Nekochu commited on
Commit
c58b93f
1 Parent(s): a7eac54
.gitattributes ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ trainer_log.jsonl filter=lfs diff=lfs merge=lfs -text
37
+ trainer_state.json filter=lfs diff=lfs merge=lfs -text
38
+ Luminia-13B-v3-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Luminia-13B-v3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Luminia-13B-v3-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a177fc0418ee402a1426c91be9315a68fed91395d3cf2a9555cc9346f3b2ed
3
+ size 7410072096
Luminia-13B-v3-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65f064e21ce901530a117231ceea472344041f5c061286fe4fd72021ebddd42
3
+ size 7865956896
README.md ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ model_creator: Nekochu
3
+ model_name: Luminia 13B v3
4
+ model_type: llama2
5
+ prompt_template: >-
6
+ Below is an instruction that describes a task. Write a response that
7
+ appropriately completes the request. ### Instruction: {Instruction} {summary} ### input: {category} ### Response: {prompt}
8
+ base_model: meta-llama/Llama-2-13b-chat-hf
9
+ library_name: peft
10
+ license: apache-2.0
11
+ inference: True
12
+ datasets:
13
+ - Nekochu/discord-unstable-diffusion-SD-prompts
14
+ - glaiveai/glaive-function-calling-v2
15
+ - TIGER-Lab/MathInstruct
16
+ - Open-Orca/SlimOrca
17
+ - GAIR/lima
18
+ - sahil2801/CodeAlpaca-20k
19
+ - garage-bAInd/Open-Platypus
20
+ language:
21
+ - en
22
+ widget:
23
+ - text: >
24
+ Below is an instruction that describes a task, paired with an input that
25
+ provides further context. Write a response that appropriately completes the
26
+ request.
27
+
28
+
29
+ ### Instruction:
30
+
31
+ Create stable diffusion metadata based on the given english description. Luminia
32
+
33
+
34
+ ### Input:
35
+
36
+ favorites and popular SFW
37
+
38
+
39
+ ### Response:
40
+ output:
41
+ text: Luminia, 1girl, solo, blonde hair, long hair,
42
+ tags:
43
+ - llama-factory
44
+ - lora
45
+ - generated_from_trainer
46
+ pipeline_tag: text-generation
47
+ model-index:
48
+ - name: Luminia-13B-v3
49
+ results: []
50
+ ---
51
+
52
+ <div style="display: flex;">
53
+ <div style="flex: 1;">
54
+ <img src="https://i.imgur.com/uyjdkhk.jpeg" alt="DALL-E 3 prompt: a single seed growing slowly in laboratory in a desert sand, the single little plant try fight to reach light sun, while a little cute kitty feel the plant, cute 8k anime, digitral art, close up" style="width: 90%; min-width: 380px; border: 2px solid #555; border-radius: 5px;">
55
+ </div>
56
+ <div style="flex: 1; text-align: left;">
57
+ <p style="font-family: 'Comic Sans MS', cursive, sans-serif; padding-left: 2px; padding-top: 10px;">Luminia v3 is good at reasoning to enchance Stable Diffusion prompt from short summary description, may output NSFW content.</p>
58
+ </div>
59
+ </div>
60
+
61
+ LoRa is include and Quants: exllamav2 [2.4bpw-h6](https://huggingface.co/Nekochu/Luminia-13B-v3/tree/2.4bpw-h6), [4.25bpw-h6](https://huggingface.co/Nekochu/Luminia-13B-v3/tree/4.25bpw-h6), [8.0bpw-h8](https://huggingface.co/Nekochu/Luminia-13B-v3/tree/8.0bpw-h8) | GGUF [Q4_K_M](https://huggingface.co/Nekochu/Luminia-13B-v3/blob/main/Luminia-13B-v3-Q4_K_M.gguf), [IQ4_NL](https://huggingface.co/Nekochu/Luminia-13B-v3/blob/main/Luminia-13B-v3-IQ4_NL.gguf) |
62
+
63
+ ## Prompt template: Alpaca
64
+
65
+ <details>
66
+ <summary>Output example tested In <i>text-generation-webui</i></summary>
67
+
68
+ | Input | base llama-2-chat | QLoRa |
69
+ |:---------:|:-------:|:---------:|
70
+ | [question]:<br><br> Create stable diffusion metadata based on the given english description. Luminia \n### Input:\n favorites and popular SFW | Answer:<br><br> Luminia, a mystical world of wonder and magic 🧝‍♀️✨ A place where technology and nature seamlessly blend together ... | Answer! <br><br> < lora:Luminari-10:0.8> Luminari, 1girl, solo, blonde hair, long hair, blue eyes, (black dress), looking at viewer, night sky, starry sky, constellation, smile, upper body, outdoors, forest, moon, tree, mountain, light particle .... |
