初始化项目，由ModelHub XC社区提供模型
Model: justinj92/phi2-bunny Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
phi2-bunny-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
phi2-bunny-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
phi2-bunny-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
200
README.md
Normal file
200
README.md
Normal file
@@ -0,0 +1,200 @@
|
||||
---
|
||||
license: mit
|
||||
library_name: transformers
|
||||
tags:
|
||||
- axolotl
|
||||
- generated_from_trainer
|
||||
base_model: microsoft/phi-2
|
||||
model-index:
|
||||
- name: phi2-bunny
|
||||
results: []
|
||||
datasets:
|
||||
- WhiteRabbitNeo/WRN-Chapter-1
|
||||
- WhiteRabbitNeo/WRN-Chapter-2
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
[<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)
|
||||
<details><summary>See axolotl config</summary>
|
||||
|
||||
axolotl version: `0.4.0`
|
||||
```yaml
|
||||
base_model: microsoft/phi-2
|
||||
model_type: AutoModelForCausalLM
|
||||
tokenizer_type: AutoTokenizer
|
||||
is_llama_derived_model: false
|
||||
# trust_remote_code: true
|
||||
|
||||
load_in_8bit: false
|
||||
load_in_4bit: false
|
||||
strict: false
|
||||
|
||||
datasets:
|
||||
- path: WhiteRabbitNeo/WRN-Chapter-1
|
||||
type:
|
||||
system_prompt: ""
|
||||
field_system: system
|
||||
field_instruction: instruction
|
||||
field_output: response
|
||||
prompt_style: chatml
|
||||
- path: WhiteRabbitNeo/WRN-Chapter-2
|
||||
type:
|
||||
system_prompt: ""
|
||||
field_system: system
|
||||
field_instruction: instruction
|
||||
field_output: response
|
||||
prompt_style: chatml
|
||||
|
||||
dataset_prepared_path: ./phi2-bunny/last-run-prepared
|
||||
val_set_size: 0.05
|
||||
output_dir: ./phi2-bunny/
|
||||
|
||||
sequence_len: 2048
|
||||
sample_packing: true
|
||||
pad_to_sequence_len: true
|
||||
|
||||
adapter: lora
|
||||
lora_model_dir:
|
||||
lora_r: 64
|
||||
lora_alpha: 32
|
||||
lora_dropout: 0.05
|
||||
lora_target_linear: true
|
||||
lora_fan_in_fan_out:
|
||||
lora_modules_to_save:
|
||||
- embed_tokens
|
||||
- lm_head
|
||||
|
||||
|
||||
hub_model_id: justinj92/phi2-bunny
|
||||
|
||||
wandb_project: phi2-bunny
|
||||
wandb_entity: justinjoy-5
|
||||
wandb_watch:
|
||||
wandb_name:
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 8
|
||||
micro_batch_size: 2
|
||||
num_epochs: 5
|
||||
optimizer: paged_adamw_8bit
|
||||
adam_beta1: 0.9
|
||||
adam_beta2: 0.999
|
||||
adam_epsilon: 0.00001
|
||||
max_grad_norm: 1000.0
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 0.0002
|
||||
|
||||
train_on_inputs: false
|
||||
group_by_length: true
|
||||
bf16: true
|
||||
fp16: false
|
||||
tf32: true
|
||||
|
||||
gradient_checkpointing: true
|
||||
early_stopping_patience:
|
||||
resume_from_checkpoint:
|
||||
auto_resume_from_checkpoints:
|
||||
local_rank:
|
||||
logging_steps: 1
|
||||
xformers_attention:
|
||||
flash_attention: true
|
||||
chat_template: chatml
|
||||
|
||||
warmup_steps: 100
|
||||
evals_per_epoch: 4
|
||||
save_steps: 0.01
|
||||
save_total_limit: 2
|
||||
debug:
|
||||
deepspeed:
|
||||
weight_decay: 0.01
|
||||
fsdp:
|
||||
fsdp_config:
|
||||
resize_token_embeddings_to_32x: true
|
||||
special_tokens:
|
||||
eos_token: "<|im_end|>"
|
||||
pad_token: "<|endoftext|>"
|
||||
tokens:
|
||||
- "<|im_start|>"
|
||||
|
||||
```
|
||||
|
||||
</details><br>
|
||||
|
||||
## Hardware
|
||||
|
||||
Azure 1xNC_H100 VM - 8 Hours Training Time
|
||||
|
||||
# phi2-bunny
|
||||
|
||||
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the WhiteRabbit Cybersecurity dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.5347
|
||||
|
||||
## Model description
|
||||
|
||||
Phi-2 SLM
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
Research & Learning
|
||||
|
||||
## ChatML Prompt
|
||||
|
||||
<|im_start|>system
|
||||
You are Bunny, a helpful AI cyber researcher. Answer the Question in a logical, step-by-step manner that makes the reasoning process clear. Carefully analyze the question to identify the core issue or problem to be solved.<|im_end|>
|
||||
<|im_start|>user
|
||||
{prompt}<|im_end|>
|
||||
<|im_start|>assistant
|
||||
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 0.0002
|
||||
- train_batch_size: 2
|
||||
- eval_batch_size: 2
|
||||
- seed: 42
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 16
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-05
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_steps: 100
|
||||
- num_epochs: 5
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:-----:|:----:|:---------------:|
