Hugging Face's logo

quockhangdev
/
fastvilr-checkpoints

Safetensors
Model card Files
xet
 Community
quockhangdev commited on
Commit
0384283
·
verified ·
1 Parent(s): c342d82

Qwen3-Embedding-4B-peft-vilegal-stage2-ok

Browse files
Files changed (43) hide show
  1. .gitattributes +2 -0
  2. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/1_Pooling/config.json +5 -0
  3. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/README.md +0 -0
  4. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/added_tokens.json +24 -0
  5. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/1_Pooling/config.json +5 -0
  6. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/README.md +0 -0
  7. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/added_tokens.json +24 -0
  8. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/config.json +73 -0
  9. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/config_sentence_transformers.json +14 -0
  10. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/merges.txt +0 -0
  11. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model-00001-of-00004.safetensors +3 -0
  12. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model-00002-of-00004.safetensors +3 -0
  13. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model-00003-of-00004.safetensors +3 -0
  14. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model-00004-of-00004.safetensors +3 -0
  15. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model.safetensors.index.json +909 -0
  16. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/modules.json +20 -0
  17. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/optimizer.pt +3 -0
  18. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/rng_state_0.pth +3 -0
  19. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/rng_state_1.pth +3 -0
  20. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/rng_state_2.pth +3 -0
  21. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/rng_state_3.pth +3 -0
  22. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/scheduler.pt +3 -0
  23. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/sentence_bert_config.json +10 -0
  24. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/special_tokens_map.json +16 -0
  25. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/tokenizer.json +3 -0
  26. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/tokenizer_config.json +194 -0
  27. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/trainer_state.json +62 -0
  28. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/training_args.bin +3 -0
  29. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/vocab.json +0 -0
  30. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/config.json +73 -0
  31. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/config_sentence_transformers.json +14 -0
  32. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/merges.txt +0 -0
  33. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model-00001-of-00004.safetensors +3 -0
  34. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model-00002-of-00004.safetensors +3 -0
  35. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model-00003-of-00004.safetensors +3 -0
  36. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model-00004-of-00004.safetensors +3 -0
  37. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model.safetensors.index.json +909 -0
  38. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/modules.json +20 -0
  39. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/sentence_bert_config.json +10 -0
  40. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/special_tokens_map.json +16 -0
  41. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/tokenizer.json +3 -0
  42. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/tokenizer_config.json +194 -0
  43. Qwen3-Embedding-4B-peft-vilegal-stage2-ok/vocab.json +0 -0
.gitattributes CHANGED
@@ -51,3 +51,5 @@ Qwen3-Embedding-4B-peft-vilegal-stage1-adapter/checkpoint-123/tokenizer.json fil
51
  Qwen3-Embedding-4B-peft-vilegal-stage1-adapter/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
  Qwen3-Embedding-4B-peft-vilegal-stage1-adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
  Qwen3-Embedding-4B-peft-vilegal-stage1-ok/hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
51
  Qwen3-Embedding-4B-peft-vilegal-stage1-adapter/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
  Qwen3-Embedding-4B-peft-vilegal-stage1-adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
  Qwen3-Embedding-4B-peft-vilegal-stage1-ok/hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
+ Qwen3-Embedding-4B-peft-vilegal-stage2-ok/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/1_Pooling/config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "embedding_dimension": 2560,
3
+ "pooling_mode": "lasttoken",
4
+ "include_prompt": true
5
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/README.md ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/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
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/1_Pooling/config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "embedding_dimension": 2560,
3
+ "pooling_mode": "lasttoken",
4
+ "include_prompt": true
5
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/README.md ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/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
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3Model"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_parameters": {
61
+ "rope_theta": 1000000,
62
+ "rope_type": "default"
63
+ },
64
+ "rope_scaling": null,
65
+ "rope_theta": 10000.0,
66
+ "sliding_window": null,
67
+ "tie_word_embeddings": true,
68
+ "torch_dtype": "float32",
69
+ "transformers_version": "4.51.3",
70
+ "use_cache": true,
71
+ "use_sliding_window": false,
72
+ "vocab_size": 151665
73
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "pytorch": "2.9.0+cu130",
4
+ "sentence_transformers": "5.4.1",
5
+ "transformers": "4.51.3"
6
+ },
7
+ "default_prompt_name": null,
8
+ "model_type": "SentenceTransformer",
9
+ "prompts": {
10
+ "document": "",
11
+ "query": ""
12
+ },
13
+ "similarity_fn_name": "cosine"
14
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b037459c469b7e18e11408e985185ee3ad68020301782063ee76cbcae7e7a8
3
+ size 4903055136
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c68c34394a2609aac185f9ed6c8024dee421b0d737366824aa848b03cfc9a6
3
+ size 4966743104
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce2793ef85628acdefba8f17c21f31618ef30c9d166fb633645073f62da3e4
3
+ size 4966743136
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d901e095f196f94764fc9a58db151ef6310daea5f15d495d64e5bf2e9d346e8e
3
+ size 1316722960
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/model.safetensors.index.json ADDED
@@ -0,0 +1,909 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16153157632
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
9
+ "layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
10
+ "layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
11
+ "layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
12
+ "layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
13
+ "layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
14
+ "layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
15
+ "layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
16
+ "layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
17
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
19
+ "layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
20
+ "layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
21
+ "layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
22
+ "layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
23
+ "layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
24
+ "layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
25
+ "layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
26
+ "layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
27
+ "layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
28
+ "layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
29
+ "layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
30
+ "layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
31
+ "layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
32
+ "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
33
+ "layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
34
+ "layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
35
+ "layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
36
+ "layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
37
+ "layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
38
+ "layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
39
+ "layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
40
+ "layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
41
+ "layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
42
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
43
+ "layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
44
+ "layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
45
+ "layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
46
+ "layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
47
+ "layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
48
+ "layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
49
+ "layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
50
+ "layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
51
+ "layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
52
+ "layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
53
+ "layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
54
+ "layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
55
+ "layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
56
+ "layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
57
+ "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
59
+ "layers.10.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
60
+ "layers.10.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
61
+ "layers.10.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
62
+ "layers.10.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
63
+ "layers.10.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
64
+ "layers.10.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
65
+ "layers.10.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
66
+ "layers.10.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
67
+ "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
69
+ "layers.10.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
70
+ "layers.10.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
71
+ "layers.10.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
72
+ "layers.10.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
73
+ "layers.10.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
74
+ "layers.10.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
75
+ "layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
76
+ "layers.10.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
77
+ "layers.10.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
78
+ "layers.10.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
79
+ "layers.10.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
80
+ "layers.10.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
81
+ "layers.10.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
82
+ "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
83
+ "layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
84
+ "layers.11.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
85
+ "layers.11.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
86
+ "layers.11.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
87
+ "layers.11.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
88
+ "layers.11.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
89
+ "layers.11.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
90
+ "layers.11.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
91
+ "layers.11.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
92
+ "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
94
+ "layers.11.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
95
+ "layers.11.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
96
+ "layers.11.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
97
+ "layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
98
+ "layers.11.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
99
+ "layers.11.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
100
+ "layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
101
+ "layers.11.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
102
+ "layers.11.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
103
+ "layers.11.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
104
+ "layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
105
+ "layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
106
+ "layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
107
+ "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
109
+ "layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
110
+ "layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
111
+ "layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
112
+ "layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
113
+ "layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
114
+ "layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
115
+ "layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
116
+ "layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
117
+ "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
119
+ "layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
120
+ "layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
121
+ "layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
122
+ "layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
123
+ "layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
124
+ "layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
125
+ "layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
126
+ "layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
127
+ "layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
128
+ "layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
129
+ "layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
130
+ "layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
131
+ "layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
132
+ "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
133
+ "layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
134
+ "layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
135
+ "layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
136
+ "layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
137
+ "layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
138
+ "layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
139
+ "layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
140
+ "layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
141
+ "layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
142
+ "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
143
+ "layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
144
+ "layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
145
+ "layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
146
+ "layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
147
+ "layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
148
+ "layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
149
+ "layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
150
+ "layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
151
+ "layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
152
+ "layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
153
+ "layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
154
+ "layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
155
+ "layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
156
+ "layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
157
+ "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
158
+ "layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
159
+ "layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
160
+ "layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
161
+ "layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
162
+ "layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
163
+ "layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
164
+ "layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
165
+ "layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
166
+ "layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
167
+ "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
168
+ "layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
169
+ "layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
170
+ "layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
171
+ "layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
172
+ "layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
173
+ "layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
174
+ "layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
175
+ "layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
176
+ "layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
177
+ "layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
178
+ "layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
179
+ "layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
180
+ "layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
181
+ "layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
182
+ "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
183
+ "layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
184
+ "layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
185
+ "layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
186
+ "layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
187
+ "layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
188
+ "layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
189
+ "layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
190
+ "layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
191
+ "layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
192
+ "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
193
+ "layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
194
+ "layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
195
+ "layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
196
+ "layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
197
+ "layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
198
+ "layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
199
+ "layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
200
+ "layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
201
+ "layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
202
+ "layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
203
+ "layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
204
+ "layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
205
+ "layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
206
+ "layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
207
+ "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
208
+ "layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
209
+ "layers.16.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
210
+ "layers.16.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
211
+ "layers.16.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
212
+ "layers.16.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
213
+ "layers.16.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
214
+ "layers.16.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
215
+ "layers.16.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
216
+ "layers.16.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
217
+ "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
218
+ "layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
219
+ "layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
220
+ "layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
221
+ "layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
222
+ "layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
223
+ "layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
224
+ "layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
225
+ "layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
226
+ "layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
227
+ "layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
228
+ "layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
229
+ "layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
230
+ "layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
231
+ "layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
232
+ "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
233
+ "layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
234
+ "layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
235
+ "layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
236
+ "layers.17.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
237
+ "layers.17.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
238
+ "layers.17.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
239
+ "layers.17.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
240
+ "layers.17.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
241
+ "layers.17.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
242
+ "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
243
+ "layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
244
+ "layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
245
+ "layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
246
+ "layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
247
+ "layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
248
+ "layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
249
+ "layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
250
+ "layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
251
+ "layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
252
+ "layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
253
+ "layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
254
+ "layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
255
+ "layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
256
+ "layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
257
+ "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
258
+ "layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
259
+ "layers.18.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
260
+ "layers.18.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
261
+ "layers.18.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
262
+ "layers.18.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
263
+ "layers.18.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
264
+ "layers.18.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
265
+ "layers.18.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
266
+ "layers.18.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
267
+ "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
268
+ "layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
269
+ "layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
270
+ "layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
271
+ "layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
272
+ "layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
273
+ "layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
274
+ "layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
275
+ "layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
276
+ "layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
277
+ "layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
278
+ "layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
279
+ "layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
280
+ "layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
281
+ "layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
282
+ "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
283
+ "layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
284
+ "layers.19.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
285
+ "layers.19.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
286
+ "layers.19.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
287
+ "layers.19.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
288
+ "layers.19.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
289
+ "layers.19.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
290
+ "layers.19.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
291
+ "layers.19.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
292
+ "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
294
+ "layers.19.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
295
+ "layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
296
+ "layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
297
+ "layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
298
+ "layers.19.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
299
+ "layers.19.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
300
+ "layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
301
+ "layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
302
+ "layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
303
+ "layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
304
+ "layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
305
+ "layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
306
+ "layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
307
+ "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
308
+ "layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
309
+ "layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
310
+ "layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
311
+ "layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
312
+ "layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
313
+ "layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
314
+ "layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
315
+ "layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
316
+ "layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
317
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
318
+ "layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
319
+ "layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
320
+ "layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
321
+ "layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
322
+ "layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
323
+ "layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
324
+ "layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
325
+ "layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
326
+ "layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
327
+ "layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
328
+ "layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
329
+ "layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
330
+ "layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
331
+ "layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
332
+ "layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
333
+ "layers.20.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
334
+ "layers.20.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
335
+ "layers.20.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
336
+ "layers.20.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
337
+ "layers.20.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
338
+ "layers.20.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
339
+ "layers.20.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
340
+ "layers.20.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
341
+ "layers.20.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
342
+ "layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
343
+ "layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
344
+ "layers.20.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
345
+ "layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
346
+ "layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
347
+ "layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
348
+ "layers.20.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
349
+ "layers.20.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
350
+ "layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
351
+ "layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
352
+ "layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
353
+ "layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
354
+ "layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
355
+ "layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
356
+ "layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
357
+ "layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
358
+ "layers.21.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
359
+ "layers.21.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
360
+ "layers.21.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
361
+ "layers.21.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
362
+ "layers.21.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
363
+ "layers.21.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
364
+ "layers.21.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
365
+ "layers.21.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
366
+ "layers.21.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
367
+ "layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
368
+ "layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
369
+ "layers.21.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
370
+ "layers.21.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
371
+ "layers.21.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
372
+ "layers.21.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
373
+ "layers.21.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
374
+ "layers.21.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
375
+ "layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
376
+ "layers.21.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
377
+ "layers.21.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
378
+ "layers.21.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
379
+ "layers.21.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
380
+ "layers.21.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
381
+ "layers.21.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
382
+ "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
383
+ "layers.22.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
384
+ "layers.22.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
385
+ "layers.22.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
386
+ "layers.22.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
387
+ "layers.22.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
388
+ "layers.22.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
389
+ "layers.22.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
390
+ "layers.22.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
391
+ "layers.22.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
392
+ "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
393
+ "layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
394
+ "layers.22.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
395
+ "layers.22.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
396
+ "layers.22.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
397
+ "layers.22.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
398
+ "layers.22.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
399
+ "layers.22.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
400
+ "layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
401
+ "layers.22.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
402
+ "layers.22.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
403
+ "layers.22.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
404
+ "layers.22.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
405
+ "layers.22.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
406
+ "layers.22.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
407
+ "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
408
+ "layers.23.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
409
+ "layers.23.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
410
+ "layers.23.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
411
+ "layers.23.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
412
+ "layers.23.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
413
+ "layers.23.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
414
+ "layers.23.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
415
