Commit
•
206b412
1
Parent(s):
f712e6f
Upload folder using huggingface_hub
Browse files- README.md +130 -1
- checkpoint-3240/config.json +37 -0
- checkpoint-3240/generation_config.json +8 -0
- checkpoint-3240/model-00001-of-00002.safetensors +3 -0
- checkpoint-3240/model-00002-of-00002.safetensors +3 -0
- checkpoint-3240/model.safetensors.index.json +369 -0
- checkpoint-3240/optimizer.pt +3 -0
- checkpoint-3240/rng_state_0.pth +3 -0
- checkpoint-3240/rng_state_1.pth +3 -0
- checkpoint-3240/rng_state_2.pth +3 -0
- checkpoint-3240/rng_state_3.pth +3 -0
- checkpoint-3240/scheduler.pt +3 -0
- checkpoint-3240/trainer_state.json +0 -0
- checkpoint-3240/training_args.bin +3 -0
- config.json +37 -0
- generation_config.json +8 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +370 -0
- runs/Feb03_02-11-36_2fe4fa228bfd/events.out.tfevents.1706926297.2fe4fa228bfd.3235.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
README.md
CHANGED
@@ -1,3 +1,132 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: openbmb/MiniCPM-2B-sft-bf16
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: qlora-out
|
7 |
+
results: []
|
8 |
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
14 |
+
<details><summary>See axolotl config</summary>
|
15 |
+
|
16 |
+
axolotl version: `0.4.0`
|
17 |
+
```yaml
|
18 |
+
base_model: openbmb/MiniCPM-2B-sft-bf16
|
19 |
+
load_in_8bit: false
|
20 |
+
load_in_4bit: false
|
21 |
+
strict: false
|
22 |
+
push_dataset_to_hub:
|
23 |
+
datasets:
|
24 |
+
- path: teknium/GPT4-LLM-Cleaned
|
25 |
+
type: alpaca
|
26 |
+
dataset_prepared_path:
|
27 |
+
val_set_size: 0.05
|
28 |
+
adapter:
|
29 |
+
lora_model_dir:
|
30 |
+
sequence_len: 4096
|
31 |
+
max_packed_sequence_len:
|
32 |
+
lora_r: 8
|
33 |
+
lora_alpha: 32
|
34 |
+
lora_dropout: 0.05
|
35 |
+
lora_target_modules:
|
36 |
+
lora_target_linear: true
|
37 |
+
lora_fan_in_fan_out:
|
38 |
+
wandb_project:
|
39 |
+
wandb_entity:
|
40 |
+
wandb_watch:
|
41 |
+
wandb_name:
|
42 |
+
wandb_log_model:
|
43 |
+
output_dir: ./qlora-out
|
44 |
+
gradient_accumulation_steps: 2
|
45 |
+
micro_batch_size: 2
|
46 |
+
num_epochs: 1.5
|
47 |
+
optimizer: paged_adamw_8bit
|
48 |
+
torchdistx_path:
|
49 |
+
lr_scheduler: cosine
|
50 |
+
learning_rate: 0.0001
|
51 |
+
train_on_inputs: false
|
52 |
+
group_by_length: false
|
53 |
+
bf16: auto
|
54 |
+
fp16:
|
55 |
+
tf32: true
|
56 |
+
gradient_checkpointing: true
|
57 |
+
early_stopping_patience:
|
58 |
+
resume_from_checkpoint:
|
59 |
+
local_rank:
|
60 |
+
logging_steps: 1
|
61 |
+
xformers_attention: true
|
62 |
+
flash_attention:
|
63 |
+
gptq_groupsize:
|
64 |
+
gptq_model_v1:
|
65 |
+
warmup_steps: 10
|
66 |
+
evals_per_epoch: 2
|
67 |
+
saves_per_epoch: 1
|
68 |
+
debug:
|
69 |
+
deepspeed:
|
70 |
+
weight_decay: 0.1
|
71 |
+
fsdp:
|
72 |
+
fsdp_config:
|
73 |
+
special_tokens:
|
74 |
+
trust_remote_code: true
|
75 |
+
|
76 |
+
```
|
77 |
+
|
78 |
+
</details><br>
|
79 |
+
|
80 |
+
# qlora-out
|
81 |
+
|
82 |
+
This model is a fine-tuned version of [openbmb/MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) on the None dataset.
