JingyiLiu commited on
Commit
3a61d40
1 Parent(s): e74aa9e

Upload 4 files

Browse files
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 256,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "dense",
25
+ "v_proj",
26
+ "fc1",
27
+ "fc2",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c246dc6a82412069e11f1be9c7d35dbc1dc0cb726939b3a713cbdd6a8df110
3
+ size 226531176
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-1_5",
3
+ "architectures": [
4
+ "PhiForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": 50256,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 50256,
14
+ "freeze_mm_mlp_adapter": false,
15
+ "hidden_act": "gelu_new",
16
+ "hidden_size": 2048,
17
+ "image_aspect_ratio": "pad",
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 2048,
22
+ "mm_hidden_size": 1152,
23
+ "mm_projector_lr": null,
24
+ "mm_projector_type": "ppc_14_7_1",
25
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
26
+ "model_type": "colongpt-phi",
27
+ "num_attention_heads": 32,
28
+ "num_hidden_layers": 24,
29
+ "num_key_value_heads": 32,
30
+ "partial_rotary_factor": 0.5,
31
+ "qk_layernorm": false,
32
+ "resid_pdrop": 0.0,
33
+ "rope_scaling": null,
34
+ "rope_theta": 10000.0,
35
+ "tie_word_embeddings": false,
36
+ "tokenizer_model_max_length": 2048,
37
+ "tokenizer_padding_side": "right",
38
+ "torch_dtype": "float16",
39
+ "transformers_version": "4.42.3",
40
+ "tune_mm_mlp_adapter": true,
41
+ "unfreeze_vision_tower": false,
42
+ "use_cache": true,
43
+ "use_mm_proj": true,
44
+ "use_s2": false,
45
+ "vocab_size": 51200
46
+ }
non_lora_trainables.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e498e276f6546a9826cb4b37359aba58cbd7cd851ca7ee7e85f0284055cf0689
3
+ size 88619904