|
||||
| 0.8645 | 0.0 | 1 | 0.7932 |
|
||||
| 0.6246 | 0.25 | 228 | 0.6771 |
|
||||
| 0.6449 | 0.5 | 456 | 0.6186 |
|
||||
| 0.6658 | 0.75 | 684 | 0.6073 |
|
||||
| 0.5419 | 1.0 | 912 | 0.5911 |
|
||||
| 0.5477 | 1.24 | 1140 | 0.5878 |
|
||||
| 0.612 | 1.49 | 1368 | 0.5715 |
|
||||
| 0.6328 | 1.74 | 1596 | 0.5632 |
|
||||
| 0.5082 | 1.99 | 1824 | 0.5534 |
|
||||
| 0.5807 | 2.24 | 2052 | 0.5513 |
|
||||
| 0.4775 | 2.49 | 2280 | 0.5448 |
|
||||
| 0.514 | 2.74 | 2508 | 0.5430 |
|
||||
| 0.4943 | 2.99 | 2736 | 0.5398 |
|
||||
| 0.5012 | 3.22 | 2964 | 0.5396 |
|
||||
| 0.5203 | 3.48 | 3192 | 0.5371 |
|
||||
| 0.5112 | 3.73 | 3420 | 0.5356 |
|
||||
| 0.4978 | 3.98 | 3648 | 0.5351 |
|
||||
| 0.5642 | 4.22 | 3876 | 0.5348 |
|
||||
| 0.5383 | 4.47 | 4104 | 0.5348 |
|
||||
| 0.4679 | 4.72 | 4332 | 0.5347 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.8.1.dev0
|
||||
- Transformers 4.37.0
|
||||
- Pytorch 2.1.2+cu121
|
||||
- Datasets 2.16.1
|
||||
- Tokenizers 0.15.0
|
||||
34
adapter_config.json
Normal file
34
adapter_config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "microsoft/phi-2",
|
||||
"bias": "none",
|
||||
"fan_in_fan_out": null,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.05,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": [
|
||||
"embed_tokens",
|
||||
"lm_head"
|
||||
],
|
||||
"peft_type": "LORA",
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"dense",
|
||||
"k_proj",
|
||||
"v_proj",
|
||||
"fc2",
|
||||
"q_proj",
|
||||
"fc1"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
3
adapter_model.bin
Normal file
3
adapter_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bbacf6cea80132a5062734e8ca0ab079bb429cf8fc25f9bb3ccf88f2f9460f6a
|
||||
size 713273302
|
||||
42
added_tokens.json
Normal file
42
added_tokens.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"\t\t": 50294,
|
||||
"\t\t\t": 50293,
|
||||
"\t\t\t\t": 50292,
|
||||
"\t\t\t\t\t": 50291,
|
||||
"\t\t\t\t\t\t": 50290,
|
||||
"\t\t\t\t\t\t\t": 50289,
|
||||
"\t\t\t\t\t\t\t\t": 50288,
|
||||
"\t\t\t\t\t\t\t\t\t": 50287,
|
||||
" ": 50286,
|
||||
" ": 50285,
|
||||
" ": 50284,
|
||||
" ": 50283,
|
||||
" ": 50282,
|
||||
" ": 50281,
|
||||
" ": 50280,
|
||||
" ": 50279,
|
||||
" ": 50278,
|
||||
" ": 50277,
|
||||
" ": 50276,
|
||||
" ": 50275,
|
||||
" ": 50274,
|
||||
" ": 50273,
|
||||
" ": 50272,
|
||||
" ": 50271,
|
||||
" ": 50270,
|
||||
" ": 50269,
|
||||
" ": 50268,
|
||||
" ": 50267,
|
||||
" ": 50266,
|
||||
" ": 50265,
|
||||
" ": 50264,
|
||||
" ": 50263,
|
||||
" ": 50262,
|
||||
" ": 50261,
|
||||
" ": 50260,
|
||||
" ": 50259,
|
||||
" ": 50258,
|
||||
" ": 50257,
|
||||
"<|im_end|>": 50295,
|
||||
"<|im_start|>": 50296
|
||||
}
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"_name_or_path": "microsoft/phi-2",
|
||||
"architectures": [
|
||||
"PhiForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"auto_map": {
|
||||
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
|
||||
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
|
||||
},
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 50295,
|
||||
"hidden_act": "gelu_new",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 10240,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "phi",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"partial_rotary_factor": 0.4,
|
||||
"qk_layernorm": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.37.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.37.0"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c4c851c147938984b12a85a1bcf10fbd6271c6921fce71ad7a66488cb865b4bd
|
||||
size 266265696
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:28d0fa0412b71aa6207731b04fcf598f1066a6ee3845b3dbb27b6976d5c40f4c
|
||||
size 267109512
|
||||
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"citation": "",
|
||||
"description": "",
|
||||
"features": {
|
||||
"input_ids": {
|
||||
"feature": {
|
||||
"dtype": "int32",
|
||||
"_type": "Value"
|
||||
},
|
||||
"_type": "Sequence"
|
||||
},
|
||||
"attention_mask": {
|
||||
"feature": {
|
||||
"dtype": "int8",
|
||||
"_type": "Value"
|
||||
},
|
||||
"_type": "Sequence"
|
||||
},
|
||||
"labels": {
|
||||
"feature": {
|
||||
"dtype": "int64",
|
||||
"_type": "Value"
|
||||
},
|
||||
"_type": "Sequence"
|
||||
},
|
||||
"length": {
|
||||
"dtype": "int64",
|
||||
"_type": "Value"
|
||||
},
|
||||
"position_ids": {
|
||||
"feature": {
|
||||
"dtype": "int64",
|
||||
"_type": "Value"
|
||||
},
|
||||
"_type": "Sequence"
|
||||
}
|
||||
},
|
||||
"homepage": "",
