Training in progress, step 100
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- config.json +29 -0
- merges.txt +0 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +778 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -0
- trainer_log.jsonl +102 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-32B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 27648,
|
13 |
+
"max_position_embeddings": 131072,
|
14 |
+
"max_window_layers": 64,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 40,
|
17 |
+
"num_hidden_layers": 64,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.48.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 152064
|
29 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16b5c03d547f738a4ec0fcfada7d2dee1709e538792d1427b2976a52ccfe72af
|
3 |
+
size 4891730992
|
model-00002-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:668a9ae90a7d141d899444645723e1d82f22ee1f43c536aa4b0044bb154b33cc
|
3 |
+
size 4876059352
|
model-00003-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cb7f47dbc4aca7db7895168e4975bca6a2961a1e5620ce7cf7f1cffbce14000
|
3 |
+
size 4876059384
|
model-00004-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93a0f42257862cb6ae70eef8181908555b2782d4130819e37fb049ef320aac3d
|
3 |
+
size 4876059416
|
model-00005-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1ed7c50b50e36d2377596d1d100a386f6aae74dc61f29473cd83859a89a28ed
|
3 |
+
size 4876059416
|
model-00006-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3311814ba6d1e6d871cc565edb6153537ad05119d221de7bac6a85aab2f71af6
|
3 |
+
size 4876059416
|
model-00007-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e62a46f78145a4515e3a6a9a3465b3387469db15007d9677ea08770a0571bb4
|
3 |
+
size 4876059416
|
model-00008-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfd5e75413c492d63e8ab6304637c00d30ab68c31c8820588e278d35dcf9a8ba
|
3 |
+
size 4876059416
|
model-00009-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86de457cf28a371df4d0e75445567e4f181b356db027b8fe577ef6072a67b6bb
|
3 |
+
size 4876059416
|
model-00010-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d446537bc86246d077ada88326ad132a2407742a1a7a127e587f19bf254a050
|
3 |
+
size 4876059416
|
model-00011-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c7bf8bb80efd3f4d16798ba83cd399a97839d7e8003a8e347f73db322282bd8
|
3 |
+
size 4876059416
|
model-00012-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:688e753ff443b758a02b36366cec3e810a1b74547fd9685f54282bfe5ebd8e56
|
3 |
+
size 4876059416
|
model-00013-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a06a2f467257de65798137df7deb45dce3a9b0a066d254a636982bb880e1fad6
|
3 |
+
size 4876059416
|
model-00014-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15e14bad24559ea075a43e9fe7e26396a068f124828fda75b1cc55e1585cbbda
|
3 |
+
size 2123397800
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,778 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 65527752704
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00014-of-00014.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
32 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
44 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
56 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
68 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
80 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
92 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
104 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
116 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
128 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
140 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
164 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
176 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
188 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
200 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
212 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
224 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
236 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
248 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
260 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
261 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
262 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
263 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
264 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
265 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
266 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
267 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
268 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
269 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
270 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
271 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
272 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
273 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
274 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
275 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
276 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
277 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
278 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
279 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
280 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
281 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
282 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
283 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
284 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
285 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
286 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
287 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
288 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
289 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
290 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
291 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
292 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
293 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
294 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
295 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
296 |
+
"model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
297 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
298 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
299 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
300 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
301 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
302 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
303 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
304 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
305 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
306 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
307 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
308 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
309 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
