",
57
+ "_version": 2
58
  }
59
  },
60
+ "quant_type_kwargs": {},
61
+ "untie_embedding_weights": false
62
  },
63
  "resid_pdrop": 0.0,
64
  "rms_norm_eps": 1e-05,
 
169
  "sliding_window": 262144,
170
  "tie_word_embeddings": true,
171
  "torch_dtype": "bfloat16",
172
+ "transformers_version": "4.55.4",
173
  "use_cache": true,
174
  "vocab_size": 200064
175
  }
generation_config.json CHANGED
@@ -6,5 +6,5 @@
6
  199999
7
  ],
8
  "pad_token_id": 199999,
9
- "transformers_version": "4.52.0.dev0"
10
  }
 
6
  199999
7
  ],
8
  "pad_token_id": 199999,
9
+ "transformers_version": "4.55.4"
10
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d8e3b9096abe58a1092e2f5f53e88916716a23d0e4942bb5aff7fa883d88f33
3
- size 2941004562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99cad594e45263155d3a7b076d7672304348d1c0132eed39a02fdc5d09efc7dd
3
+ size 2940988651