Upload 6 files
Browse files
base-3784m-pretrained/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.4.0
|
base-3784m-pretrained/adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "llama2_weights",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32.0,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": [
|
| 13 |
+
"embed_tokens",
|
| 14 |
+
"lm_head"
|
| 15 |
+
],
|
| 16 |
+
"peft_type": "LORA",
|
| 17 |
+
"r": 8,
|
| 18 |
+
"revision": null,
|
| 19 |
+
"target_modules": [
|
| 20 |
+
"q_proj",
|
| 21 |
+
"v_proj",
|
| 22 |
+
"k_proj",
|
| 23 |
+
"o_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM"
|
| 29 |
+
}
|
base-3784m-pretrained/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0731dee20efb5e6e3ca72d654cfd755e7ba8880667d90c480b66656337386a87
|
| 3 |
+
size 40131533
|
base-3784m-pretrained/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "llama2_weights",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 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 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mm_hidden_size": 1024,
|
| 16 |
+
"mm_projector_lr": 2e-05,
|
| 17 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 18 |
+
"mm_use_im_patch_token": false,
|
| 19 |
+
"mm_use_im_start_end": false,
|
| 20 |
+
"mm_vision_select_feature": "patch",
|
| 21 |
+
"mm_vision_select_layer": -2,
|
| 22 |
+
"mm_vision_tower": "clip-vit-large-patch14-336",
|
| 23 |
+
"model_type": "llava",
|
| 24 |
+
"num_attention_heads": 32,
|
| 25 |
+
"num_hidden_layers": 32,
|
| 26 |
+
"num_key_value_heads": 32,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"pretraining_tp": 1,
|
| 29 |
+
"rms_norm_eps": 1e-05,
|
| 30 |
+
"rope_scaling": null,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"tokenizer_model_max_length": 2048,
|
| 33 |
+
"tokenizer_padding_side": "right",
|
| 34 |
+
"torch_dtype": "float16",
|
| 35 |
+
"transformers_version": "4.31.0",
|
| 36 |
+
"tune_mm_mlp_adapter": false,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"use_mm_proj": true,
|
| 39 |
+
"vocab_size": 51008
|
| 40 |
+
}
|
base-3784m-pretrained/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ade9447c7b1625b1369b115f83d5aca21dfaacac6eb9d11043edf06178be1e74
|
| 3 |
+
size 1713392647
|
base-3784m-pretrained/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|