310 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
311 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
312 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
313 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
314 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
315 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
316 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
318 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
320 |
+
"model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
321 |
+
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
322 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
323 |
+
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
324 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
325 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
326 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
327 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
328 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
329 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
330 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
331 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
332 |
+
"model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
333 |
+
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
334 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
335 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
336 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
337 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
338 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
339 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
340 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
341 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
342 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
343 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
344 |
+
"model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
345 |
+
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
346 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
347 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
348 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
349 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
350 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
351 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
352 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
353 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
354 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
355 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
356 |
+
"model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
357 |
+
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
358 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
359 |
+
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
360 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
361 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
362 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
363 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
364 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
365 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
366 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
367 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
368 |
+
"model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
369 |
+
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
370 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
371 |
+
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
372 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
373 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
374 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
375 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
376 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
377 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
378 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
379 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
380 |
+
"model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
381 |
+
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
382 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
383 |
+
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
384 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
385 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
386 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
387 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
388 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
389 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
390 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
391 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
392 |
+
"model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
393 |
+
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
394 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
395 |
+
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
396 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
397 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
398 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
399 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
400 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
401 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
402 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
403 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
404 |
+
"model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
405 |
+
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
406 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
407 |
+
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
408 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
409 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
410 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
411 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
412 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
413 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
414 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
415 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
416 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
417 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
418 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
419 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
420 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
421 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
422 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
423 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
424 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
425 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
426 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
427 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
428 |
+
"model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
429 |
+
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