|
||||
"license": ""
|
||||
}
|
||||
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"_data_files": [
|
||||
{
|
||||
"filename": "data-00000-of-00002.arrow"
|
||||
},
|
||||
{
|
||||
"filename": "data-00001-of-00002.arrow"
|
||||
}
|
||||
],
|
||||
"_fingerprint": "9e1bf20356e01222",
|
||||
"_format_columns": [
|
||||
"input_ids",
|
||||
"attention_mask",
|
||||
"labels",
|
||||
"length",
|
||||
"position_ids"
|
||||
],
|
||||
"_format_kwargs": {},
|
||||
"_format_type": null,
|
||||
"_output_all_columns": false,
|
||||
"_split": null
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6324b856a3e83fd4f5c15344a011afe8c9fd377d2738384c22f3e2cf7c0ab39
|
||||
size 4995584848
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8a10f69d81c3dc22b3d003ba799f635db3213d6a52ed5549ee32ba65d235afff
|
||||
size 563833008
|
||||
460
model.safetensors.index.json
Normal file
460
model.safetensors.index.json
Normal file
@@ -0,0 +1,460 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5559367680
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.bias": "model-00002-of-00002.safetensors",
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.final_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
3
phi2-bunny-q4_k_m.gguf
Normal file
3
phi2-bunny-q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1252eda9048185944ca77fb8600bb2ea8f6c335ce87aa5838b02207ffaa931c9
|
||||
size 1737637120
|
||||
3
phi2-bunny-q5_k_m.gguf
Normal file
3
phi2-bunny-q5_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c82db0c85e5be387c1497575638167383fcd9fd854db3bfb2c5451248e72019c
|
||||
size 2003057920
|
||||
3
phi2-bunny-q8_0.gguf
Normal file
3
phi2-bunny-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cf9f5e4bca851e2a993d93129375aea08703777230a056776aa07d28f66f827a
|
||||
size 2958040320
|
||||
460
pytorch_model.bin.index.json
Normal file
460
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,460 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5559367680
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.final_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
100665
tokenizer.json
Normal file
100665
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
341
tokenizer_config.json
Normal file
341
tokenizer_config.json
Normal file
@@ -0,0 +1,341 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"50256": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50257": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50270": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50271": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50272": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50273": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50274": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50275": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50276": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50277": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50278": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50279": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50280": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50281": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50282": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50283": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50284": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50285": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50286": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50287": {
|
||||
"content": "\t\t\t\t\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50288": {
|
||||
"content": "\t\t\t\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50289": {
|
||||
"content": "\t\t\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50290": {
|
||||
"content": "\t\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50291": {
|
||||
"content": "\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50292": {
|
||||
"content": "\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50293": {
|
||||
"content": "\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50294": {
|
||||
"content": "\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50295": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50296": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|im_end|>",
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "CodeGenTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:de26191eb112fbf3eeef230d19125183a92832834ac54b80a89ca357303f2acb
|
||||
size 5240
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user