71
+
72
+ Output prompt from QLoRa to [A1111/SD-WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui):
73
+
74
+ <div style="display: flex; justify-content: space-between;">
75
+ <div style="flex: 1; text-align: center;">
76
+ <img src="https://i.imgur.com/rNLaobj.png" alt="parameters image metadata: <lora:Luminari-10:0.8> Luminari, 1girl, solo, blonde hair, long hair, blue eyes, (black dress), looking at viewer, night sky, starry sky, constellation, smile, upper body, outdoors, forest, moon, tree, mountain, light particle, shine, sparkle, dark theme, fantasy, magic, goddess, celestial, nature, peaceful, serene, tranquil, mystical, enchanting, otherworldly, mysterious, captivating, alluring, beautiful, elegant, graceful, majestic, divine, powerful, epic, grand, sweeping, breathtaking, mesmerizing, magical, fantastical, wondrous, marvelous, extraordinary, magnificent, glorious, radiant, luminous, illumination, brilliance, glow, radiance, luminescence, brightness, splendor, glory, triumph, victory, achievement, honor, celebration, recognition, praise, admiration, appreciation, love, affection, devotion, loyalty, dedication, commitment, passion, intensity, drive, determination, energy, enthusiasm, excitement, joy, happiness, fulfillment, pleasure, enjoyment, satisfaction, delight, wonder, amazement, awe, curiosity, interest, intrigue, question, exploration, discovery, adventure, journey, path, road, trail, course, pursuit, challenge, obstacle, adversity, hardship, struggle, perseverance, resilience, tenacity, courage, bravery, heroism, inspiration, motivation, spirit, heart, soul, essence, creativity, imagination, dreams, aspirations, goals, ambition, vision, purpose, meaning, significance, relevance, importance, impact, influence, change, growth, development, evolution, improvement, progress, learning, knowledge, wisdom, insight, understanding, empathy, compassion, kindness, generosity, forgiveness, gratitude, humility, patience, tolerance, acceptance, diversity, inclusivity, unity, equality, justice, fairness, honesty, integrity, accountability, responsibility, morality, ethics, principles, values, beliefs, faith, hope, optimism,
77
+ Steps: 20, Sampler: Heun, CFG scale: 7, Seed: 479539365, Size: 512x512, Model hash: 84d76a0328, Model: epicrealism_naturalSinRC1VAE, Version: v1.7.0" style="width: 100%; min-width: 200px; display: block; margin: auto;">
78
+ </div>
79
+ <div style="flex: 1; text-align: center;">
80
+ <img src="https://i.imgur.com/hU8Ut4p.png" alt="parameters image metadata: <lora:Luminari-10:0.8> Luminari, 1girl, solo, blonde hair, long hair, blue eyes, (black dress), looking at viewer, night sky, starry sky, constellation, smile, upper body, outdoors, forest, moon, tree, mountain, light particle, shine, sparkle, dark theme, fantasy, magic, goddess, celestial, nature, peaceful, serene, tranquil, mystical, enchanting, otherworldly, mysterious, captivating, alluring, beautiful, elegant, graceful, majestic, divine, powerful, epic, grand, sweeping, breathtaking, mesmerizing, magical, fantastical, wondrous, marvelous, extraordinary, magnificent, glorious, radiant, luminous, illumination, brilliance, glow, radiance, luminescence, brightness, splendor, glory, triumph, victory, achievement, honor, celebration, recognition, praise, admiration, appreciation, love, affection, devotion, loyalty, dedication, commitment, passion, intensity, drive, determination, energy, enthusiasm, excitement, joy, happiness, fulfillment, pleasure, enjoyment, satisfaction, delight, wonder, amazement, awe, curiosity, interest, intrigue, question, exploration, discovery, adventure, journey, path, road, trail, course, pursuit, challenge, obstacle, adversity, hardship, struggle, perseverance, resilience, tenacity, courage, bravery, heroism, inspiration, motivation, spirit, heart, soul, essence, creativity, imagination, dreams, aspirations, goals, ambition, vision, purpose, meaning, significance, relevance, importance, impact, influence, change, growth, development, evolution, improvement, progress, learning, knowledge, wisdom, insight, understanding, empathy, compassion, kindness, generosity, forgiveness, gratitude, humility, patience, tolerance, acceptance, diversity, inclusivity, unity, equality, justice, fairness, honesty, integrity, accountability, responsibility, morality, ethics, principles, values, beliefs, faith, hope, optimism
81
+ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 959582434, Size: 512x512, Model hash: 84d76a0328, Model: epicrealism_naturalSinRC1VAE, Version: v1.7.0" style="width: 100%; min-width: 200px; display: block; margin: auto;">
82
+ </div>
83
+ </div>
84
+
85
+ </details>
86
+
87
+ ## Training Details
88
+
89
+ <details>
90
+ <summary>Click to see details</summary>
91
+
92
+ ### Model Description
93
+
94
+ - **Train by:** [Nekochu](https://huggingface.co/Nekochu), **Model type:** Llama, **Finetuned from model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf)**
95
+ - Continue from the base of LoRA Luminia-13B-v2-QLora
96
+
97
+ Know issue: [issue]
98
+
99
+ ### Trainer
100
+
101
+ - hiyouga/LLaMA-Efficient-Tuning
102
+
103
+ Hardware: QLoRA training OS Windows, Python 3.10.8, CUDA 12.1 on 24GB VRAM.
104
+
105
+ ### Training hyperparameters
106
+
107
+ The following hyperparameters were used during training:
108
+
109
+ - num_epochs: 1.0
110
+ - finetuning_type: lora
111
+ - quantization_bit: 4
112
+ - stage: sft
113
+ - learning_rate: 5e-05
114
+ - cutoff_len: 4096
115
+ - num_train_epochs: 3.0
116
+ - max_samples: 100000
117
+ - warmup_steps: 0
118
+ - train_batch_size: 1
119
+ - distributed_type: single-GPU
120
+ - num_devices: 1
121
+ - warmup_steps: 0
122
+ - rope_scaling: linear
123
+ - lora_rank: 32
124
+ - lora_target: all
125
+ - lora_dropout: 0.15
126
+ - bnb_4bit_compute_dtype: bfloat16
127
+ - seed: 42
128
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
129
+ - lr_scheduler_type: cosine
130
+
131
+ #### training_loss:
132
+ <div style="width: auto; margin-left: auto; margin-right: auto">
133
+ <img src="https://i.imgur.com/qhuPG6F.jpg" alt="Nekochu" style="width: 100%; min-width: 400px; display: block; margin: auto;">
134
+ </div>
135
+
136
+ ### Framework versions
137
+
138
+ - PEFT 0.9.0
139
+ - Transformers 4.38.1
140
+ - Pytorch 2.1.2+cu121
141
+ - Datasets 2.14.5
142
+ - Tokenizers 0.15.0
143
+
144
+ </details>
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "C:\\Llama-2-13b-chat-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 40,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.38.1",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.38.1"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4910447eb5b7fb941cfb1f6da2580dbe9cd0fafdbbf5de350e0805c9af1f91c0
3
+ size 9948687888
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98593e2dffd2f9a76adfd710c54c0bd986d69d708776f11fa56d220a6c4580b
3
+ size 9904123616
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44af3ca4d462897b41dd8c2220951a9cb24760abf6069f6bcce6124f960bb65d
3
+ size 6178959040
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26031728640
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
368
+ "model.norm.weight": "model-00003-of-00003.safetensors"
369
+ }
370
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\\n' + content + '\\n\\n### Response:\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n\\n' }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "left",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false
45
+ }