430 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
431 |
+
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
432 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
433 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
434 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
435 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
436 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
437 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
438 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
439 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
440 |
+
"model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
441 |
+
"model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
442 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
443 |
+
"model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
444 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
445 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
446 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
447 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
448 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
449 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
450 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
451 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
452 |
+
"model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
453 |
+
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
454 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
455 |
+
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
456 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
457 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
458 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
459 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
460 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
461 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
462 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
463 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
464 |
+
"model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
465 |
+
"model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
466 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
467 |
+
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
468 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
469 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
470 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
471 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
472 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
473 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
474 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
475 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
476 |
+
"model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
477 |
+
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
478 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
479 |
+
"model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
480 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
481 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
482 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
483 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
484 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
485 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
486 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
487 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
488 |
+
"model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
489 |
+
"model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
490 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
491 |
+
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
492 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
493 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
494 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
495 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
496 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
497 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
498 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
499 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
500 |
+
"model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
501 |
+
"model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
502 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
503 |
+
"model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
504 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
505 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
506 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
507 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
508 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
509 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
510 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
511 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
512 |
+
"model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
513 |
+
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
514 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
515 |
+
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
516 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
517 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
518 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
519 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
520 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
521 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
522 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
523 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
524 |
+
"model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
525 |
+
"model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
526 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
527 |
+
"model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
528 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
529 |
+
"model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
530 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
531 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
532 |
+
"model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
533 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
534 |
+
"model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
535 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
536 |
+
"model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
537 |
+
"model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
538 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
539 |
+
"model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
540 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
541 |
+
"model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
542 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
543 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
544 |
+
"model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
545 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
546 |
+