+ "layers.23.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
416
+ "layers.23.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
417
+ "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
418
+ "layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
419
+ "layers.23.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
420
+ "layers.23.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
421
+ "layers.23.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
422
+ "layers.23.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
423
+ "layers.23.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
424
+ "layers.23.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
425
+ "layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
426
+ "layers.23.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
427
+ "layers.23.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
428
+ "layers.23.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
429
+ "layers.23.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
430
+ "layers.23.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
431
+ "layers.23.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
432
+ "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
433
+ "layers.24.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
434
+ "layers.24.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
435
+ "layers.24.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
436
+ "layers.24.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
437
+ "layers.24.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
438
+ "layers.24.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
439
+ "layers.24.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
440
+ "layers.24.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
441
+ "layers.24.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
442
+ "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
443
+ "layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
444
+ "layers.24.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
445
+ "layers.24.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
446
+ "layers.24.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
447
+ "layers.24.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
448
+ "layers.24.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
449
+ "layers.24.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
450
+ "layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
451
+ "layers.24.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
452
+ "layers.24.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
453
+ "layers.24.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
454
+ "layers.24.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
455
+ "layers.24.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
456
+ "layers.24.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
457
+ "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
458
+ "layers.25.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
459
+ "layers.25.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
460
+ "layers.25.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
461
+ "layers.25.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
462
+ "layers.25.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
463
+ "layers.25.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
464
+ "layers.25.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
465
+ "layers.25.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
466
+ "layers.25.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
467
+ "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
468
+ "layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
469
+ "layers.25.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
470
+ "layers.25.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
471
+ "layers.25.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
472
+ "layers.25.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
473
+ "layers.25.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
474
+ "layers.25.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
475
+ "layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
476
+ "layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
477
+ "layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
478
+ "layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
479
+ "layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
480
+ "layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
481
+ "layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
482
+ "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
483
+ "layers.26.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
484
+ "layers.26.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
485
+ "layers.26.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
486
+ "layers.26.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
487
+ "layers.26.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
488
+ "layers.26.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
489
+ "layers.26.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
490
+ "layers.26.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
491
+ "layers.26.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
492
+ "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
493
+ "layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
494
+ "layers.26.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
495
+ "layers.26.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
496
+ "layers.26.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
497
+ "layers.26.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
498
+ "layers.26.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
499
+ "layers.26.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
500
+ "layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
501
+ "layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
502
+ "layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
503
+ "layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
504
+ "layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
505
+ "layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
506
+ "layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
507
+ "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
508
+ "layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
509
+ "layers.27.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
510
+ "layers.27.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
511
+ "layers.27.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
512
+ "layers.27.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
513
+ "layers.27.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
514
+ "layers.27.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
515
+ "layers.27.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
516
+ "layers.27.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
517
+ "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
518
+ "layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
519
+ "layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
520
+ "layers.27.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
521
+ "layers.27.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
522
+ "layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
523
+ "layers.27.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
524
+ "layers.27.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
525
+ "layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
526
+ "layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
527
+ "layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
528
+ "layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
529
+ "layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
530
+ "layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
531
+ "layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
532
+ "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
533
+ "layers.28.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
534
+ "layers.28.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
535
+ "layers.28.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
536
+ "layers.28.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
537
+ "layers.28.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
538
+ "layers.28.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
539
+ "layers.28.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
540
+ "layers.28.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
541
+ "layers.28.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
542
+ "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
543
+ "layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
544
+ "layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
545
+ "layers.28.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
546
+ "layers.28.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
547
+ "layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
548
+ "layers.28.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
549
+ "layers.28.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
550
+ "layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
551
+ "layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
552
+ "layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
553
+ "layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
554
+ "layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
555
+ "layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
556
+ "layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
557
+ "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
558
+ "layers.29.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
559
+ "layers.29.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
560
+ "layers.29.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
561
+ "layers.29.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
562
+ "layers.29.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
563
+ "layers.29.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
564
+ "layers.29.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
565
+ "layers.29.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
566
+ "layers.29.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
567
+ "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
568
+ "layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
569
+ "layers.29.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
570
+ "layers.29.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
571
+ "layers.29.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
572
+ "layers.29.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
573
+ "layers.29.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
574
+ "layers.29.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
575
+ "layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
576
+ "layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
577
+ "layers.29.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
578
+ "layers.29.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
579
+ "layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
580
+ "layers.29.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
581
+ "layers.29.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
582
+ "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
583
+ "layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
584
+ "layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
585
+ "layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
586
+ "layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
587
+ "layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
588
+ "layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
589
+ "layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
590
+ "layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
591
+ "layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
592
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
593
+ "layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
594
+ "layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
595
+ "layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
596
+ "layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
597
+ "layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
598
+ "layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
599
+ "layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
600
+ "layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
601
+ "layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
602
+ "layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
603
+ "layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
604
+ "layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
605
+ "layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
606
+ "layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
607
+ "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
608
+ "layers.30.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
609
+ "layers.30.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
610
+ "layers.30.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
611
+ "layers.30.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
612
+ "layers.30.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
613
+ "layers.30.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
614
+ "layers.30.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
615
+ "layers.30.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
616
+ "layers.30.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
617
+ "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
618
+ "layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
619
+ "layers.30.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
620
+ "layers.30.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
621
+ "layers.30.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
622
+ "layers.30.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
623
+ "layers.30.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
624
+ "layers.30.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
625
+ "layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
626
+ "layers.30.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
627
+ "layers.30.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
628
+ "layers.30.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
629
+ "layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
630
+ "layers.30.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
631
+ "layers.30.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
632
+ "layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
633
+ "layers.31.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
634
+ "layers.31.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
635
+ "layers.31.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
636
+ "layers.31.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
637
+ "layers.31.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
638
+ "layers.31.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
639
+ "layers.31.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
640
+ "layers.31.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
641
+ "layers.31.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
642
+ "layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
643
+ "layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
644
+ "layers.31.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
645
+ "layers.31.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
646
+ "layers.31.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
647
+ "layers.31.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
648
+ "layers.31.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
649
+ "layers.31.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
650
+ "layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
651
+ "layers.31.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
652
+ "layers.31.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
653
+ "layers.31.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
654
+ "layers.31.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
655
+ "layers.31.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
656
+ "layers.31.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
657
+ "layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
658
+ "layers.32.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
659
+ "layers.32.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
