KublaiKhan1 commited on
Commit
addd7bd
1 Parent(s): b2fa172

Upload 5 files

Browse files
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
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:c101add8957de09218245a466ba9ef52f991338d202b64154c2011aab81ac5a0
3
+ size 1342332557
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "freeze_mm_mlp_adapter": false,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "image_aspect_ratio": "pad",
13
+ "image_grid_pinpoints": null,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 32768,
17
+ "mm_hidden_size": 1152,
18
+ "mm_projector_lr": 2e-05,
19
+ "mm_projector_type": "mlp2x_gelu",
20
+ "mm_use_im_patch_token": false,
21
+ "mm_use_im_start_end": false,
22
+ "mm_vision_select_feature": "patch",
23
+ "mm_vision_select_layer": -2,
24
+ "mm_vision_tower": "hf-hub:timm/ViT-SO400M-14-SigLIP-384",
25
+ "model_type": "llava",
26
+ "num_attention_heads": 32,
27
+ "num_hidden_layers": 32,
28
+ "num_key_value_heads": 8,
29
+ "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": null,
32
+ "rope_theta": 10000.0,
33
+ "sliding_window": 4096,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.35.0",
37
+ "tune_mm_mlp_adapter": false,
38
+ "use_cache": true,
39
+ "use_mm_proj": true,
40
+ "vocab_size": 32002
41
+ }
non_lora_trainables.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a250b4d3debf930641d732656cd4e96dd78dd94d537263ff44dda7014725f15
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
+ }