|
83 |
+
It achieves the following results on the evaluation set:
|
84 |
+
- Loss: 1.0525
|
85 |
+
|
86 |
+
## Model description
|
87 |
+
|
88 |
+
More information needed
|
89 |
+
|
90 |
+
## Intended uses & limitations
|
91 |
+
|
92 |
+
More information needed
|
93 |
+
|
94 |
+
## Training and evaluation data
|
95 |
+
|
96 |
+
More information needed
|
97 |
+
|
98 |
+
## Training procedure
|
99 |
+
|
100 |
+
### Training hyperparameters
|
101 |
+
|
102 |
+
The following hyperparameters were used during training:
|
103 |
+
- learning_rate: 0.0001
|
104 |
+
- train_batch_size: 2
|
105 |
+
- eval_batch_size: 2
|
106 |
+
- seed: 42
|
107 |
+
- distributed_type: multi-GPU
|
108 |
+
- num_devices: 4
|
109 |
+
- gradient_accumulation_steps: 2
|
110 |
+
- total_train_batch_size: 16
|
111 |
+
- total_eval_batch_size: 8
|
112 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
113 |
+
- lr_scheduler_type: cosine
|
114 |
+
- lr_scheduler_warmup_steps: 10
|
115 |
+
- num_epochs: 1.5
|
116 |
+
|
117 |
+
### Training results
|
118 |
+
|
119 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
120 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
121 |
+
| 1.0903 | 0.0 | 1 | 1.7199 |
|
122 |
+
| 0.8959 | 0.5 | 1620 | 1.1007 |
|
123 |
+
| 0.995 | 1.0 | 3240 | 1.0342 |
|
124 |
+
| 0.864 | 1.5 | 4860 | 1.0525 |
|
125 |
+
|
126 |
+
|
127 |
+
### Framework versions
|
128 |
+
|
129 |
+
- Transformers 4.38.0.dev0
|
130 |
+
- Pytorch 2.1.2+cu118
|
131 |
+
- Datasets 2.16.1
|
132 |
+
- Tokenizers 0.15.0
|
checkpoint-3240/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openbmb/MiniCPM-2B-sft-bf16",
|
3 |
+
"architectures": [
|
4 |
+
"MiniCPMForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "openbmb/MiniCPM-2B-sft-bf16--configuration_minicpm.MiniCPMConfig",
|
10 |
+
"AutoModel": "openbmb/MiniCPM-2B-sft-bf16--modeling_minicpm.MiniCPMModel",
|
11 |
+
"AutoModelForCausalLM": "openbmb/MiniCPM-2B-sft-bf16--modeling_minicpm.MiniCPMForCausalLM",
|
12 |
+
"AutoModelForSeq2SeqLM": "openbmb/MiniCPM-2B-sft-bf16--modeling_minicpm.MiniCPMForCausalLM",
|
13 |
+
"AutoModelForSequenceClassification": "openbmb/MiniCPM-2B-sft-bf16--modeling_minicpm.MiniCPMForSequenceClassification"
|
14 |
+
},
|
15 |
+
"bos_token_id": 1,
|
16 |
+
"dim_model_base": 256,
|
17 |
+
"eos_token_id": 2,
|
18 |
+
"hidden_act": "silu",
|
19 |
+
"hidden_size": 2304,
|
20 |
+
"initializer_range": 0.1,
|
21 |
+
"intermediate_size": 5760,
|
22 |
+
"max_position_embeddings": 4096,
|
23 |
+
"model_type": "minicpm",
|
24 |
+
"num_attention_heads": 36,
|
25 |
+
"num_hidden_layers": 40,
|
26 |
+
"num_key_value_heads": 36,
|
27 |
+
"pretraining_tp": 1,
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_scaling": null,
|
30 |
+
"rope_theta": 10000.0,
|
31 |
+
"scale_depth": 1.4,
|
32 |
+
"scale_emb": 12,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.38.0.dev0",
|
35 |
+
"use_cache": false,
|
36 |
+
"vocab_size": 122753
|
37 |
+
}
|
checkpoint-3240/generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"temperature": 0.8,
|
6 |
+
"top_p": 0.8,
|
7 |
+
"transformers_version": "4.38.0.dev0"
|
8 |
+
}
|
checkpoint-3240/model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65d038cbb3a868009aea39cf6badb584d1014b0a0a4fcae22e998245c81192f3
|
3 |
+
size 4985806120
|
checkpoint-3240/model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e8454a14436222d75df31a7578561c123e26e8c80f4c8f54e4dba135f62a803
|
3 |
+
size 1030016472
|
checkpoint-3240/model.safetensors.index.json
ADDED
@@ -0,0 +1,369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 6015780864
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
20 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
26 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
35 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
38 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
40 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
44 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
49 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
56 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
58 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
62 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
74 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
76 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
94 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
98 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
100 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
101 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
102 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
103 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
105 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
106 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
107 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
108 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
109 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
110 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
111 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
112 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
113 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
114 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
115 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
116 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
117 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
119 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
120 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
121 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
122 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
125 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
126 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
127 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
128 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
129 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
130 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
131 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
132 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
133 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
134 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
135 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
136 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
137 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
138 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
139 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
140 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
141 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
142 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
143 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
144 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
145 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
146 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
147 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
148 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
149 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
152 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
153 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
154 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
155 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
156 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
157 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
158 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
159 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
160 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
161 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
162 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
163 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
164 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
166 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
170 |
+
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
172 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
173 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
174 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
176 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
180 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
182 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
184 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
188 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
189 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
190 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
192 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