"model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
547 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
548 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
549 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
550 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
551 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
552 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
553 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
554 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
555 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
556 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
557 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
558 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
559 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
560 |
+
"model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
561 |
+
"model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
562 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
563 |
+
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
564 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
565 |
+
"model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
566 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
567 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
568 |
+
"model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
569 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
570 |
+
"model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
571 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
572 |
+
"model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
573 |
+
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
574 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
575 |
+
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
576 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
577 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
578 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
579 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
580 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
581 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
582 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
583 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
584 |
+
"model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
585 |
+
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
586 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
587 |
+
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
588 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
589 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
590 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
591 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
592 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
593 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
594 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
595 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
596 |
+
"model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
597 |
+
"model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
598 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
599 |
+
"model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
600 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
601 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
602 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
603 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
604 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
605 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
606 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
607 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
608 |
+
"model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
609 |
+
"model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
610 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
611 |
+
"model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
612 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
613 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
614 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
615 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
616 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
617 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
618 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
619 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
620 |
+
"model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
621 |
+
"model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
622 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
623 |
+
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
624 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
625 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
626 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
627 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
628 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
629 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
630 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
631 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
632 |
+
"model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
633 |
+
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
634 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
635 |
+
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
636 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
637 |
+
"model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
638 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
639 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
640 |
+
"model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
641 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
642 |
+
"model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
643 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
644 |
+
"model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
645 |
+
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
646 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
647 |
+
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
648 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
649 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
650 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
651 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
652 |
+
"model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
653 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
654 |
+
"model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
655 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
656 |
+
"model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
657 |
+
"model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
658 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
659 |
+
"model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
660 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
661 |
+
"model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
