Natkituwu commited on
Commit
d93c125
1 Parent(s): deaf27a

Upload 10 files

Browse files
README.md CHANGED
@@ -1,3 +1,38 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-Nemo-Base-2407
3
+ license: apache-2.0
4
+ datasets:
5
+ - BeaverAI/Nemo-Inst-Tune-ds
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ ---
10
+ # Dory 12b
11
+ redone instruct finetune of mistral nemo 12b. *not* (E)RP-focused, leave that to drummer.
12
+
13
+ ![image/gif](https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/tP5kiebGrg8DJZbeBEc3Q.gif)
14
+
15
+ thanks to twisted for the compute :3
16
+
17
+ ## Prompting
18
+ alpaca-like:
19
+ ```
20
+ ### System:
21
+ [Optional system prompt]
22
+
23
+ ### Instruction:
24
+ [Query]
25
+
26
+ ### Response:
27
+ [Response]<EOT>
28
+
29
+ ### Instruction:
30
+ [...]
31
+ ```
32
+
33
+ ## Training details
34
+ Rank 64 QDoRA, trained on the following data mix:
35
+ - All of [kalomaze/Opus_Instruct_3k](https://huggingface.co/datasets/kalomaze/Opus_Instruct_3k)
36
+ - All conversations with a reward model rating above 5 in [Magpie-Align/Magpie-Gemma2-Pro-Preview-Filtered](https://huggingface.co/datasets/Magpie-Align/Magpie-Gemma2-Pro-Preview-Filtered)
37
+ - 50k of [Gryphe/Sonnet3.5-SlimOrcaDedupCleaned](https://huggingface.co/datasets/Gryphe/Sonnet3.5-SlimOrcaDedupCleaned)
38
+ - All stories above 4.7 rating and published before 2020 in [Fizzarolli/FallingThroughTheSkies-592k-Filtered-Filtered](https://huggingface.co/datasets/Fizzarolli/FallingThroughTheSkies-592k-Filtered-Filtered)
axolotl_config.yaml ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Weights and Biases logging config
2
+ wandb_project: nemo-instruct-tune
3
+ wandb_entity:
4
+ wandb_watch:
5
+ wandb_name: v1
6
+ wandb_log_model:
7
+
8
+ # Model architecture config
9
+ base_model: mistralai/Mistral-Nemo-Base-2407
10
+ model_type: AutoModelForCausalLM
11
+ tokenizer_type: AutoTokenizer
12
+ chat_template: alpaca
13
+
14
+ # Hugging Face saving config
15
+ hub_model_id: Fizzarolli/nemo-instruct-tune-v1
16
+ hub_strategy: all_checkpoints
17
+ push_dataset_to_hub:
18
+ hf_use_auth_token:
19
+
20
+ # Model checkpointing config
21
+ output_dir: ./lora-out
22
+ resume_from_checkpoint:
23
+ save_steps:
24
+ saves_per_epoch: 10
25
+ save_safetensors: true
26
+ save_total_limit: 2
27
+
28
+ # Mixed precision training config
29
+ bf16: true
30
+ fp16: false
31
+ tf32: false
32
+
33
+ # Model loading config
34
+ load_in_8bit: false
35
+ load_in_4bit: true
36
+ strict: false
37
+
38
+ # Sequence config
39
+ sequence_len: 16384
40
+ s2_attention: false
41
+ sample_packing: true
42
+ eval_sample_packing: true
43
+ pad_to_sequence_len: true
44
+ train_on_inputs: false
45
+ group_by_length: false
46
+
47
+ # QLoRA adapter config
48
+ adapter: qlora
49
+ lora_model_dir:
50
+ lora_r: 64
51
+ lora_alpha: 64
52
+ lora_dropout: 0.125
53
+ lora_fan_in_fan_out:
54
+ lora_target_linear:
55
+ save_embedding_layers:
56
+ peft_layers_to_transform:
57
+ peft_use_dora: true
58
+ peft_use_rslora:
59
+ peft_layer_replication:
60
+ lora_target_modules:
61
+ - gate_proj
62
+ - down_proj
63
+ - up_proj
64
+ - q_proj
65
+ - v_proj
66
+ - k_proj
67
+ - o_proj
68
+ lora_modules_to_save:
69
+
70
+ # Unfrozen parameters for FFT
71
+ unfrozen_parameters:
72
+
73
+ # Dataset config
74
+ datasets:
75
+ - path: BeaverAI/Nemo-Inst-Tune-ds
76
+ type: chat_template
77
+ val_set_size: 0.05
78
+ evaluation_strategy:
79
+ eval_steps:
80
+ evals_per_epoch: 20
81
+ test_datasets:
82
+ dataset_prepared_path: ./prepared-datasets
83
+ shuffle_merged_datasets: true
84
+
85
+ # Training hyperparameters
86
+ num_epochs: 1
87
+ gradient_accumulation_steps: 2
88
+ micro_batch_size: 1
89
+ eval_batch_size: 1
90
+ warmup_steps: 25
91
+ optimizer: paged_adamw_8bit
92
+ lr_scheduler: cosine
93
+ learning_rate: 0.000007
94
+ loraplus_lr_ratio: 8
95
+ loraplus_lr_embedding:
96
+ cosine_min_lr_ratio: 0.1
97
+ weight_decay: 0.1
98
+ max_grad_norm: 1
99
+ logging_steps: 1
100
+
101
+ # Model optimization
102
+ gradient_checkpointing: unsloth
103
+ xformers_attention: false
104
+ flash_attention: true
105
+ sdp_attention: false
106
+ unsloth_cross_entropy_loss: false
107
+ unsloth_lora_mlp: false
108
+ unsloth_lora_qkv: false
109
+ unsloth_lora_o: false
110
+
111
+ # Loss monitoring config
112
+ early_stopping_patience: false
113
+ loss_watchdog_threshold: 100.0
114
+ loss_watchdog_patience: 3
115
+
116
+ # Debug config
117
+ debug: true
118
+ seed: 42
119
+
120
+ # DeepSpeed and FSDP config
121
+ deepspeed: deepspeed_configs/zero2.json
122
+ fsdp:
123
+ fsdp_config:
124
+
125
+ # Token config
126
+ special_tokens:
127
+ pad_token: "<pad>"
128
+ tokens:
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-Nemo-Base-2407",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.43.0.dev0",
25
+ "use_cache": false,
26
+ "vocab_size": 131072,
27
+ "quantization_config": {
28
+ "quant_method": "exl2",
29
+ "version": "0.1.7",
30
+ "bits": 5.0,
31
+ "head_bits": 6,
32
+ "calibration": {
33
+ "rows": 115,
34
+ "length": 2048,
35
+ "dataset": "(default)"
36
+ }
37
+ }
38
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.43.0.dev0"
7
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24495564800
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
368
+ "model.norm.weight": "model-00005-of-00005.safetensors"
369
+ }
370
+ }
output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b0590d934562033989af93f9346702a67719acaff3edbdfa5d36255a439d78
3
+ size 8160983840
output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c183c80ba449f8d1d1131653752465fc08004b0633de93e638059ecc46ddc2
3
+ size 528482400
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff