初始化项目，由ModelHub XC社区提供模型
Model: wvnvwn/llama2-7b-chat-lr5e-5-boolq-lr5e-5-safeinstr0_1 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
1
chat_template.jinja
Normal file
1
chat_template.jinja
Normal file
@@ -0,0 +1 @@
|
||||
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.13.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
23
finetune_config.json
Normal file
23
finetune_config.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"base_model": "/NHNHOME/26msit001_A/BASE/edge_ai_lab/jongbokwon/warp-safety/outputs/chat_ssft/llama2_7b_chat_circuit_breakers",
|
||||
"fine_tuning_type": "Full Parameter Fine-tuning",
|
||||
"dataset": "boolq",
|
||||
"dataset_path": "/NHNHOME/26msit001_A/BASE/edge_ai_lab/jongbokwon/Safety-WaRP-LLM/data/commonsense/boolq_train.json",
|
||||
"num_train_samples": 0,
|
||||
"batch_size": 4,
|
||||
"grad_accum": 4,
|
||||
"learning_rate": 5e-05,
|
||||
"weight_decay": 0.01,
|
||||
"warmup_ratio": 0.1,
|
||||
"epochs": 3,
|
||||
"max_length": 1024,
|
||||
"max_grad_norm": 1.0,
|
||||
"lr_scheduler_type": "cosine",
|
||||
"optimizer": "AdamW (torch)",
|
||||
"gradient_checkpointing": false,
|
||||
"dtype": "bf16",
|
||||
"trainer_type": "Trainer",
|
||||
"safety_mix_ratio": 0.1,
|
||||
"safety_data_path": "/NHNHOME/26msit001_A/BASE/edge_ai_lab/jongbokwon/Safety-WaRP-LLM/data/circuit_breakers_train.json",
|
||||
"geometry_trace_dir": null
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
2
|
||||
],
|
||||
"max_length": 4096,
|
||||
"pad_token_id": 2,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "5.13.0"
|
||||
}
|
||||
77
logs/finetune_boolq_20260718_221735.log
Normal file
77
logs/finetune_boolq_20260718_221735.log
Normal file
@@ -0,0 +1,77 @@
|
||||
2026-07-18 22:17:35 - __main__ - INFO -
|
||||
======================================================================
|
||||
2026-07-18 22:17:35 - __main__ - INFO - 🚀 Full Parameter boolq Fine-tuning (SN-Tuned Model)
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ======================================================================
|
||||
|
||||
2026-07-18 22:17:35 - __main__ - INFO - Log file: /NHNHOME/26msit001_A/BASE/edge_ai_lab/jongbokwon/minseong_results/checkpoints/llama-2-7b-chat-hf/baselines/safeinstr/ratio_0_1/boolq/logs/finetune_boolq_20260718_221735.log
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ⚙️ Configuration:
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ SN-Tuned model: /NHNHOME/26msit001_A/BASE/edge_ai_lab/jongbokwon/warp-safety/outputs/chat_ssft/llama2_7b_chat_circuit_breakers
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Downstream task: boolq
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Input formatting: chat template
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Training samples: 0
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Batch size: 4
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Gradient accumulation: 4
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Epochs: 3
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Learning rate: 5e-05
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Weight decay: 0.01
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Optimizer: AdamW (torch)
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Warmup ratio: 0.1
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Max length: 1024
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Dtype: bf16
|
||||
2026-07-18 22:17:35 - __main__ - INFO - └─ Output dir: /NHNHOME/26msit001_A/BASE/edge_ai_lab/jongbokwon/minseong_results/checkpoints/llama-2-7b-chat-hf/baselines/safeinstr/ratio_0_1/boolq
|
||||
|
||||
2026-07-18 22:17:35 - __main__ - INFO -
|
||||
======================================================================
|
||||
2026-07-18 22:17:35 - __main__ - INFO - [1/4] Loading Tokenizer
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ======================================================================
|
||||
|
||||
2026-07-18 22:17:35 - __main__ - INFO - Attempting to load tokenizer (local files only)...
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ✓ Tokenizer loaded from local files
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ✅ Tokenizer loaded successfully
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Tokenizer type: LlamaTokenizer
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ├─ Vocab size: 32000
|
||||
2026-07-18 22:17:35 - __main__ - INFO - └─ Pad token: </s>
|
||||
2026-07-18 22:17:35 - __main__ - INFO -
|
||||
======================================================================
|
||||
2026-07-18 22:17:35 - __main__ - INFO - [2/4] Loading Model (bf16)
|
||||
2026-07-18 22:17:35 - __main__ - INFO - ======================================================================
|
||||
|
||||
2026-07-18 22:17:35 - __main__ - INFO - Attempting to load model (local files only)...
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ✓ Model loaded from local files
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ✅ Model loaded successfully
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ├─ Model size: 6.74B parameters
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ├─ Trainable: 6.74B (100.00%)
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ├─ Dtype: torch.bfloat16
|
||||
2026-07-18 22:17:42 - __main__ - INFO - └─ Gradient checkpointing: Disabled
|
||||
2026-07-18 22:17:42 - __main__ - INFO -
|
||||
======================================================================
|
||||
2026-07-18 22:17:42 - __main__ - INFO - [3/4] Loading boolq Dataset
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ======================================================================
|
||||
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ✅ Datasets loaded
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ├─ Train: 9427 samples
|
||||
2026-07-18 22:17:42 - __main__ - INFO -
|
||||
======================================================================
|
||||
2026-07-18 22:17:42 - __main__ - INFO - [3.5/4] Preprocessing Data
|
||||
2026-07-18 22:17:42 - __main__ - INFO - ======================================================================
|
||||
|
||||
2026-07-18 22:17:44 - __main__ - INFO - ✅ Safety data mixed: 942 samples (ratio=0.1)
|
||||
2026-07-18 22:17:44 - __main__ - INFO - Total training samples: 10369 (boolq 9427 + Safety 942)
|
||||
2026-07-18 22:17:44 - __main__ - INFO -
|
||||
======================================================================
|
||||
2026-07-18 22:17:44 - __main__ - INFO - [4/4] Training with Trainer + AdamW
|
||||
2026-07-18 22:17:44 - __main__ - INFO - ======================================================================
|
||||
|
||||
2026-07-18 22:17:44 - __main__ - INFO - Starting training...
|
||||
2026-07-18 22:26:07 - __main__ - INFO -
|
||||
======================================================================
|
||||
2026-07-18 22:26:07 - __main__ - INFO - Saving Fine-tuned Model
|
||||
2026-07-18 22:26:07 - __main__ - INFO - ======================================================================
|
||||
|
||||
2026-07-18 22:26:19 - __main__ - INFO - ✅ Fine-tuned model saved successfully to /NHNHOME/26msit001_A/BASE/edge_ai_lab/jongbokwon/minseong_results/checkpoints/llama-2-7b-chat-hf/baselines/safeinstr/ratio_0_1/boolq
|
||||
2026-07-18 22:26:19 - __main__ - INFO - ✅ Config saved to: /NHNHOME/26msit001_A/BASE/edge_ai_lab/jongbokwon/minseong_results/checkpoints/llama-2-7b-chat-hf/baselines/safeinstr/ratio_0_1/boolq/finetune_config.json
|
||||
2026-07-18 22:26:19 - __main__ - INFO -
|
||||
======================================================================
|
||||
2026-07-18 22:26:19 - __main__ - INFO - ✅ Fine-tuning Complete!
|
||||
2026-07-18 22:26:19 - __main__ - INFO - ======================================================================
|
||||
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e92f1008581643477a42b7a0080be2df3025b5f115f0e67514b9cca87fa0807
|
||||
size 4976741976
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9353754e2b7d1b7904a0089c0126e4c8cdb5a7c45c3cb9c1a0998a235150501e
|
||||
size 4947390888
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d002e995d81e4cc198a5e2aaf6e3fbf75f448b562155b9ef2e97fb101cf64e97
|
||||
size 3552732192
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13476831232
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
277134
tokenizer.json
Normal file
277134
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
16
tokenizer_config.json
Normal file
16
tokenizer_config.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"add_prefix_space": null,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"is_local": true,
|
||||
"local_files_only": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dddb8a860c573bfea4806c320d60b543a10e40fcaa46da1027dbb0c4e5dac967
|
||||
size 5265
|
||||
Reference in New Issue
Block a user