660
+ "layers.32.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
661
+ "layers.32.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
662
+ "layers.32.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
663
+ "layers.32.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
664
+ "layers.32.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
665
+ "layers.32.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
666
+ "layers.32.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
667
+ "layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
668
+ "layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
669
+ "layers.32.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
670
+ "layers.32.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
671
+ "layers.32.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
672
+ "layers.32.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
673
+ "layers.32.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
674
+ "layers.32.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
675
+ "layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
676
+ "layers.32.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
677
+ "layers.32.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
678
+ "layers.32.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
679
+ "layers.32.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
680
+ "layers.32.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
681
+ "layers.32.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
682
+ "layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
683
+ "layers.33.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
684
+ "layers.33.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
685
+ "layers.33.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
686
+ "layers.33.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
687
+ "layers.33.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
688
+ "layers.33.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
689
+ "layers.33.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
690
+ "layers.33.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
691
+ "layers.33.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
692
+ "layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
693
+ "layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
694
+ "layers.33.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
695
+ "layers.33.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
696
+ "layers.33.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
697
+ "layers.33.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
698
+ "layers.33.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
699
+ "layers.33.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
700
+ "layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
701
+ "layers.33.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
702
+ "layers.33.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
703
+ "layers.33.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
704
+ "layers.33.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
705
+ "layers.33.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
706
+ "layers.33.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
707
+ "layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
708
+ "layers.34.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
709
+ "layers.34.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
710
+ "layers.34.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
711
+ "layers.34.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
712
+ "layers.34.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
713
+ "layers.34.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
714
+ "layers.34.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
715
+ "layers.34.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
716
+ "layers.34.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
717
+ "layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
718
+ "layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
719
+ "layers.34.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
720
+ "layers.34.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
721
+ "layers.34.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
722
+ "layers.34.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
723
+ "layers.34.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
724
+ "layers.34.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
725
+ "layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
726
+ "layers.34.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
727
+ "layers.34.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
728
+ "layers.34.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
729
+ "layers.34.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
730
+ "layers.34.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
731
+ "layers.34.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
732
+ "layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
733
+ "layers.35.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
734
+ "layers.35.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
735
+ "layers.35.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
736
+ "layers.35.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
737
+ "layers.35.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
738
+ "layers.35.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
739
+ "layers.35.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
740
+ "layers.35.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
741
+ "layers.35.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
742
+ "layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
743
+ "layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
744
+ "layers.35.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
745
+ "layers.35.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
746
+ "layers.35.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
747
+ "layers.35.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
748
+ "layers.35.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
749
+ "layers.35.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
750
+ "layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
751
+ "layers.35.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
752
+ "layers.35.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
753
+ "layers.35.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
754
+ "layers.35.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
755
+ "layers.35.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
756
+ "layers.35.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
757
+ "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
758
+ "layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
759
+ "layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
760
+ "layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
761
+ "layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
762
+ "layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
763
+ "layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
764
+ "layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
765
+ "layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
766
+ "layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
767
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
768
+ "layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
769
+ "layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
770
+ "layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
771
+ "layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
772
+ "layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
773
+ "layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
774
+ "layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
775
+ "layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
776
+ "layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
777
+ "layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
778
+ "layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
779
+ "layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
780
+ "layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
781
+ "layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
782
+ "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
783
+ "layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
784
+ "layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
785
+ "layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
786
+ "layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
787
+ "layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
788
+ "layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
789
+ "layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
790
+ "layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
791
+ "layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
792
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
793
+ "layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
794
+ "layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
795
+ "layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
796
+ "layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
797
+ "layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
798
+ "layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
799
+ "layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
800
+ "layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
801
+ "layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
802
+ "layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
803
+ "layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
804
+ "layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
805
+ "layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
806
+ "layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
807
+ "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
808
+ "layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
809
+ "layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
810
+ "layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
811
+ "layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
812
+ "layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
813
+ "layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
814
+ "layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
815
+ "layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
816
+ "layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
817
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
818
+ "layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
819
+ "layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
820
+ "layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
821
+ "layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
822
+ "layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
823
+ "layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
824
+ "layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
825
+ "layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
826
+ "layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
827
+ "layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
828
+ "layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
829
+ "layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
830
+ "layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
831
+ "layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
832
+ "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
833
+ "layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
834
+ "layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
835
+ "layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
836
+ "layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
837
+ "layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
838
+ "layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
839
+ "layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
840
+ "layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
841
+ "layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
842
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
843
+ "layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
844
+ "layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
845
+ "layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
846
+ "layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
847
+ "layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
848
+ "layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
849
+ "layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
850
+ "layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
851
+ "layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
852
+ "layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
853
+ "layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
854
+ "layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
855
+ "layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
856
+ "layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
857
+ "layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
858
+ "layers.8.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
859
+ "layers.8.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
860
+ "layers.8.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
861
+ "layers.8.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
862
+ "layers.8.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
863
+ "layers.8.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
864
+ "layers.8.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
865
+ "layers.8.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
866
+ "layers.8.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
867
+ "layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
868
+ "layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
869
+ "layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
870
+ "layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
871
+ "layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
872
+ "layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
873
+ "layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
874
+ "layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
875
+ "layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
876
+ "layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
877
+ "layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
878
+ "layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
879
+ "layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
880
+ "layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
881
+ "layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
882
+ "layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
883
+ "layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
884
+ "layers.9.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
885
+ "layers.9.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
886
+ "layers.9.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
887
+ "layers.9.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
888
+ "layers.9.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
889
+ "layers.9.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
890
+ "layers.9.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
891
+ "layers.9.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
892
+ "layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
893
+ "layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
894
+ "layers.9.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
895
+ "layers.9.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
896
+ "layers.9.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
897
+ "layers.9.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
898
+ "layers.9.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
899
+ "layers.9.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
900
+ "layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
901
+ "layers.9.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
902
+ "layers.9.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
903
+ "layers.9.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
904
+ "layers.9.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
905
+ "layers.9.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
906
+ "layers.9.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
907
+ "norm.weight": "model-00004-of-00004.safetensors"
908
+ }
909