662 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
663 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
664 |
+
"model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
665 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
666 |
+
"model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
667 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
668 |
+
"model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
669 |
+
"model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
670 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
671 |
+
"model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
672 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
673 |
+
"model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
674 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
675 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
676 |
+
"model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
677 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
678 |
+
"model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
679 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
680 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
681 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
682 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
683 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
684 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
685 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
686 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
687 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
688 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
689 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
690 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
691 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
692 |
+
"model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
693 |
+
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
694 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
695 |
+
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
696 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
697 |
+
"model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
698 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
699 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
700 |
+
"model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
701 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
702 |
+
"model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
703 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
704 |
+
"model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
705 |
+
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
706 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
707 |
+
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
708 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
709 |
+
"model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
710 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
711 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
712 |
+
"model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
713 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
714 |
+
"model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
715 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
716 |
+
"model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
717 |
+
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
718 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
719 |
+
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
720 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
721 |
+
"model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
722 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
723 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
724 |
+
"model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
725 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
726 |
+
"model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
727 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
728 |
+
"model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
729 |
+
"model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
730 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
731 |
+
"model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
732 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
733 |
+
"model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
734 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
735 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
736 |
+
"model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
737 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
738 |
+
"model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
739 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
740 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
741 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
742 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
743 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
744 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
745 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
746 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
747 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
748 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
749 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
750 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
751 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
752 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
753 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
754 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
755 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
756 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
757 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
758 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
759 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
760 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
761 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
762 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
763 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
764 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
765 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
766 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
767 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
768 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
769 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
770 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
771 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
772 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
773 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
774 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
775 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
776 |
+
"model.norm.weight": "model-00014-of-00014.safetensors"
|
777 |
+
}
|
