Spaces:
Runtime error
Runtime error
add new checkpoint
Browse files- .vscode/launch.json +15 -0
- app.py +13 -34
- checkpoints/merged_weights_grounded_obj_ref/config.json +54 -0
- checkpoints/merged_weights_grounded_obj_ref/generation_config.json +10 -0
- checkpoints/merged_weights_grounded_obj_ref/pytorch_model-00001-of-00002.bin +3 -0
- checkpoints/merged_weights_grounded_obj_ref/pytorch_model-00002-of-00002.bin +3 -0
- checkpoints/merged_weights_grounded_obj_ref/pytorch_model.bin.index.json +330 -0
- checkpoints/merged_weights_grounded_obj_ref/special_tokens_map.json +24 -0
- checkpoints/merged_weights_grounded_obj_ref/tokenizer.model +3 -0
- checkpoints/merged_weights_grounded_obj_ref/tokenizer_config.json +36 -0
- scripts/merge_lora_weights.py +22 -0
.vscode/launch.json
CHANGED
@@ -14,6 +14,21 @@
|
|
14 |
"CUDA_VISIBLE_DEVICES": "1",
|
15 |
},
|
16 |
"args": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
]
|
19 |
}
|
|
|
14 |
"CUDA_VISIBLE_DEVICES": "1",
|
15 |
},
|
16 |
"args": []
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"name": "merge_lora_weights",
|
20 |
+
"type": "python",
|
21 |
+
"request": "launch",
|
22 |
+
"module": "scripts.merge_lora_weights",
|
23 |
+
"justMyCode": false,
|
24 |
+
"env": {
|
25 |
+
"CUDA_VISIBLE_DEVICES": "1",
|
26 |
+
},
|
27 |
+
"args": [
|
28 |
+
"--model-base=/data/jianingy/3d_grand_demo_hf_space/checkpoints/llava-llama-2-7b-chat-lightning-preview",
|
29 |
+
"--model-path=/data/jianingy/3d_grand_demo_hf_space/checkpoints/llava_lora_grounded_obj_ref_checkpoint-4896",
|
30 |
+
"--save-model-path=/data/jianingy/3d_grand_demo_hf_space/checkpoints/merged_weights_grounded_obj_ref"
|
31 |
+
]
|
32 |
}
|
33 |
]
|
34 |
}
|
app.py
CHANGED
@@ -27,8 +27,8 @@ from session import Session
|
|
27 |
from model import load_model_and_dataloader, get_model_response
|
28 |
|
29 |
# Load model and tokenizer once at the start
|
30 |
-
model_path = "checkpoints/
|
31 |
-
model_base =
|
32 |
load_8bit = False
|
33 |
load_4bit = False
|
34 |
load_bf16 = True
|
@@ -38,37 +38,16 @@ max_new_tokens = 5000
|
|
38 |
obj_context_feature_type = "text"
|
39 |
|
40 |
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
# Restore the original CUDA_VISIBLE_DEVICES environment variable
|
52 |
-
if self.original_cuda_visible_devices is not None:
|
53 |
-
os.environ["CUDA_VISIBLE_DEVICES"] = self.original_cuda_visible_devices
|
54 |
-
else:
|
55 |
-
del os.environ["CUDA_VISIBLE_DEVICES"]
|
56 |
-
# Reinitialize CUDA state in PyTorch
|
57 |
-
torch.cuda.device_count()
|
58 |
-
|
59 |
-
|
60 |
-
# HACK: we need to temporarily disable CUDA b/c when loading model,
|
61 |
-
# PEFT somehow always uses CUDA even if we set device_map to 'cpu'
|
62 |
-
with TemporaryDisableCUDA():
|
63 |
-
tokenizer, model, data_loader = load_model_and_dataloader(
|
64 |
-
model_path=model_path,
|
65 |
-
model_base=model_base,
|
66 |
-
load_8bit=load_8bit,
|
67 |
-
load_4bit=load_4bit,
|
68 |
-
load_bf16=load_bf16,
|
69 |
-
scene_to_obj_mapping=scene_to_obj_mapping,
|
70 |
-
device_map='cpu',
|
71 |
-
) # Huggingface Zero-GPU has to use .to(device) to set the device, otherwise it will fail
|
72 |
|
73 |
model.to("cuda") # Huggingface Zero-GPU requires explicit device placement
|
74 |
|
@@ -509,7 +488,7 @@ for x in range(1, 10): # try 8 times
|
|
509 |
# debug=True,
|
510 |
# server_name="0.0.0.0",
|
511 |
# server_port=port,
|
512 |
-
|
513 |
)
|
514 |
except OSError:
|
515 |
for proc in process_iter():
|
|
|
27 |
from model import load_model_and_dataloader, get_model_response
|
28 |
|
29 |
# Load model and tokenizer once at the start
|
30 |
+
model_path = "checkpoints/merged_weights_grounded_obj_ref"
|
31 |
+
model_base = None
|
32 |
load_8bit = False
|
33 |
load_4bit = False
|
34 |
load_bf16 = True
|
|
|
38 |
obj_context_feature_type = "text"
|
39 |
|
40 |
|
41 |
+
|
42 |
+
tokenizer, model, data_loader = load_model_and_dataloader(
|
43 |
+
model_path=model_path,
|
44 |
+
model_base=model_base,
|
45 |
+
load_8bit=load_8bit,
|
46 |
+
load_4bit=load_4bit,
|
47 |
+
load_bf16=load_bf16,
|
48 |
+
scene_to_obj_mapping=scene_to_obj_mapping,
|
49 |
+
device_map='cpu',
|
50 |
+
) # Huggingface Zero-GPU has to use .to(device) to set the device, otherwise it will fail
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
model.to("cuda") # Huggingface Zero-GPU requires explicit device placement
|
53 |
|
|
|
488 |
# debug=True,
|
489 |
# server_name="0.0.0.0",
|
490 |
# server_port=port,
|
491 |
+
share=True
|
492 |
)
|
493 |
except OSError:
|
494 |
for proc in process_iter():
|