193 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
194 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
195 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
196 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
197 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
198 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
199 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
200 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
201 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
202 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
203 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
204 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
205 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
206 |
+
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
207 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
208 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
209 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
210 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
211 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
212 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
213 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
214 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
215 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
216 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
217 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
218 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
219 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
220 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
221 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
222 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
223 |
+
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
224 |
+
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
225 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
226 |
+
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
227 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
228 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
229 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
230 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
231 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
232 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
233 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
234 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
235 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
236 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
237 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
238 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
239 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
240 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
241 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
242 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
243 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
244 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
245 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
246 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
247 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
248 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
249 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
250 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
251 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
252 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
253 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
254 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
255 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
256 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
257 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
258 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
259 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
260 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
261 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
262 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
263 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
264 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
265 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
266 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
267 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
268 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
269 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
270 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
271 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
272 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
273 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
274 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
275 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
276 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
277 |
+
"model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
278 |
+
"model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
279 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
280 |
+
"model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
281 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
282 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
283 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
284 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
285 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
286 |
+
"model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
287 |
+
"model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
288 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
289 |
+
"model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
290 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
291 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
292 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
293 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
294 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
295 |
+
"model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
296 |
+
"model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
297 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
298 |
+
"model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
299 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
300 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
301 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
302 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
303 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
304 |
+
"model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
305 |
+
"model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
306 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
307 |
+
"model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
308 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
309 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
310 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
311 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
312 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
313 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
314 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
315 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
316 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
317 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
318 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
319 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
320 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
321 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
322 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
323 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
324 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
325 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
326 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
327 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
328 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
329 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
330 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
331 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
332 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
333 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
334 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
335 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
336 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
337 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
338 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