778 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|endoftext|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 8192,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"padding_side": "right",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 273, "loss": 1.3486, "lr": 3.5714285714285714e-06, "epoch": 0.003657978966620942, "percentage": 0.37, "elapsed_time": "0:04:02", "remaining_time": "18:17:14"}
|
2 |
+
{"current_steps": 2, "total_steps": 273, "loss": 1.359, "lr": 7.142857142857143e-06, "epoch": 0.007315957933241884, "percentage": 0.73, "elapsed_time": "0:07:41", "remaining_time": "17:23:01"}
|
3 |
+
{"current_steps": 3, "total_steps": 273, "loss": 1.3603, "lr": 1.0714285714285714e-05, "epoch": 0.010973936899862825, "percentage": 1.1, "elapsed_time": "0:11:26", "remaining_time": "17:10:05"}
|
4 |
+
{"current_steps": 4, "total_steps": 273, "loss": 1.352, "lr": 1.4285714285714285e-05, "epoch": 0.014631915866483767, "percentage": 1.47, "elapsed_time": "0:15:02", "remaining_time": "16:51:02"}
|
5 |
+
{"current_steps": 5, "total_steps": 273, "loss": 1.3645, "lr": 1.785714285714286e-05, "epoch": 0.01828989483310471, "percentage": 1.83, "elapsed_time": "0:18:39", "remaining_time": "16:40:10"}
|
6 |
+
{"current_steps": 6, "total_steps": 273, "loss": 1.3406, "lr": 2.1428571428571428e-05, "epoch": 0.02194787379972565, "percentage": 2.2, "elapsed_time": "0:22:16", "remaining_time": "16:31:34"}
|
7 |
+
{"current_steps": 7, "total_steps": 273, "loss": 1.3445, "lr": 2.5e-05, "epoch": 0.025605852766346592, "percentage": 2.56, "elapsed_time": "0:25:52", "remaining_time": "16:23:20"}
|
8 |
+
{"current_steps": 8, "total_steps": 273, "loss": 1.3225, "lr": 2.857142857142857e-05, "epoch": 0.029263831732967534, "percentage": 2.93, "elapsed_time": "0:29:28", "remaining_time": "16:16:18"}
|
9 |
+
{"current_steps": 9, "total_steps": 273, "loss": 1.3063, "lr": 3.2142857142857144e-05, "epoch": 0.03292181069958848, "percentage": 3.3, "elapsed_time": "0:33:04", "remaining_time": "16:10:01"}
|
10 |
+
{"current_steps": 10, "total_steps": 273, "loss": 1.3201, "lr": 3.571428571428572e-05, "epoch": 0.03657978966620942, "percentage": 3.66, "elapsed_time": "0:36:39", "remaining_time": "16:04:16"}
|
11 |
+
{"current_steps": 11, "total_steps": 273, "loss": 1.324, "lr": 3.928571428571429e-05, "epoch": 0.040237768632830365, "percentage": 4.03, "elapsed_time": "0:40:15", "remaining_time": "15:58:59"}
|
12 |
+
{"current_steps": 12, "total_steps": 273, "loss": 1.324, "lr": 4.2857142857142856e-05, "epoch": 0.0438957475994513, "percentage": 4.4, "elapsed_time": "0:43:50", "remaining_time": "15:53:36"}
|
13 |
+
{"current_steps": 13, "total_steps": 273, "loss": 1.3072, "lr": 4.642857142857143e-05, "epoch": 0.04755372656607224, "percentage": 4.76, "elapsed_time": "0:47:25", "remaining_time": "15:48:26"}
|
14 |
+
{"current_steps": 14, "total_steps": 273, "loss": 1.3005, "lr": 5e-05, "epoch": 0.051211705532693184, "percentage": 5.13, "elapsed_time": "0:51:00", "remaining_time": "15:43:42"}
|
15 |
+
{"current_steps": 15, "total_steps": 273, "loss": 1.3036, "lr": 4.999816090185888e-05, "epoch": 0.05486968449931413, "percentage": 5.49, "elapsed_time": "0:54:35", "remaining_time": "15:39:01"}
|
16 |
+
{"current_steps": 16, "total_steps": 273, "loss": 1.3188, "lr": 4.9992643878018054e-05, "epoch": 0.05852766346593507, "percentage": 5.86, "elapsed_time": "0:58:06", "remaining_time": "15:33:27"}
|
17 |
+
{"current_steps": 17, "total_steps": 273, "loss": 1.2834, "lr": 4.99834497401854e-05, "epoch": 0.06218564243255601, "percentage": 6.23, "elapsed_time": "1:01:39", "remaining_time": "15:28:31"}
|
18 |
+
{"current_steps": 18, "total_steps": 273, "loss": 1.287, "lr": 4.997057984107466e-05, "epoch": 0.06584362139917696, "percentage": 6.59, "elapsed_time": "1:05:12", "remaining_time": "15:23:48"}
|
19 |
+
{"current_steps": 19, "total_steps": 273, "loss": 1.2819, "lr": 4.995403607420644e-05, "epoch": 0.0695016003657979, "percentage": 6.96, "elapsed_time": "1:08:44", "remaining_time": "15:18:51"}
|
20 |
+
{"current_steps": 20, "total_steps": 273, "loss": 1.2616, "lr": 4.993382087362959e-05, "epoch": 0.07315957933241884, "percentage": 7.33, "elapsed_time": "1:12:15", "remaining_time": "15:14:06"}
|
21 |
+
{"current_steps": 21, "total_steps": 273, "loss": 1.276, "lr": 4.9909937213563165e-05, "epoch": 0.07681755829903979, "percentage": 7.69, "elapsed_time": "1:15:47", "remaining_time": "15:09:33"}
|
22 |
+
{"current_steps": 22, "total_steps": 273, "loss": 1.2654, "lr": 4.988238860795873e-05, "epoch": 0.08047553726566073, "percentage": 8.06, "elapsed_time": "1:19:19", "remaining_time": "15:05:03"}
|
23 |
+
{"current_steps": 23, "total_steps": 273, "loss": 1.2802, "lr": 4.985117910998345e-05, "epoch": 0.08413351623228166, "percentage": 8.42, "elapsed_time": "1:22:51", "remaining_time": "15:00:39"}
|
24 |
+
{"current_steps": 24, "total_steps": 273, "loss": 1.267, "lr": 4.981631331142368e-05, "epoch": 0.0877914951989026, "percentage": 8.79, "elapsed_time": "1:26:23", "remaining_time": "14:56:22"}
|
25 |
+
{"current_steps": 25, "total_steps": 273, "loss": 1.2659, "lr": 4.977779634200947e-05, "epoch": 0.09144947416552354, "percentage": 9.16, "elapsed_time": "1:29:54", "remaining_time": "14:51:57"}
|
26 |
+
{"current_steps": 26, "total_steps": 273, "loss": 1.2462, "lr": 4.973563386865974e-05, "epoch": 0.09510745313214448, "percentage": 9.52, "elapsed_time": "1:33:26", "remaining_time": "14:47:39"}
|
27 |
+
{"current_steps": 27, "total_steps": 273, "loss": 1.2546, "lr": 4.968983209464863e-05, "epoch": 0.09876543209876543, "percentage": 9.89, "elapsed_time": "1:36:57", "remaining_time": "14:43:22"}
|
28 |
+
{"current_steps": 28, "total_steps": 273, "loss": 1.2446, "lr": 4.9640397758692715e-05, "epoch": 0.10242341106538637, "percentage": 10.26, "elapsed_time": "1:40:28", "remaining_time": "14:39:07"}
|
29 |
+
{"current_steps": 29, "total_steps": 273, "loss": 1.2615, "lr": 4.9587338133959625e-05, "epoch": 0.10608139003200731, "percentage": 10.62, "elapsed_time": "1:43:59", "remaining_time": "14:34:56"}
|
30 |
+
{"current_steps": 30, "total_steps": 273, "loss": 1.275, "lr": 4.953066102699795e-05, "epoch": 0.10973936899862825, "percentage": 10.99, "elapsed_time": "1:47:30", "remaining_time": "14:30:50"}
|
31 |
+
{"current_steps": 31, "total_steps": 273, "loss": 1.2436, "lr": 4.947037477658865e-05, "epoch": 0.1133973479652492, "percentage": 11.36, "elapsed_time": "1:51:02", "remaining_time": "14:26:48"}
|
32 |
+
{"current_steps": 32, "total_steps": 273, "loss": 1.2502, "lr": 4.9406488252518203e-05, "epoch": 0.11705532693187014, "percentage": 11.72, "elapsed_time": "1:54:34", "remaining_time": "14:22:52"}
|
33 |
+
{"current_steps": 33, "total_steps": 273, "loss": 1.2489, "lr": 4.933901085427362e-05, "epoch": 0.12071330589849108, "percentage": 12.09, "elapsed_time": "1:58:05", "remaining_time": "14:18:49"}
|
34 |
+
{"current_steps": 34, "total_steps": 273, "loss": 1.233, "lr": 4.926795250965952e-05, "epoch": 0.12437128486511202, "percentage": 12.45, "elapsed_time": "2:01:36", "remaining_time": "14:14:50"}