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.base.modules.transformer.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
19
+ }
20
+ ]
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a732c01dda4fe381f086ea7e10496eae74079eb6558e4fea565fa316664cfc49
3
+ size 132545355
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c7818cff7cfa15ac036e7d99de57c66f3546948d0318970e66adffa11ae356
3
+ size 15365
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf1ddbbdd3e2b2a4fc0d6c20dda2cf27bf4d264d3993040c2f54879967d25602
3
+ size 15365
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90bb92e49c2b434e9c058486aee05ba9e57c4012dd4b97815840ef2bc7680ce9
3
+ size 15365
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b767392d13194694df8f64661d6ff484ea9f25addbb98712993567a100e422
3
+ size 15365
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f4ebf3b42b4fff476d116c209c38a9436df0e2be767ad7d16baec3b6b3948e
3
+ size 1465
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/sentence_bert_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "transformer_task": "feature-extraction",
3
+ "modality_config": {
4
+ "text": {
5
+ "method": "forward",
6
+ "method_output_name": "last_hidden_state"
7
+ }
8
+ },
9
+ "module_output_name": "token_embeddings"
10
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|im_end|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f54d81d9580ee55fdc08d587cc480150361f58a6c60007a28fce7fd393b143e
3
+ size 11423210
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "151658": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "151659": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "151660": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "151661": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "151662": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "151663": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "151664": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ }
180
+ },
181
+ "backend": "tokenizers",
182
+ "bos_token": null,
183
+ "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",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<|im_end|>",
186
+ "errors": "replace",
187
+ "extra_special_tokens": {},
188
+ "is_local": true,
189
+ "model_max_length": 4096,
190
+ "pad_token": "<|endoftext|>",
191
+ "split_special_tokens": false,
192
+ "tokenizer_class": "Qwen2Tokenizer",
193
+ "unk_token": null
194
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 218,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.22935779816513763,
14
+ "grad_norm": 0.19518133997917175,
15
+ "learning_rate": 2e-05,
16
+ "loss": 0.6676,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.45871559633027525,
21
+ "grad_norm": 0.22115333378314972,
22
+ "learning_rate": 2e-05,
23
+ "loss": 0.5824,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.6880733944954128,
28
+ "grad_norm": 0.2794207036495209,
29
+ "learning_rate": 2e-05,
30
+ "loss": 0.555,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.9174311926605505,
35
+ "grad_norm": 0.2969784438610077,
36
+ "learning_rate": 2e-05,
37
+ "loss": 0.5253,
38
+ "step": 200
39
+ }
40
+ ],
41
+ "logging_steps": 50,
42
+ "max_steps": 218,
43
+ "num_input_tokens_seen": 0,
44
+ "num_train_epochs": 1,
45
+ "save_steps": 500,
46
+ "stateful_callbacks": {
47
+ "TrainerControl": {
48
+ "args": {
49
+ "should_epoch_stop": false,
50
+ "should_evaluate": false,
51
+ "should_log": false,
52
+ "should_save": true,
53
+ "should_training_stop": true
54
+ },
55
+ "attributes": {}
56
+ }
57
+ },
58
+ "total_flos": 0.0,
59
+ "train_batch_size": 512,
60
+ "trial_name": null,
61
+ "trial_params": null
62
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80541cbe6860371a0057ef090e9e8c6e7b65e45f40bb7c29c9b2a3baa408beaa
3
+ size 6353
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3Model"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_parameters": {
61
+ "rope_theta": 1000000,
62
+ "rope_type": "default"
63
+ },
64
+ "rope_scaling": null,
65
+ "rope_theta": 10000.0,
66
+ "sliding_window": null,
67
+ "tie_word_embeddings": true,
68
+ "torch_dtype": "float32",
69
+ "transformers_version": "4.51.3",
70
+ "use_cache": true,
71
+ "use_sliding_window": false,
72
+ "vocab_size": 151665
73
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "pytorch": "2.9.0+cu130",
4
+ "sentence_transformers": "5.4.1",
5
+ "transformers": "4.51.3"
6
+ },
7
+ "default_prompt_name": null,
8
+ "model_type": "SentenceTransformer",
9
+ "prompts": {
10
+ "document": "",
11
+ "query": ""
12
+ },
13
+ "similarity_fn_name": "cosine"
14
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b037459c469b7e18e11408e985185ee3ad68020301782063ee76cbcae7e7a8
3
+ size 4903055136
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c68c34394a2609aac185f9ed6c8024dee421b0d737366824aa848b03cfc9a6
3
+ size 4966743104
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce2793ef85628acdefba8f17c21f31618ef30c9d166fb633645073f62da3e4
3
+ size 4966743136
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d901e095f196f94764fc9a58db151ef6310daea5f15d495d64e5bf2e9d346e8e
3
+ size 1316722960
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/model.safetensors.index.json ADDED
@@ -0,0 +1,909 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16153157632
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
9
+ "layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
10
+ "layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
11
+ "layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
12
+ "layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
13
+ "layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
14
+ "layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
15
+ "layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
16
+ "layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
17
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
19
+ "layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
20
+ "layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
21
+ "layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
22
+ "layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
23
+ "layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
24
+ "layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
25
+ "layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
26
+ "layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
27
+ "layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
28
+ "layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
29
+ "layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
30
+ "layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
31
+ "layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
32
+ "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
33
+ "layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
34
+ "layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
35
+ "layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
36
+ "layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
37
+ "layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
38
+ "layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
39
+ "layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
40
+ "layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
41
+ "layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
42
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
43
+ "layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
44
+ "layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
45
+ "layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
46
+ "layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
47
+ "layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
48
+ "layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
49
+ "layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
50
+ "layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
51
+ "layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
52
+ "layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
53
+ "layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
54
+ "layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
55
+ "layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
56
+ "layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
57
+ "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
59
+ "layers.10.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
60
+ "layers.10.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
61
+ "layers.10.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
62
+ "layers.10.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
63
+ "layers.10.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
64
+ "layers.10.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
65
+ "layers.10.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
66
+ "layers.10.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
67
+ "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
69
+ "layers.10.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
70
+ "layers.10.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
71
+ "layers.10.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
72
+ "layers.10.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
73
+ "layers.10.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
74
+ "layers.10.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
75
+ "layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
76
+ "layers.10.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
77
+ "layers.10.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
78
+ "layers.10.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
79
+ "layers.10.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
80
+ "layers.10.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
81
+ "layers.10.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
82
+ "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
83
+ "layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
84
+ "layers.11.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
85
+ "layers.11.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
86
+ "layers.11.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
87
+ "layers.11.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
88
+ "layers.11.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
89
+ "layers.11.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
90
+ "layers.11.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
91
+ "layers.11.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
92
+ "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
94
+ "layers.11.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
95
+ "layers.11.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
96
+ "layers.11.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
97
+ "layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
98
+ "layers.11.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
99
+ "layers.11.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
100
+ "layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
101
+ "layers.11.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
102
+ "layers.11.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
103
+ "layers.11.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
104
+ "layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
105
+ "layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
106
+ "layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
107
+ "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
109
+ "layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
110
+ "layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
111
+ "layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
112
+ "layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
113
+ "layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
114
+ "layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
115
+ "layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
116
+ "layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
117
+ "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
119
+ "layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
120
+ "layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
121
+ "layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
122
+ "layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
123
+ "layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
124
+ "layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
125
+ "layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
126
+ "layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
127
+ "layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
128
+ "layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
129
+ "layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
130
+ "layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
131
+ "layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
132
+ "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
133
+ "layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
134
+ "layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
135
+ "layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
136
+ "layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
137
+ "layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
138
+ "layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
139
+ "layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
140
+ "layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
141
+ "layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
142
+ "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
143
+ "layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
144
+ "layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
145
+ "layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
146
+ "layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
147
+ "layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
148
+ "layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
149
+ "layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
150
+ "layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
151
+ "layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
152
+ "layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
153
+ "layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
154
+ "layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
155
+ "layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
156
+ "layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
157
+ "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
158
+ "layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
159
+ "layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
160
+ "layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
161
+ "layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
162
+ "layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
163
+ "layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
164
+ "layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
165
+ "layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
166
+ "layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
167
+ "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
168
+ "layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
169
+ "layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
170
+ "layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
171
+ "layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
172
+ "layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
173
+ "layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
174
+ "layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
175
+ "layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
176
+ "layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
177
+ "layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
178
+ "layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
179
+ "layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
180
+ "layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
181
+ "layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
182
+ "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
183
+ "layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
184
+ "layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
185
+ "layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
186
+ "layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
187
+ "layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
188
+ "layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
189
+ "layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
190
+ "layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