339 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
340 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
341 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
342 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
343 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
344 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
345 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
346 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
347 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
348 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
349 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
350 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
351 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
352 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
353 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
354 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
355 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
356 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
357 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
358 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
359 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
360 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
361 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
362 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
363 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
364 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
365 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
366 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
367 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
368 |
+
}
|
369 |
+
}
|
checkpoint-3240/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2bc3158e15f19260981ceb8e6217f366a7380c31cb4d2c5b06b8d35124ea837
|
3 |
+
size 5461914338
|
checkpoint-3240/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c5e18f922d0af74d820247ae97bee506ab412554a58345ddf2558abc94ee3e3
|
3 |
+
size 15024
|
checkpoint-3240/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a2dcca6d9741f46592359768ea2212b9321da6408d1fd7d3a80b017bf37f434
|
3 |
+
size 15024
|
checkpoint-3240/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69420ece2c255923c5cbb3c6c9c4a6b9cb38fb57e5d3033c8b7d436a1faf6f13
|
3 |
+
size 15024
|
checkpoint-3240/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66f278b40a1e23b88a657c4e5d03afa8dbbbe14dfeb16f6b4beedaece6cdd0b9
|
3 |
+
size 15024
|
checkpoint-3240/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cbc72706138d9ea9b6846664d3a41b182681b949ab5e019e8f8cb27c3f1b92b
|
3 |
+
size 1064
|
checkpoint-3240/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3240/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24d5cb4ca3f08022e48f8f84c337e476b18363dc536325c21491c785309a5d84
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openbmb/MiniCPM-2B-sft-bf16",
|
3 |
+
"architectures": [
|
4 |
+
"MiniCPMForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "openbmb/MiniCPM-2B-sft-bf16--configuration_minicpm.MiniCPMConfig",
|
10 |
+
"AutoModel": "openbmb/MiniCPM-2B-sft-bf16--modeling_minicpm.MiniCPMModel",
|
11 |
+
"AutoModelForCausalLM": "openbmb/MiniCPM-2B-sft-bf16--modeling_minicpm.MiniCPMForCausalLM",
|
12 |
+
"AutoModelForSeq2SeqLM": "openbmb/MiniCPM-2B-sft-bf16--modeling_minicpm.MiniCPMForCausalLM",
|
13 |
+
"AutoModelForSequenceClassification": "openbmb/MiniCPM-2B-sft-bf16--modeling_minicpm.MiniCPMForSequenceClassification"
|
14 |
+
},
|
15 |
+
"bos_token_id": 1,
|
16 |
+
"dim_model_base": 256,
|
17 |
+
"eos_token_id": 2,
|
18 |
+
"hidden_act": "silu",
|
19 |
+
"hidden_size": 2304,
|
20 |
+
"initializer_range": 0.1,
|
21 |
+
"intermediate_size": 5760,
|
22 |
+
"max_position_embeddings": 4096,
|
23 |
+
"model_type": "minicpm",
|
24 |
+
"num_attention_heads": 36,
|
25 |
+
"num_hidden_layers": 40,
|
26 |
+
"num_key_value_heads": 36,
|
27 |
+
"pretraining_tp": 1,
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_scaling": null,
|
30 |
+
"rope_theta": 10000.0,
|
31 |
+
"scale_depth": 1.4,
|
32 |
+
"scale_emb": 12,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.38.0.dev0",
|
35 |
+
"use_cache": false,
|
36 |
+
"vocab_size": 122753
|
37 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"temperature": 0.8,
|
6 |
+
"top_p": 0.8,
|
7 |
+
"transformers_version": "4.38.0.dev0"
|
8 |
+
}
|
pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d64e7c4bf11b7e9bfdea5d140f19504358e8eae859cdf290c764e9dcdbf2aaa
|
3 |
+
size 4985874685
|
pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f25863c7eb327de5d5fe505390c5efafbc6032e34d2e0f764a699aab90caf6c2
|
3 |
+
size 1030035220
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 6015780864
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00001-of-00002.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
242 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
251 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
260 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
269 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
278 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
287 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
296 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
305 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
314 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
323 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
324 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
325 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
326 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
327 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
328 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
329 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
330 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
331 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
332 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
333 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
334 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
335 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
336 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
337 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
338 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
339 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
340 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
341 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
342 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
343 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
344 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
345 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
346 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
347 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
348 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
349 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
350 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
351 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
352 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
353 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
354 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
355 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
356 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
357 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
358 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
359 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
360 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
361 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
362 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
363 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
364 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
365 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
366 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
367 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
368 |
+
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
369 |
+
}
|
370 |
+
}
|
runs/Feb03_02-11-36_2fe4fa228bfd/events.out.tfevents.1706926297.2fe4fa228bfd.3235.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0a5d7b30680c0afc124516b9dac57a2a47cb60ce5a13540de0764930ed33298
|
3 |
+
size 769642
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9aafcd7da1f5611dab6be545db74d5552a2ccc9c2a12c72ea7be63aac4a25d7
|
3 |
+
size 1994871
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<用户>' + message['content'].strip() + '<AI>'}}{% else %}{{message['content'].strip()}}{% endif %}{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|