|
35 |
+
{"current_steps": 35, "total_steps": 273, "loss": 1.2434, "lr": 4.9193323673337476e-05, "epoch": 0.12802926383173296, "percentage": 12.82, "elapsed_time": "2:05:05", "remaining_time": "14:10:38"}
|
36 |
+
{"current_steps": 36, "total_steps": 273, "loss": 1.2406, "lr": 4.91151353252878e-05, "epoch": 0.13168724279835392, "percentage": 13.19, "elapsed_time": "2:08:35", "remaining_time": "14:06:35"}
|
37 |
+
{"current_steps": 37, "total_steps": 273, "loss": 1.2213, "lr": 4.9033398969194145e-05, "epoch": 0.13534522176497485, "percentage": 13.55, "elapsed_time": "2:12:06", "remaining_time": "14:02:36"}
|
38 |
+
{"current_steps": 38, "total_steps": 273, "loss": 1.23, "lr": 4.894812663075095e-05, "epoch": 0.1390032007315958, "percentage": 13.92, "elapsed_time": "2:15:40", "remaining_time": "13:59:03"}
|
39 |
+
{"current_steps": 39, "total_steps": 273, "loss": 1.2455, "lr": 4.8859330855894156e-05, "epoch": 0.14266117969821673, "percentage": 14.29, "elapsed_time": "2:19:15", "remaining_time": "13:55:33"}
|
40 |
+
{"current_steps": 40, "total_steps": 273, "loss": 1.2272, "lr": 4.876702470895531e-05, "epoch": 0.1463191586648377, "percentage": 14.65, "elapsed_time": "2:22:46", "remaining_time": "13:51:39"}
|
41 |
+
{"current_steps": 41, "total_steps": 273, "loss": 1.2272, "lr": 4.867122177073948e-05, "epoch": 0.14997713763145862, "percentage": 15.02, "elapsed_time": "2:26:16", "remaining_time": "13:47:41"}
|
42 |
+
{"current_steps": 42, "total_steps": 273, "loss": 1.2417, "lr": 4.857193613652711e-05, "epoch": 0.15363511659807957, "percentage": 15.38, "elapsed_time": "2:29:46", "remaining_time": "13:43:45"}
|
43 |
+
{"current_steps": 43, "total_steps": 273, "loss": 1.2409, "lr": 4.846918241400022e-05, "epoch": 0.1572930955647005, "percentage": 15.75, "elapsed_time": "2:33:16", "remaining_time": "13:39:51"}
|
44 |
+
{"current_steps": 44, "total_steps": 273, "loss": 1.2237, "lr": 4.836297572109323e-05, "epoch": 0.16095107453132146, "percentage": 16.12, "elapsed_time": "2:36:46", "remaining_time": "13:35:58"}
|
45 |
+
{"current_steps": 45, "total_steps": 273, "loss": 1.2558, "lr": 4.825333168376864e-05, "epoch": 0.1646090534979424, "percentage": 16.48, "elapsed_time": "2:40:17", "remaining_time": "13:32:09"}
|
46 |
+
{"current_steps": 46, "total_steps": 273, "loss": 1.2149, "lr": 4.8140266433718095e-05, "epoch": 0.16826703246456332, "percentage": 16.85, "elapsed_time": "2:43:48", "remaining_time": "13:28:22"}
|
47 |
+
{"current_steps": 47, "total_steps": 273, "loss": 1.1882, "lr": 4.8023796605988866e-05, "epoch": 0.17192501143118427, "percentage": 17.22, "elapsed_time": "2:47:19", "remaining_time": "13:24:33"}
|
48 |
+
{"current_steps": 48, "total_steps": 273, "loss": 1.2114, "lr": 4.790393933653646e-05, "epoch": 0.1755829903978052, "percentage": 17.58, "elapsed_time": "2:50:50", "remaining_time": "13:20:47"}
|
49 |
+
{"current_steps": 49, "total_steps": 273, "loss": 1.1857, "lr": 4.77807122597034e-05, "epoch": 0.17924096936442616, "percentage": 17.95, "elapsed_time": "2:54:20", "remaining_time": "13:16:59"}
|
50 |
+
{"current_steps": 50, "total_steps": 273, "loss": 1.2132, "lr": 4.7654133505624695e-05, "epoch": 0.18289894833104708, "percentage": 18.32, "elapsed_time": "2:57:51", "remaining_time": "13:13:13"}
|
51 |
+
{"current_steps": 51, "total_steps": 273, "loss": 1.2046, "lr": 4.752422169756048e-05, "epoch": 0.18655692729766804, "percentage": 18.68, "elapsed_time": "3:01:21", "remaining_time": "13:09:25"}
|
52 |
+
{"current_steps": 52, "total_steps": 273, "loss": 1.2374, "lr": 4.7390995949155915e-05, "epoch": 0.19021490626428897, "percentage": 19.05, "elapsed_time": "3:04:51", "remaining_time": "13:05:38"}
|
53 |
+
{"current_steps": 53, "total_steps": 273, "loss": 1.2076, "lr": 4.725447586162911e-05, "epoch": 0.19387288523090992, "percentage": 19.41, "elapsed_time": "3:08:25", "remaining_time": "13:02:07"}
|
54 |
+
{"current_steps": 54, "total_steps": 273, "loss": 1.2239, "lr": 4.711468152088719e-05, "epoch": 0.19753086419753085, "percentage": 19.78, "elapsed_time": "3:11:56", "remaining_time": "12:58:23"}
|
55 |
+
{"current_steps": 55, "total_steps": 273, "loss": 1.2117, "lr": 4.697163349457115e-05, "epoch": 0.2011888431641518, "percentage": 20.15, "elapsed_time": "3:15:26", "remaining_time": "12:54:38"}
|
56 |
+
{"current_steps": 56, "total_steps": 273, "loss": 1.1859, "lr": 4.6825352829029705e-05, "epoch": 0.20484682213077274, "percentage": 20.51, "elapsed_time": "3:18:57", "remaining_time": "12:50:56"}
|
57 |
+
{"current_steps": 57, "total_steps": 273, "loss": 1.2065, "lr": 4.667586104622288e-05, "epoch": 0.2085048010973937, "percentage": 20.88, "elapsed_time": "3:22:29", "remaining_time": "12:47:18"}
|
58 |
+
{"current_steps": 58, "total_steps": 273, "loss": 1.2196, "lr": 4.652318014055547e-05, "epoch": 0.21216278006401462, "percentage": 21.25, "elapsed_time": "3:26:00", "remaining_time": "12:43:39"}
|
59 |
+
{"current_steps": 59, "total_steps": 273, "loss": 1.204, "lr": 4.636733257564104e-05, "epoch": 0.21582075903063558, "percentage": 21.61, "elapsed_time": "3:29:32", "remaining_time": "12:40:00"}
|
60 |
+
{"current_steps": 60, "total_steps": 273, "loss": 1.1865, "lr": 4.620834128099696e-05, "epoch": 0.2194787379972565, "percentage": 21.98, "elapsed_time": "3:33:03", "remaining_time": "12:36:20"}
|
61 |
+
{"current_steps": 61, "total_steps": 273, "loss": 1.195, "lr": 4.604622964867078e-05, "epoch": 0.22313671696387746, "percentage": 22.34, "elapsed_time": "3:36:34", "remaining_time": "12:32:42"}
|
62 |
+
{"current_steps": 62, "total_steps": 273, "loss": 1.2179, "lr": 4.588102152979863e-05, "epoch": 0.2267946959304984, "percentage": 22.71, "elapsed_time": "3:40:06", "remaining_time": "12:29:04"}
|
63 |
+
{"current_steps": 63, "total_steps": 273, "loss": 1.183, "lr": 4.571274123109606e-05, "epoch": 0.23045267489711935, "percentage": 23.08, "elapsed_time": "3:43:38", "remaining_time": "12:25:29"}
|
64 |
+
{"current_steps": 64, "total_steps": 273, "loss": 1.2011, "lr": 4.5541413511281826e-05, "epoch": 0.23411065386374028, "percentage": 23.44, "elapsed_time": "3:47:10", "remaining_time": "12:21:53"}
|
65 |
+
{"current_steps": 65, "total_steps": 273, "loss": 1.2092, "lr": 4.536706357743522e-05, "epoch": 0.23776863283036123, "percentage": 23.81, "elapsed_time": "3:50:43", "remaining_time": "12:18:17"}
|
66 |
+
{"current_steps": 66, "total_steps": 273, "loss": 1.1903, "lr": 4.518971708128737e-05, "epoch": 0.24142661179698216, "percentage": 24.18, "elapsed_time": "3:54:16", "remaining_time": "12:14:44"}
|
67 |
+
{"current_steps": 67, "total_steps": 273, "loss": 1.1801, "lr": 4.5009400115447206e-05, "epoch": 0.24508459076360312, "percentage": 24.54, "elapsed_time": "3:57:48", "remaining_time": "12:11:09"}
|
68 |
+
{"current_steps": 68, "total_steps": 273, "loss": 1.1868, "lr": 4.4826139209562444e-05, "epoch": 0.24874256973022404, "percentage": 24.91, "elapsed_time": "4:01:20", "remaining_time": "12:07:33"}
|
69 |
+