191
+ "layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
192
+ "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
193
+ "layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
194
+ "layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
195
+ "layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
196
+ "layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
197
+ "layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
198
+ "layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
199
+ "layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
200
+ "layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
201
+ "layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
202
+ "layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
203
+ "layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
204
+ "layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
205
+ "layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
206
+ "layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
207
+ "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
208
+ "layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
209
+ "layers.16.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
210
+ "layers.16.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
211
+ "layers.16.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
212
+ "layers.16.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
213
+ "layers.16.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
214
+ "layers.16.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
215
+ "layers.16.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
216
+ "layers.16.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
217
+ "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
218
+ "layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
219
+ "layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
220
+ "layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
221
+ "layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
222
+ "layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
223
+ "layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
224
+ "layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
225
+ "layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
226
+ "layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
227
+ "layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
228
+ "layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
229
+ "layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
230
+ "layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
231
+ "layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
232
+ "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
233
+ "layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
234
+ "layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
235
+ "layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
236
+ "layers.17.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
237
+ "layers.17.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
238
+ "layers.17.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
239
+ "layers.17.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
240
+ "layers.17.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
241
+ "layers.17.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
242
+ "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
243
+ "layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
244
+ "layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
245
+ "layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
246
+ "layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
247
+ "layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
248
+ "layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
249
+ "layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
250
+ "layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
251
+ "layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
252
+ "layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
253
+ "layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
254
+ "layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
255
+ "layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
256
+ "layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
257
+ "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
258
+ "layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
259
+ "layers.18.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
260
+ "layers.18.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
261
+ "layers.18.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
262
+ "layers.18.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
263
+ "layers.18.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
264
+ "layers.18.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
265
+ "layers.18.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
266
+ "layers.18.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
267
+ "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
268
+ "layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
269
+ "layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
270
+ "layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
271
+ "layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
272
+ "layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
273
+ "layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
274
+ "layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
275
+ "layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
276
+ "layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
277
+ "layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
278
+ "layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
279
+ "layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
280
+ "layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
281
+ "layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
282
+ "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
283
+ "layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
284
+ "layers.19.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
285
+ "layers.19.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
286
+ "layers.19.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
287
+ "layers.19.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
288
+ "layers.19.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
289
+ "layers.19.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
290
+ "layers.19.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
291
+ "layers.19.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
292
+ "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
294
+ "layers.19.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
295
+ "layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
296
+ "layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
297
+ "layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
298
+ "layers.19.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
299
+ "layers.19.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
300
+ "layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
301
+ "layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
302
+ "layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
303
+ "layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
304
+ "layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
305
+ "layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
306
+ "layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
307
+ "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
308
+ "layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
309
+ "layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
310
+ "layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
311
+ "layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
312
+ "layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
313
+ "layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
314
+ "layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
315
+ "layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
316
+ "layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
317
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
318
+ "layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
319
+ "layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
320
+ "layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
321
+ "layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
322
+ "layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
323
+ "layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
324
+ "layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
325
+ "layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
326
+ "layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
327
+ "layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
328
+ "layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
329
+ "layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
330
+ "layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
331
+ "layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
332
+ "layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
333
+ "layers.20.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
334
+ "layers.20.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
335
+ "layers.20.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
336
+ "layers.20.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
337
+ "layers.20.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
338
+ "layers.20.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
339
+ "layers.20.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
340
+ "layers.20.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
341
+ "layers.20.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
342
+ "layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
343
+ "layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
344
+ "layers.20.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
345
+ "layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
346
+ "layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
347
+ "layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
348
+ "layers.20.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
349
+ "layers.20.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
350
+ "layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
351
+ "layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
352
+ "layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
353
+ "layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
354
+ "layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
355
+ "layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
356
+ "layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
357
+ "layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
358
+ "layers.21.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
359
+ "layers.21.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
360
+ "layers.21.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
361
+ "layers.21.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
362
+ "layers.21.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
363
+ "layers.21.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
364
+ "layers.21.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
365
+ "layers.21.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
366
+ "layers.21.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
367
+ "layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
368
+ "layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
369
+ "layers.21.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
370
+ "layers.21.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
371
+ "layers.21.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
372
+ "layers.21.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
373
+ "layers.21.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
374
+ "layers.21.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
375
+ "layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
376
+ "layers.21.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
377
+ "layers.21.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
378
+ "layers.21.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
379
+ "layers.21.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
380
+ "layers.21.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
381
+ "layers.21.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
382
+ "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
383
+ "layers.22.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
384
+ "layers.22.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
385
+ "layers.22.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
386
+ "layers.22.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
387
+ "layers.22.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
388
+ "layers.22.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
389
+ "layers.22.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
390
+ "layers.22.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
391
+ "layers.22.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
392
+ "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
393
+ "layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
394
+ "layers.22.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
395
+ "layers.22.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
396
+ "layers.22.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
397
+ "layers.22.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
398
+ "layers.22.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
399
+ "layers.22.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
400
+ "layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
401
+ "layers.22.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
402
+ "layers.22.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
403
+ "layers.22.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
404
+ "layers.22.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
405
+ "layers.22.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
406
+ "layers.22.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
407
+ "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
408
+ "layers.23.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
409
+ "layers.23.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
410
+ "layers.23.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
411
+ "layers.23.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
412
+ "layers.23.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
413
+ "layers.23.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
414
+ "layers.23.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
415
+ "layers.23.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
416
+ "layers.23.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
417
+ "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
418
+ "layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
419
+ "layers.23.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
420
+ "layers.23.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
421
+ "layers.23.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
422
+ "layers.23.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
423
+ "layers.23.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
424
+ "layers.23.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
425
+ "layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
426
+ "layers.23.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
427
+ "layers.23.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
428
+ "layers.23.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
429
+ "layers.23.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
430
+ "layers.23.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
431
+ "layers.23.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
432
+ "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
433
+ "layers.24.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
434
+ "layers.24.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
435
+ "layers.24.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
436
+ "layers.24.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
437
+ "layers.24.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
438
+ "layers.24.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
439
+ "layers.24.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
