初始化项目，由ModelHub XC社区提供模型
Model: shisa-ai/ablation-177-finalsft2-shisa-v2-mistral-nemo-12b Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 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
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack 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
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* 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
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
288
README.md
Normal file
288
README.md
Normal file
@@ -0,0 +1,288 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: apache-2.0
|
||||||
|
base_model: mistralai/Mistral-Nemo-Instruct-2407
|
||||||
|
tags:
|
||||||
|
- generated_from_trainer
|
||||||
|
datasets:
|
||||||
|
- shisa-ai/shisa-v2-best-of-n-athenev2-tulu70b-llama33-only-no-sysprompt
|
||||||
|
- shisa-ai/shisa-v2-roleplaying-sft
|
||||||
|
- shisa-ai/translation_set_april_6
|
||||||
|
- shisa-ai/rewild-set-deepseek-subset
|
||||||
|
- shisa-ai/magpie-ultra-set
|
||||||
|
- shisa-ai/magpie-advanced-questions-set
|
||||||
|
- shisa-ai/japan-magpie-set
|
||||||
|
- shisa-ai/shisa-v2-instruction-following-sft
|
||||||
|
model-index:
|
||||||
|
- name: outputs/ablation-177-finalsft2-shisa-v2-mistral-nemo-12b
|
||||||
|
results: []
|
||||||
|
---
|
||||||
|
|
||||||
|
<!-- 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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
||||||
|
<details><summary>See axolotl config</summary>
|
||||||
|
|
||||||
|
axolotl version: `0.8.0.dev0`
|
||||||
|
```yaml
|
||||||
|
# train w/ shisa-ai/shisa-v1-athenev2-reannotated-filtered
|
||||||
|
|
||||||
|
base_model: mistralai/Mistral-Nemo-Instruct-2407
|
||||||
|
tokenizer_type: AutoTokenizer
|
||||||
|
|
||||||
|
load_in_8bit: false
|
||||||
|
load_in_4bit: false
|
||||||
|
strict: false
|
||||||
|
|
||||||
|
# User Liger
|
||||||
|
plugins:
|
||||||
|
- axolotl.integrations.liger.LigerPlugin
|
||||||
|
liger_rope: true
|
||||||
|
liger_rms_norm: true
|
||||||
|
liger_glu_activation: true
|
||||||
|
liger_fused_linear_cross_entropy: true
|
||||||
|
|
||||||
|
chat_template: tokenizer_default
|
||||||
|
datasets:
|
||||||
|
- path: shisa-ai/shisa-v2-best-of-n-athenev2-tulu70b-llama33-only-no-sysprompt
|
||||||
|
type: chat_template
|
||||||
|
field_messages: conversations
|
||||||
|
message_field_role: from
|
||||||
|
message_field_content: value
|
||||||
|
- path: shisa-ai/shisa-v2-roleplaying-sft
|
||||||
|
type: chat_template
|
||||||
|
field_messages: conversations
|
||||||
|
message_property_mappings:
|
||||||
|
role: role
|
||||||
|
content: content
|
||||||
|
roles:
|
||||||
|
system:
|
||||||
|
- system
|
||||||
|
assistant:
|
||||||
|
- gpt
|
||||||
|
- model
|
||||||
|
- assistant
|
||||||
|
user:
|
||||||
|
- human
|
||||||
|
- user
|
||||||
|
roles_to_train: ["assistant"]
|
||||||
|
- path: shisa-ai/translation_set_april_6
|
||||||
|
split: train[:25%]
|
||||||
|
type: chat_template
|
||||||
|
field_messages: conversations
|
||||||
|
message_property_mappings:
|
||||||
|
role: role
|
||||||
|
content: content
|
||||||
|
roles:
|
||||||
|
system:
|
||||||
|
- system
|
||||||
|
assistant:
|
||||||
|
- gpt
|
||||||
|
- model
|
||||||
|
- assistant
|
||||||
|
user:
|
||||||
|
- human
|
||||||
|
- user
|
||||||
|
roles_to_train: ["assistant"]
|
||||||
|
- path: shisa-ai/rewild-set-deepseek-subset
|
||||||
|
split: train[:25%]
|
||||||
|
type: chat_template
|
||||||
|
field_messages: conversations
|
||||||
|
message_property_mappings:
|
||||||
|
role: role
|
||||||
|
content: content
|
||||||
|
roles:
|
||||||
|
system:
|
||||||
|
- system
|
||||||
|
assistant:
|
||||||
|
- gpt
|
||||||
|
- model
|
||||||
|
- assistant
|
||||||
|
user:
|
||||||
|
- human
|
||||||
|
- user
|
||||||
|
roles_to_train: ["assistant"]
|
||||||
|
- path: shisa-ai/magpie-ultra-set
|
||||||
|
split: train[:8%]
|
||||||
|
type: chat_template
|
||||||
|
field_messages: conversations
|
||||||
|
message_property_mappings:
|
||||||
|
role: role
|
||||||
|
content: content
|
||||||
|
roles:
|
||||||
|
system:
|
||||||
|
- system
|
||||||
|
assistant:
|
||||||
|
- gpt
|
||||||
|
- model
|
||||||
|
- assistant
|
||||||
|
user:
|
||||||
|
- human
|
||||||
|
- user
|
||||||
|
roles_to_train: ["assistant"]
|
||||||
|
- path: shisa-ai/magpie-advanced-questions-set
|
||||||
|
split: train[:8%]
|
||||||
|
type: chat_template
|
||||||
|
field_messages: conversations
|
||||||
|
message_property_mappings:
|
||||||
|
role: role
|
||||||
|
content: content
|
||||||
|
roles:
|
||||||
|
system:
|
||||||
|
- system
|
||||||
|
assistant:
|
||||||
|
- gpt
|
||||||
|
- model
|
||||||
|
- assistant
|
||||||
|
user:
|
||||||
|
- human
|
||||||
|
- user
|
||||||
|
roles_to_train: ["assistant"]
|
||||||
|
- path: shisa-ai/japan-magpie-set
|
||||||
|
split: train
|
||||||
|
type: chat_template
|
||||||
|
field_messages: conversations
|
||||||
|
message_property_mappings:
|
||||||
|
role: role
|
||||||
|
content: content
|
||||||
|
roles:
|
||||||
|
system:
|
||||||
|
- system
|
||||||
|
assistant:
|
||||||
|
- gpt
|
||||||
|
- model
|
||||||
|
- assistant
|
||||||
|
user:
|
||||||
|
- human
|
||||||
|
- user
|
||||||
|
roles_to_train: ["assistant"]
|
||||||
|
- path: shisa-ai/shisa-v2-instruction-following-sft
|
||||||
|
split: train[:50%]
|
||||||
|
type: chat_template
|
||||||
|
field_messages: conversations
|
||||||
|
message_property_mappings:
|
||||||
|
role: role
|
||||||
|
content: content
|
||||||
|
roles:
|
||||||
|
system:
|
||||||
|
- system
|
||||||
|
assistant:
|
||||||
|
- gpt
|
||||||
|
- model
|
||||||
|
- assistant
|
||||||
|
user:
|
||||||
|
- human
|
||||||
|
- user
|
||||||
|
roles_to_train: ["assistant"]
|
||||||
|
|
||||||
|
dataset_prepared_path: last_run_prepared
|
||||||
|
val_set_size: 0.05
|
||||||
|
output_dir: ./outputs/ablation-177-finalsft2-shisa-v2-mistral-nemo-12b
|
||||||
|
|
||||||
|
sequence_len: 8192
|
||||||
|
sample_packing: true
|
||||||
|
pad_to_sequence_len: true
|
||||||
|
|
||||||
|
# marginal difference
|
||||||
|
neftune_noise_alpha: 5
|
||||||
|
|
||||||
|
use_wandb: true
|
||||||
|
wandb_project: shisa-v2
|
||||||
|
wandb_entity: augmxnt
|
||||||
|
wandb_name: ablation-177-finalsft2-shisa-v2-mistral-nemo-12b
|
||||||
|
|
||||||
|
gradient_accumulation_steps: 1
|
||||||
|
micro_batch_size: 4
|
||||||
|
num_epochs: 3
|
||||||
|
optimizer: paged_adamw_8bit
|
||||||
|
lr_scheduler: linear
|
||||||
|
learning_rate: 8.2e-6
|
||||||
|
|
||||||
|
train_on_inputs: false
|
||||||
|
group_by_length: false
|
||||||
|
bf16: auto
|
||||||
|
fp16:
|
||||||
|
tf32: false
|
||||||
|
|
||||||
|
gradient_checkpointing: true
|
||||||
|
gradient_checkpointing_kwargs:
|
||||||
|
use_reentrant: false
|
||||||
|
early_stopping_patience:
|
||||||
|
resume_from_checkpoint:
|
||||||
|
logging_steps: 1
|
||||||
|
xformers_attention:
|
||||||
|
flash_attention: true
|
||||||
|
|
||||||
|
warmup_steps: 100
|
||||||
|
evals_per_epoch: 2
|
||||||
|
eval_table_size:
|
||||||
|
saves_per_epoch: 0
|
||||||
|
save_total_limit: 1 # Only store a single checkpoint
|
||||||
|
debug:
|
||||||
|
deepspeed: zero3_bf16.json
|
||||||
|
weight_decay: 1e-4
|
||||||
|
fsdp:
|
||||||
|
fsdp_config:
|
||||||
|
special_tokens:
|
||||||
|
pad_token: <pad>
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
</details><br>
|
||||||
|
|
||||||
|
# outputs/ablation-177-finalsft2-shisa-v2-mistral-nemo-12b
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the shisa-ai/shisa-v2-best-of-n-athenev2-tulu70b-llama33-only-no-sysprompt, the shisa-ai/shisa-v2-roleplaying-sft, the shisa-ai/translation_set_april_6, the shisa-ai/rewild-set-deepseek-subset, the shisa-ai/magpie-ultra-set, the shisa-ai/magpie-advanced-questions-set, the shisa-ai/japan-magpie-set and the shisa-ai/shisa-v2-instruction-following-sft datasets.
|
||||||
|
It achieves the following results on the evaluation set:
|
||||||
|
- Loss: 0.5948
|
||||||
|
|
||||||
|
## Model description
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Intended uses & limitations
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training and evaluation data
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
### Training hyperparameters
|
||||||
|
|
||||||
|
The following hyperparameters were used during training:
|
||||||
|
- learning_rate: 8.2e-06
|
||||||
|
- train_batch_size: 4
|
||||||
|
- eval_batch_size: 4
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- num_devices: 32
|
||||||
|
- total_train_batch_size: 128
|
||||||
|
- total_eval_batch_size: 128
|
||||||
|
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||||
|
- lr_scheduler_type: linear
|
||||||
|
- lr_scheduler_warmup_steps: 100
|
||||||
|
- num_epochs: 3.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
| Training Loss | Epoch | Step | Validation Loss |
|
||||||
|
|:-------------:|:------:|:----:|:---------------:|
|
||||||
|
| 0.9785 | 0.0025 | 1 | 0.9577 |
|
||||||
|
| 0.6062 | 0.5 | 199 | 0.6314 |
|
||||||
|
| 0.6085 | 1.0 | 398 | 0.5994 |
|
||||||
|
| 0.5382 | 1.5 | 597 | 0.5941 |
|
||||||
|
| 0.4897 | 2.0 | 796 | 0.5834 |
|
||||||
|
| 0.415 | 2.5 | 995 | 0.5982 |
|
||||||
|
| 0.4268 | 3.0 | 1194 | 0.5948 |
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.50.0
|
||||||
|
- Pytorch 2.6.0+cu124
|
||||||
|
- Datasets 3.4.1
|
||||||
|
- Tokenizers 0.21.1
|
||||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"MistralForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"model_type": "mistral",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.50.0",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 131072
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"transformers_version": "4.50.0"
|
||||||
|
}
|
||||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ff7bcd91c167e9508c11a292c75c17bca37288dd6106a2211877049d2c1ceeb8
|
||||||
|
size 4865522496
|
||||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7d6f346b6960806d104ecacca9a0e264edc9aa84e4f7b2e5a10a4a3ba82bf4ba
|
||||||
|
size 4907529424
|
||||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c6a7ee9a7e5219b94c03aab6630931a82ea92025014c64a8c6d9cb03a83b35d4
|
||||||
|
size 4907529456
|
||||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:826c82509f1199a891fa5a28a741397ea55c0f7fe9ea935c3384587e082f6d7e
|
||||||
|
size 4907529456
|
||||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7e15d1d7906a60dab28ef7db6b15f087b9f3d899193cb5077f31e979d4f2aa91
|
||||||
|
size 4907496272
|
||||||
370
model.safetensors.index.json
Normal file
370
model.safetensors.index.json
Normal file
@@ -0,0 +1,370 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 24495564800
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
|
||||||
|
size 17078292
|
||||||
8020
tokenizer_config.json
Normal file
8020
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
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 sha256:259a81b0e3321a44aa969647bcca50ed44905ef87d2df8659672f85bf47d2fee
|
||||||
|
size 12600
|
||||||
Reference in New Issue
Block a user