{"current_steps": 69, "total_steps": 273, "loss": 1.1879, "lr": 4.463996132641641e-05, "epoch": 0.252400548696845, "percentage": 25.27, "elapsed_time": "4:04:52", "remaining_time": "12:03:57"}
|
70 |
+
{"current_steps": 70, "total_steps": 273, "loss": 1.1986, "lr": 4.445089385796099e-05, "epoch": 0.25605852766346593, "percentage": 25.64, "elapsed_time": "4:08:23", "remaining_time": "12:00:19"}
|
71 |
+
{"current_steps": 71, "total_steps": 273, "loss": 1.1835, "lr": 4.4258964621286584e-05, "epoch": 0.2597165066300869, "percentage": 26.01, "elapsed_time": "4:11:54", "remaining_time": "11:56:43"}
|
72 |
+
{"current_steps": 72, "total_steps": 273, "loss": 1.1773, "lr": 4.4064201854529365e-05, "epoch": 0.26337448559670784, "percentage": 26.37, "elapsed_time": "4:15:26", "remaining_time": "11:53:05"}
|
73 |
+
{"current_steps": 73, "total_steps": 273, "loss": 1.1814, "lr": 4.386663421271674e-05, "epoch": 0.26703246456332874, "percentage": 26.74, "elapsed_time": "4:18:57", "remaining_time": "11:49:28"}
|
74 |
+
{"current_steps": 74, "total_steps": 273, "loss": 1.1928, "lr": 4.366629076355131e-05, "epoch": 0.2706904435299497, "percentage": 27.11, "elapsed_time": "4:22:34", "remaining_time": "11:46:06"}
|
75 |
+
{"current_steps": 75, "total_steps": 273, "loss": 1.1426, "lr": 4.346320098313429e-05, "epoch": 0.27434842249657065, "percentage": 27.47, "elapsed_time": "4:26:14", "remaining_time": "11:42:53"}
|
76 |
+
{"current_steps": 76, "total_steps": 273, "loss": 1.1639, "lr": 4.3257394751628686e-05, "epoch": 0.2780064014631916, "percentage": 27.84, "elapsed_time": "4:29:49", "remaining_time": "11:39:24"}
|
77 |
+
{"current_steps": 77, "total_steps": 273, "loss": 1.1879, "lr": 4.3048902348863116e-05, "epoch": 0.2816643804298125, "percentage": 28.21, "elapsed_time": "4:33:22", "remaining_time": "11:35:51"}
|
78 |
+
{"current_steps": 78, "total_steps": 273, "loss": 1.218, "lr": 4.283775444987681e-05, "epoch": 0.28532235939643347, "percentage": 28.57, "elapsed_time": "4:36:56", "remaining_time": "11:32:20"}
|
79 |
+
{"current_steps": 79, "total_steps": 273, "loss": 1.1989, "lr": 4.262398212040646e-05, "epoch": 0.2889803383630544, "percentage": 28.94, "elapsed_time": "4:40:30", "remaining_time": "11:28:49"}
|
80 |
+
{"current_steps": 80, "total_steps": 273, "loss": 1.1594, "lr": 4.2407616812315554e-05, "epoch": 0.2926383173296754, "percentage": 29.3, "elapsed_time": "4:44:05", "remaining_time": "11:25:21"}
|
81 |
+
{"current_steps": 81, "total_steps": 273, "loss": 1.1876, "lr": 4.218869035896697e-05, "epoch": 0.2962962962962963, "percentage": 29.67, "elapsed_time": "4:47:37", "remaining_time": "11:21:47"}
|
82 |
+
{"current_steps": 82, "total_steps": 273, "loss": 1.1746, "lr": 4.1967234970539384e-05, "epoch": 0.29995427526291724, "percentage": 30.04, "elapsed_time": "4:51:10", "remaining_time": "11:18:14"}
|
83 |
+
{"current_steps": 83, "total_steps": 273, "loss": 1.179, "lr": 4.1743283229288245e-05, "epoch": 0.3036122542295382, "percentage": 30.4, "elapsed_time": "4:54:43", "remaining_time": "11:14:40"}
|
84 |
+
{"current_steps": 84, "total_steps": 273, "loss": 1.1407, "lr": 4.151686808475204e-05, "epoch": 0.30727023319615915, "percentage": 30.77, "elapsed_time": "4:58:15", "remaining_time": "11:11:05"}
|
85 |
+
{"current_steps": 85, "total_steps": 273, "loss": 1.1567, "lr": 4.1288022848904485e-05, "epoch": 0.31092821216278005, "percentage": 31.14, "elapsed_time": "5:01:48", "remaining_time": "11:07:32"}
|
86 |
+
{"current_steps": 86, "total_steps": 273, "loss": 1.1337, "lr": 4.10567811912534e-05, "epoch": 0.314586191129401, "percentage": 31.5, "elapsed_time": "5:05:22", "remaining_time": "11:04:01"}
|
87 |
+
{"current_steps": 87, "total_steps": 273, "loss": 1.1751, "lr": 4.082317713388702e-05, "epoch": 0.31824417009602196, "percentage": 31.87, "elapsed_time": "5:08:55", "remaining_time": "11:00:27"}
|
88 |
+
{"current_steps": 88, "total_steps": 273, "loss": 1.1659, "lr": 4.058724504646834e-05, "epoch": 0.3219021490626429, "percentage": 32.23, "elapsed_time": "5:12:29", "remaining_time": "10:56:57"}
|
89 |
+
{"current_steps": 89, "total_steps": 273, "loss": 1.1451, "lr": 4.0349019641178443e-05, "epoch": 0.3255601280292638, "percentage": 32.6, "elapsed_time": "5:16:03", "remaining_time": "10:53:24"}
|
90 |
+
{"current_steps": 90, "total_steps": 273, "loss": 1.1479, "lr": 4.010853596760933e-05, "epoch": 0.3292181069958848, "percentage": 32.97, "elapsed_time": "5:19:35", "remaining_time": "10:49:51"}
|
91 |
+
{"current_steps": 91, "total_steps": 273, "loss": 1.1453, "lr": 3.986582940760717e-05, "epoch": 0.33287608596250573, "percentage": 33.33, "elapsed_time": "5:23:08", "remaining_time": "10:46:16"}
|
92 |
+
{"current_steps": 92, "total_steps": 273, "loss": 1.1505, "lr": 3.962093567006662e-05, "epoch": 0.33653406492912663, "percentage": 33.7, "elapsed_time": "5:26:41", "remaining_time": "10:42:44"}
|
93 |
+
{"current_steps": 93, "total_steps": 273, "loss": 1.1718, "lr": 3.937389078567708e-05, "epoch": 0.3401920438957476, "percentage": 34.07, "elapsed_time": "5:30:15", "remaining_time": "10:39:12"}
|
94 |
+
{"current_steps": 94, "total_steps": 273, "loss": 1.1562, "lr": 3.912473110162156e-05, "epoch": 0.34385002286236854, "percentage": 34.43, "elapsed_time": "5:33:47", "remaining_time": "10:35:38"}
|
95 |
+
{"current_steps": 95, "total_steps": 273, "loss": 1.1549, "lr": 3.887349327622901e-05, "epoch": 0.3475080018289895, "percentage": 34.8, "elapsed_time": "5:37:20", "remaining_time": "10:32:04"}
|
96 |
+
{"current_steps": 96, "total_steps": 273, "loss": 1.1736, "lr": 3.8620214273580846e-05, "epoch": 0.3511659807956104, "percentage": 35.16, "elapsed_time": "5:40:54", "remaining_time": "10:28:32"}
|
97 |
+
{"current_steps": 97, "total_steps": 273, "loss": 1.1466, "lr": 3.83649313580725e-05, "epoch": 0.35482395976223136, "percentage": 35.53, "elapsed_time": "5:44:26", "remaining_time": "10:24:58"}
|
98 |
+
{"current_steps": 98, "total_steps": 273, "loss": 1.1491, "lr": 3.8107682088930794e-05, "epoch": 0.3584819387288523, "percentage": 35.9, "elapsed_time": "5:48:01", "remaining_time": "10:21:28"}
|
99 |
+
{"current_steps": 99, "total_steps": 273, "loss": 1.1497, "lr": 3.784850431468795e-05, "epoch": 0.36213991769547327, "percentage": 36.26, "elapsed_time": "5:51:33", "remaining_time": "10:17:53"}
|
100 |
+
{"current_steps": 100, "total_steps": 273, "loss": 1.1434, "lr": 3.7587436167613e-05, "epoch": 0.36579789666209417, "percentage": 36.63, "elapsed_time": "5:55:01", "remaining_time": "10:14:11"}
|
101 |
+
{"current_steps": 101, "total_steps": 273, "loss": 1.129, "lr": 3.7324516058101454e-05, "epoch": 0.3694558756287151, "percentage": 37.0, "elapsed_time": "6:05:28", "remaining_time": "10:22:22"}
|
102 |
+
{"current_steps": 102, "total_steps": 273, "loss": 1.15, "lr": 3.705978266902409e-05, "epoch": 0.3731138545953361, "percentage": 37.36, "elapsed_time": "6:09:03", "remaining_time": "10:18:43"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec6e8a251074042cdace10f0b574cab736920ef113b4fda44123d72428005f23
|
3 |
+
size 7736
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|