440
+ "layers.24.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
441
+ "layers.24.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
442
+ "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
443
+ "layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
444
+ "layers.24.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
445
+ "layers.24.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
446
+ "layers.24.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
447
+ "layers.24.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
448
+ "layers.24.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
449
+ "layers.24.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
450
+ "layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
451
+ "layers.24.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
452
+ "layers.24.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
453
+ "layers.24.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
454
+ "layers.24.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
455
+ "layers.24.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
456
+ "layers.24.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
457
+ "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
458
+ "layers.25.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
459
+ "layers.25.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
460
+ "layers.25.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
461
+ "layers.25.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
462
+ "layers.25.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
463
+ "layers.25.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
464
+ "layers.25.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
465
+ "layers.25.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
466
+ "layers.25.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
467
+ "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
468
+ "layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
469
+ "layers.25.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
470
+ "layers.25.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
471
+ "layers.25.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
472
+ "layers.25.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
473
+ "layers.25.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
474
+ "layers.25.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
475
+ "layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
476
+ "layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
477
+ "layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
478
+ "layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
479
+ "layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
480
+ "layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
481
+ "layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
482
+ "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
483
+ "layers.26.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
484
+ "layers.26.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
485
+ "layers.26.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
486
+ "layers.26.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
487
+ "layers.26.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
488
+ "layers.26.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
489
+ "layers.26.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
490
+ "layers.26.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
491
+ "layers.26.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
492
+ "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
493
+ "layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
494
+ "layers.26.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
495
+ "layers.26.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
496
+ "layers.26.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
497
+ "layers.26.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
498
+ "layers.26.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
499
+ "layers.26.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
500
+ "layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
501
+ "layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
502
+ "layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
503
+ "layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
504
+ "layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
505
+ "layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
506
+ "layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
507
+ "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
508
+ "layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
509
+ "layers.27.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
510
+ "layers.27.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
511
+ "layers.27.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
512
+ "layers.27.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
513
+ "layers.27.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
514
+ "layers.27.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
515
+ "layers.27.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
516
+ "layers.27.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
517
+ "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
518
+ "layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
519
+ "layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
520
+ "layers.27.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
521
+ "layers.27.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
522
+ "layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
523
+ "layers.27.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
524
+ "layers.27.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
525
+ "layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
526
+ "layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
527
+ "layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
528
+ "layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
529
+ "layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
530
+ "layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
531
+ "layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
532
+ "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
533
+ "layers.28.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
534
+ "layers.28.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
535
+ "layers.28.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
536
+ "layers.28.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
537
+ "layers.28.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
538
+ "layers.28.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
539
+ "layers.28.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
540
+ "layers.28.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
541
+ "layers.28.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
542
+ "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
543
+ "layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
544
+ "layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
545
+ "layers.28.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
546
+ "layers.28.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
547
+ "layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
548
+ "layers.28.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
549
+ "layers.28.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
550
+ "layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
551
+ "layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
552
+ "layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
553
+ "layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
554
+ "layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
555
+ "layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
556
+ "layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
557
+ "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
558
+ "layers.29.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
559
+ "layers.29.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
560
+ "layers.29.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
561
+ "layers.29.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
562
+ "layers.29.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
563
+ "layers.29.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
564
+ "layers.29.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
565
+ "layers.29.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
566
+ "layers.29.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
567
+ "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
568
+ "layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
569
+ "layers.29.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
570
+ "layers.29.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
571
+ "layers.29.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
572
+ "layers.29.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
573
+ "layers.29.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
574
+ "layers.29.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
575
+ "layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
576
+ "layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
577
+ "layers.29.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
578
+ "layers.29.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
579
+ "layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
580
+ "layers.29.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
581
+ "layers.29.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
582
+ "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
583
+ "layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
584
+ "layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
585
+ "layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
586
+ "layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
587
+ "layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
588
+ "layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
589
+ "layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
590
+ "layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
591
+ "layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
592
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
593
+ "layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
594
+ "layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
595
+ "layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
596
+ "layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
597
+ "layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
598
+ "layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
599
+ "layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
600
+ "layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
601
+ "layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
602
+ "layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
603
+ "layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
604
+ "layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
605
+ "layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
606
+ "layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
607
+ "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
608
+ "layers.30.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
609
+ "layers.30.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
610
+ "layers.30.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
611
+ "layers.30.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
612
+ "layers.30.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
613
+ "layers.30.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
614
+ "layers.30.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
615
+ "layers.30.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
616
+ "layers.30.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
617
+ "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
618
+ "layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
619
+ "layers.30.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
620
+ "layers.30.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
621
+ "layers.30.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
622
+ "layers.30.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
623
+ "layers.30.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
624
+ "layers.30.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
625
+ "layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
626
+ "layers.30.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
627
+ "layers.30.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
628
+ "layers.30.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
629
+ "layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
630
+ "layers.30.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
631
+ "layers.30.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
632
+ "layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
633
+ "layers.31.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
634
+ "layers.31.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
635
+ "layers.31.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
636
+ "layers.31.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
637
+ "layers.31.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
638
+ "layers.31.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
639
+ "layers.31.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
640
+ "layers.31.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
641
+ "layers.31.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
642
+ "layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
643
+ "layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
644
+ "layers.31.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
645
+ "layers.31.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
646
+ "layers.31.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
647
+ "layers.31.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
648
+ "layers.31.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
649
+ "layers.31.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
650
+ "layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
651
+ "layers.31.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
652
+ "layers.31.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
653
+ "layers.31.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
654
+ "layers.31.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
655
+ "layers.31.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
656
+ "layers.31.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
657
+ "layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
658
+ "layers.32.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
659
+ "layers.32.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
660
+ "layers.32.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
661
+ "layers.32.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
662
+ "layers.32.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
663
+ "layers.32.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
664
+ "layers.32.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
665
+ "layers.32.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
666
+ "layers.32.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
667
+ "layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
668
+ "layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
669
+ "layers.32.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
670
+ "layers.32.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
671
+ "layers.32.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
672
+ "layers.32.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
673
+ "layers.32.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
674
+ "layers.32.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
675
+ "layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
676
+ "layers.32.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
677
+ "layers.32.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
678
+ "layers.32.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
679
+ "layers.32.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
680
+ "layers.32.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
681
+ "layers.32.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
682
+ "layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
683
+ "layers.33.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
684
