Update model
Browse files- adapter_config.json +6 -4
- adapter_model.safetensors +2 -2
- config.json +6 -2
- non_lora_trainables.bin +1 -1
- trainer_state.json +0 -0
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -19,10 +19,12 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"dense",
|
23 |
"fc2",
|
24 |
-
"
|
25 |
-
"fc1"
|
|
|
|
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
|
|
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,
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"fc2",
|
23 |
+
"q_proj",
|
24 |
+
"fc1",
|
25 |
+
"v_proj",
|
26 |
+
"dense",
|
27 |
+
"k_proj"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM"
|
30 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0336e2f9f1ed41fec4766e0760643953eec093dc7f22d0c986bf5a0a8714c8c
|
3 |
+
size 226531176
|
config.json
CHANGED
@@ -4,6 +4,10 @@
|
|
4 |
"PhiForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
7 |
"bos_token_id": 50256,
|
8 |
"embd_pdrop": 0.0,
|
9 |
"eos_token_id": 50256,
|
@@ -18,13 +22,12 @@
|
|
18 |
"mm_hidden_size": 1024,
|
19 |
"mm_projector_lr": 2e-05,
|
20 |
"mm_projector_type": "mlp2x_gelu",
|
21 |
-
"mm_vision_select_feature": "patch",
|
22 |
"mm_vision_tower": "/path/to/EVA02_CLIP_L_336_psz14_s6B.pt",
|
23 |
"model_type": "bunny-phi",
|
24 |
"num_attention_heads": 32,
|
25 |
"num_hidden_layers": 24,
|
|
|
26 |
"partial_rotary_factor": 0.5,
|
27 |
-
"pretraining_tp": 1,
|
28 |
"qk_layernorm": false,
|
29 |
"resid_pdrop": 0.0,
|
30 |
"rope_scaling": null,
|
@@ -32,6 +35,7 @@
|
|
32 |
"tie_word_embeddings": false,
|
33 |
"tokenizer_model_max_length": 2048,
|
34 |
"tokenizer_padding_side": "right",
|
|
|
35 |
"transformers_version": "4.36.2",
|
36 |
"tune_mm_mlp_adapter": false,
|
37 |
"use_cache": true,
|
|
|
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,
|
|
|
22 |
"mm_hidden_size": 1024,
|
23 |
"mm_projector_lr": 2e-05,
|
24 |
"mm_projector_type": "mlp2x_gelu",
|
|
|
25 |
"mm_vision_tower": "/path/to/EVA02_CLIP_L_336_psz14_s6B.pt",
|
26 |
"model_type": "bunny-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,
|
|
|
35 |
"tie_word_embeddings": false,
|
36 |
"tokenizer_model_max_length": 2048,
|
37 |
"tokenizer_padding_side": "right",
|
38 |
+
"torch_dtype": "float16",
|
39 |
"transformers_version": "4.36.2",
|
40 |
"tune_mm_mlp_adapter": false,
|
41 |
"use_cache": true,
|
non_lora_trainables.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12593328
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38e757fefb472a2313275840ba6e86f1681fc00bc4bd0cf76b8faec66a318e0b
|
3 |
size 12593328
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|