KublaiKhan1
commited on
Commit
•
0196b36
1
Parent(s):
c1a72e9
Upload 5 files
Browse files- adapter_config.json +28 -0
- adapter_model.bin +3 -0
- config.json +38 -0
- non_lora_trainables.bin +3 -0
- trainer_state.json +18 -0
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 256,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 128,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"o_proj",
|
21 |
+
"gate_proj",
|
22 |
+
"up_proj",
|
23 |
+
"down_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b210c86bde3c599af34390eab3d8588e291e1b580dd3d6dde97108de665f53ad
|
3 |
+
size 1342332557
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"freeze_mm_mlp_adapter": false,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"image_aspect_ratio": "pad",
|
12 |
+
"image_grid_pinpoints": null,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 14336,
|
15 |
+
"max_position_embeddings": 32768,
|
16 |
+
"mm_hidden_size": 1152,
|
17 |
+
"mm_projector_lr": 2e-05,
|
18 |
+
"mm_projector_type": "mlp2x_gelu",
|
19 |
+
"mm_use_im_patch_token": false,
|
20 |
+
"mm_use_im_start_end": false,
|
21 |
+
"mm_vision_select_feature": "patch",
|
22 |
+
"mm_vision_select_layer": -2,
|
23 |
+
"mm_vision_tower": "hf-hub:timm/ViT-SO400M-14-SigLIP-384",
|
24 |
+
"model_type": "llava_mistral",
|
25 |
+
"num_attention_heads": 32,
|
26 |
+
"num_hidden_layers": 32,
|
27 |
+
"num_key_value_heads": 8,
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_theta": 10000.0,
|
30 |
+
"sliding_window": 4096,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.35.0",
|
34 |
+
"tune_mm_mlp_adapter": false,
|
35 |
+
"use_cache": true,
|
36 |
+
"use_mm_proj": true,
|
37 |
+
"vocab_size": 32000
|
38 |
+
}
|
non_lora_trainables.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ed02ed6106b5d4ed460b2828c7067f66b19968a355772df985543e753a11b94
|
3 |
+
size 942592413
|
trainer_state.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": null,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 0,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [],
|
11 |
+
"logging_steps": 500,
|
12 |
+
"max_steps": 0,
|
13 |
+
"num_train_epochs": 0,
|
14 |
+
"save_steps": 500,
|
15 |
+
"total_flos": 0,
|
16 |
+
"trial_name": null,
|
17 |
+
"trial_params": null
|
18 |
+
}
|