+ "layers.33.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
685
+ "layers.33.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
686
+ "layers.33.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
687
+ "layers.33.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
688
+ "layers.33.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
689
+ "layers.33.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
690
+ "layers.33.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
691
+ "layers.33.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
692
+ "layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
693
+ "layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
694
+ "layers.33.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
695
+ "layers.33.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
696
+ "layers.33.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
697
+ "layers.33.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
698
+ "layers.33.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
699
+ "layers.33.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
700
+ "layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
701
+ "layers.33.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
702
+ "layers.33.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
703
+ "layers.33.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
704
+ "layers.33.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
705
+ "layers.33.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
706
+ "layers.33.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
707
+ "layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
708
+ "layers.34.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
709
+ "layers.34.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
710
+ "layers.34.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
711
+ "layers.34.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
712
+ "layers.34.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
713
+ "layers.34.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
714
+ "layers.34.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
715
+ "layers.34.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
716
+ "layers.34.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
717
+ "layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
718
+ "layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
719
+ "layers.34.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
720
+ "layers.34.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
721
+ "layers.34.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
722
+ "layers.34.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
723
+ "layers.34.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
724
+ "layers.34.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
725
+ "layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
726
+ "layers.34.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
727
+ "layers.34.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
728
+ "layers.34.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
729
+ "layers.34.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
730
+ "layers.34.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
731
+ "layers.34.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
732
+ "layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
733
+ "layers.35.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
734
+ "layers.35.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
735
+ "layers.35.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
736
+ "layers.35.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
737
+ "layers.35.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
738
+ "layers.35.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
739
+ "layers.35.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
740
+ "layers.35.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
741
+ "layers.35.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
742
+ "layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
743
+ "layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
744
+ "layers.35.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
745
+ "layers.35.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
746
+ "layers.35.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
747
+ "layers.35.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
748
+ "layers.35.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
749
+ "layers.35.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
750
+ "layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
751
+ "layers.35.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
752
+ "layers.35.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
753
+ "layers.35.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
754
+ "layers.35.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
755
+ "layers.35.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
756
+ "layers.35.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
757
+ "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
758
+ "layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
759
+ "layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
760
+ "layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
761
+ "layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
762
+ "layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
763
+ "layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
764
+ "layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
765
+ "layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
766
+ "layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
767
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
768
+ "layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
769
+ "layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
770
+ "layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
771
+ "layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
772
+ "layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
773
+ "layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
774
+ "layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
775
+ "layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
776
+ "layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
777
+ "layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
778
+ "layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
779
+ "layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
780
+ "layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
781
+ "layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
782
+ "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
783
+ "layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
784
+ "layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
785
+ "layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
786
+ "layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
787
+ "layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
788
+ "layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
789
+ "layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
790
+ "layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
791
+ "layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
792
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
793
+ "layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
794
+ "layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
795
+ "layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
796
+ "layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
797
+ "layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
798
+ "layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
799
+ "layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
800
+ "layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
801
+ "layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
802
+ "layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
803
+ "layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
804
+ "layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
805
+ "layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
806
+ "layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
807
+ "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
808
+ "layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
809
+ "layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
810
+ "layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
811
+ "layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
812
+ "layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
813
+ "layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
814
+ "layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
815
+ "layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
816
+ "layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
817
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
818
+ "layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
819
+ "layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
820
+ "layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
821
+ "layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
822
+ "layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
823
+ "layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
824
+ "layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
825
+ "layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
826
+ "layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
827
+ "layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
828
+ "layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
829
+ "layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
830
+ "layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
831
+ "layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
832
+ "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
833
+ "layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
834
+ "layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
835
+ "layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
836
+ "layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
837
+ "layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
838
+ "layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
839
+ "layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
840
+ "layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
841
+ "layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
842
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
843
+ "layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
844
+ "layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
845
+ "layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
846
+ "layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
847
+ "layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
848
+ "layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
849
+ "layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
850
+ "layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
851
+ "layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
852
+ "layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
853
+ "layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
854
+ "layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
855
+ "layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
856
+ "layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
857
+ "layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
858
+ "layers.8.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
859
+ "layers.8.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
860
+ "layers.8.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
861
+ "layers.8.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
862
+ "layers.8.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
863
+ "layers.8.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
864
+ "layers.8.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
865
+ "layers.8.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
866
+ "layers.8.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
867
+ "layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
868
+ "layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
869
+ "layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
870
+ "layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
871
+ "layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
872
+ "layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
873
+ "layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
874
+ "layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
875
+ "layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
876
+ "layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
877
+ "layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
878
+ "layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
879
+ "layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
880
+ "layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
881
+ "layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
882
+ "layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
883
+ "layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
884
+ "layers.9.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
885
+ "layers.9.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
886
+ "layers.9.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
887
+ "layers.9.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
888
+ "layers.9.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
889
+ "layers.9.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
890
+ "layers.9.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
891
+ "layers.9.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
892
+ "layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
893
+ "layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
894
+ "layers.9.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
895
+ "layers.9.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
896
+ "layers.9.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
897
+ "layers.9.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
898
+ "layers.9.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
899
+ "layers.9.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
900
+ "layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
901
+ "layers.9.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
902
+ "layers.9.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
903
+ "layers.9.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
904
+ "layers.9.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
905
+ "layers.9.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
906
+ "layers.9.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
907
+ "norm.weight": "model-00004-of-00004.safetensors"
908
+ }
909
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.base.modules.transformer.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
19
+ }
20
+ ]
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/sentence_bert_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "transformer_task": "feature-extraction",
3
+ "modality_config": {
4
+ "text": {
5
+ "method": "forward",
6
+ "method_output_name": "last_hidden_state"
7
+ }
8
+ },
9
+ "module_output_name": "token_embeddings"
10
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|im_end|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f54d81d9580ee55fdc08d587cc480150361f58a6c60007a28fce7fd393b143e
3
+ size 11423210
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "151658": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "151659": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "151660": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "151661": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "151662": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "151663": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "151664": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ }
180
+ },
181
+ "backend": "tokenizers",
182
+ "bos_token": null,
183
+ "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",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<|im_end|>",
186
+ "errors": "replace",
187
+ "extra_special_tokens": {},
188
+ "is_local": true,
189
+ "model_max_length": 4096,
190
+ "pad_token": "<|endoftext|>",
191
+ "split_special_tokens": false,
192
+ "tokenizer_class": "Qwen2Tokenizer",
193
+ "unk_token": null
194
+ }
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/vocab.json ADDED
The diff for this file is too large to render. See raw diff