checkpoints/merged_weights_grounded_obj_ref/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/data/jianingy/3d_grand_demo_hf_space/checkpoints/llava-llama-2-7b-chat-lightning-preview",
|
3 |
+
"added_special_token_to_input_id": {},
|
4 |
+
"architectures": [
|
5 |
+
"LlavaLlamaForCausalLM"
|
6 |
+
],
|
7 |
+
"bbox_ce_loss_weight": 0.0,
|
8 |
+
"bbox_iou_loss_weight": 0.0,
|
9 |
+
"bbox_mse_loss_weight": 0.0,
|
10 |
+
"bbox_tokenization_type": null,
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"d_latents": 1024,
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"freeze_mm_mlp_adapter": false,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 4096,
|
17 |
+
"image_aspect_ratio": "square",
|
18 |
+
"image_grid_pinpoints": null,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 11008,
|
21 |
+
"lm_loss_weight": 1.0,
|
22 |
+
"max_position_embeddings": 2048,
|
23 |
+
"mm_hidden_size": 1024,
|
24 |
+
"mm_resampler_type": null,
|
25 |
+
"mm_use_im_patch_token": false,
|
26 |
+
"mm_use_im_start_end": false,
|
27 |
+
"mm_vision_select_feature": "patch",
|
28 |
+
"mm_vision_select_layer": -2,
|
29 |
+
"mm_vision_tower": "bbox-ground-truth",
|
30 |
+
"model_type": "llava",
|
31 |
+
"normalize_points_to_unit_cube": false,
|
32 |
+
"num_attention_heads": 32,
|
33 |
+
"num_hidden_layers": 32,
|
34 |
+
"num_key_value_heads": 32,
|
35 |
+
"num_latents": 256,
|
36 |
+
"num_voxels_per_axis_for_location_tokens": 10,
|
37 |
+
"pad_token_id": 0,
|
38 |
+
"pretraining_tp": 1,
|
39 |
+
"rms_norm_eps": 1e-06,
|
40 |
+
"rope_scaling": null,
|
41 |
+
"tie_word_embeddings": false,
|
42 |
+
"torch_dtype": "float16",
|
43 |
+
"transformers_version": "4.31.0",
|
44 |
+
"tune_mm_mlp_adapter": false,
|
45 |
+
"tune_mm_vision_resampler": false,
|
46 |
+
"tune_vision_tower": false,
|
47 |
+
"use_bbox_ce_loss": false,
|
48 |
+
"use_bbox_iou_loss": false,
|
49 |
+
"use_bbox_mse_loss": false,
|
50 |
+
"use_cache": false,
|
51 |
+
"use_mm_proj": true,
|
52 |
+
"vision_tower": "bbox-ground-truth",
|
53 |
+
"vocab_size": 32000
|
54 |
+
}
|
checkpoints/merged_weights_grounded_obj_ref/generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.6,
|
8 |
+
"top_p": 0.9,
|
9 |
+
"transformers_version": "4.31.0"
|
10 |
+
}
|
checkpoints/merged_weights_grounded_obj_ref/pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b36710588cf7afcae9a0185b27b3ef89a9bcaad9738e6d075c2e8b8d77f7af84
|
3 |
+
size 9976634558
|
checkpoints/merged_weights_grounded_obj_ref/pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f74f16d5d9ca58599add51730cf245a3bbd053daddb4769c4cc4b48708c085b2
|
3 |
+
size 3500315539
|
checkpoints/merged_weights_grounded_obj_ref/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13476839424
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
328 |
+
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
329 |
+
}
|
330 |
+
}
|
checkpoints/merged_weights_grounded_obj_ref/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoints/merged_weights_grounded_obj_ref/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoints/merged_weights_grounded_obj_ref/tokenizer_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
13 |
+
"clean_up_tokenization_spaces": false,
|
14 |
+
"eos_token": {
|
15 |
+
"__type": "AddedToken",
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"legacy": false,
|
23 |
+
"model_max_length": 4096,
|
24 |
+
"pad_token": null,
|
25 |
+
"padding_side": "right",
|
26 |
+
"sp_model_kwargs": {},
|
27 |
+
"tokenizer_class": "LlamaTokenizer",
|
28 |
+
"unk_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|
scripts/merge_lora_weights.py
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import argparse
|
2 |
+
from llava.model.builder import load_pretrained_model
|
3 |
+
from llava.mm_utils import get_model_name_from_path
|
4 |
+
|
5 |
+
|
6 |
+
def merge_lora(args):
|
7 |
+
model_name = get_model_name_from_path(args.model_path)
|
8 |
+
tokenizer, model, image_processor, context_len = load_pretrained_model(args.model_path, args.model_base, model_name, device_map='cpu')
|
9 |
+
|
10 |
+
model.save_pretrained(args.save_model_path)
|
11 |
+
tokenizer.save_pretrained(args.save_model_path)
|
12 |
+
|
13 |
+
|
14 |
+
if __name__ == "__main__":
|
15 |
+
parser = argparse.ArgumentParser()
|
16 |
+
parser.add_argument("--model-path", type=str, required=True)
|
17 |
+
parser.add_argument("--model-base", type=str, required=True)
|
18 |
+
parser.add_argument("--save-model-path", type=str, required=True)
|
19 |
+
|
20 |
+
args = parser.parse_args()
|
21 |
+
|
22 |
+
merge_lora(args)
|