初始化项目，由ModelHub XC社区提供模型
Model: Iker/Llama-3-Instruct-Neurona-8b Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
449
README.md
Normal file
449
README.md
Normal file
@@ -0,0 +1,449 @@
|
||||
---
|
||||
library_name: transformers
|
||||
tags:
|
||||
- synthetic
|
||||
license: llama3
|
||||
datasets:
|
||||
- pinzhenchen/alpaca-cleaned-es
|
||||
- Danielbrdz/Barcenas-Economia
|
||||
- HiTZ/casimedicos-exp
|
||||
- somosnlp/coser_resumenes
|
||||
- csebuetnlp/CrossSum
|
||||
- Iker/Document-Translation-en-es
|
||||
- somosnlp/es-inclusive-language-it
|
||||
- FreedomIntelligence/evol-instruct-spanish
|
||||
- glaiveai/glaive-code-assistant-v3
|
||||
- glaiveai/glaive-function-calling-v2
|
||||
- Iker/InstructTranslation-EN-ES
|
||||
- somosnlp/lenguaje-claro-dataset
|
||||
- somosnlp/LingComp_QA
|
||||
- bltlab/lr-sum
|
||||
- Iker/NoticIA
|
||||
- xaviviro/oasst2_es_gpt
|
||||
- teknium/OpenHermes-2.5
|
||||
- Iker/OpenHermes-2.5-Spanish
|
||||
- Helsinki-NLP/opus-100
|
||||
- projecte-aina/RAG_Multilingual
|
||||
- sem_eval_2018_task_1
|
||||
- davidstap/ted_talks
|
||||
- HiTZ/This-is-not-a-dataset
|
||||
- wikipedia
|
||||
language:
|
||||
- es
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# Neurona 8B Beta: Un Modelo de Lenguage en Español
|
||||
|
||||
> Esta es una versión preliminar del dataset card. El modelo está en desarrollo y no es la versión final. Si quieres saber más sobre este modelo, escribe a iker.garciaf@ehu.eus
|
||||
|
||||
|
||||
Neurona 8B es un modelo de lenguaje en Español. Esta es la primera iteración y un experimento para poner a punto los scripts y la infraestructura.
|
||||
|
||||
Neurona 8B ha sido entrenado con los siguiente datasets. No en todos los casos se ha usado el dataset completo
|
||||
|
||||
- [pinzhenchen/alpaca-cleaned-es](https://huggingface.co/datasets/pinzhenchen/alpaca-cleaned-es)
|
||||
- [Danielbrdz/Barcenas-Economia](https://huggingface.co/datasets/Danielbrdz/Barcenas-Economia)
|
||||
- [HiTZ/casimedicos-exp](https://huggingface.co/datasets/HiTZ/casimedicos-exp)
|
||||
- [somosnlp/coser_resumenes](https://huggingface.co/datasets/somosnlp/coser_resumenes)
|
||||
- [csebuetnlp/CrossSum en + es](https://huggingface.co/datasets/csebuetnlp/CrossSum)
|
||||
- [Iker/Document-Translation-en-es](https://huggingface.co/datasets/Iker/Document-Translation-en-es)
|
||||
- [somosnlp/es-inclusive-language-it](https://huggingface.co/datasets/somosnlp/es-inclusive-language-it)
|
||||
- [FreedomIntelligence/evol-instruct-spanish](https://huggingface.co/datasets/FreedomIntelligence/evol-instruct-spanish)
|
||||
- [glaiveai/glaive-code-assistant-v3](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v3)
|
||||
- [glaiveai/glaive-function-calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)
|
||||
- [Iker/InstructTranslation-EN-ES](https://huggingface.co/datasets/Iker/InstructTranslation-EN-ES)
|
||||
- [somosnlp/lenguaje-claro-dataset](https://huggingface.co/datasets/somosnlp/lenguaje-claro-dataset)
|
||||
- [somosnlp/LingComp_QA](https://huggingface.co/datasets/somosnlp/LingComp_QA)
|
||||
- [bltlab/lr-sum](https://huggingface.co/datasets/bltlab/lr-sum)
|
||||
- [Iker/NoticIA](https://huggingface.co/datasets/Iker/NoticIA)
|
||||
- [xaviviro/oasst2_es_gpt](https://huggingface.co/datasets/xaviviro/oasst2_es_gpt)
|
||||
- [teknium/OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5)
|
||||
- [Iker/OpenHermes-2.5-Spanish](https://huggingface.co/datasets/Iker/OpenHermes-2.5-Spanish)
|
||||
- [Helsinki-NLP/opus-100 en es](https://huggingface.co/datasets/Helsinki-NLP/opus-100)
|
||||
- [projecte-aina/RAG_Multilingual](https://huggingface.co/datasets/projecte-aina/RAG_Multilingual)
|
||||
- [sem_eval_2018_task_1](https://huggingface.co/datasets/sem_eval_2018_task_1)
|
||||
- [davidstap/ted_talks](https://huggingface.co/datasets/davidstap/ted_talks)
|
||||
- [HiTZ/This-is-not-a-dataset](https://huggingface.co/datasets/HiTZ/This-is-not-a-dataset)
|
||||
- [wikipedia es](https://huggingface.co/datasets/wikipedia)
|
||||
|
||||
|
||||
|
||||
|
||||
Esta mezcla de datasets en Inglés y Español, permite al modelo adquirir diferentes capacidades, como RAG, function calling, code assistant, question answering, summarization... tanto en Inglés como en Español.
|
||||
|
||||
# Entrenamiento
|
||||
|
||||
Este modelo se ha entrado usando 4xNvidia A100 80Gb y axolotl
|
||||
[<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)
|
||||
|
||||
Esta es la configuración usada
|
||||
|
||||
```yaml
|
||||
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
||||
model_type: AutoModelForCausalLM
|
||||
tokenizer_type: AutoTokenizer
|
||||
is_falcon_derived_model:
|
||||
is_llama_derived_model:
|
||||
is_qwen_derived_model:
|
||||
is_mistral_derived_model:
|
||||
|
||||
load_in_8bit: false
|
||||
load_in_4bit: false
|
||||
strict: false
|
||||
|
||||
device_map: null
|
||||
|
||||
datasets:
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/alpaca-cleaned-es.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/Barcenas-Economia.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/casimedicos.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/coser_resumene.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/CrossSum_en.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/CrossSum_es.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/Document-Translation-en-es.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/es-inclusive-language.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/evol-instruct-spanish.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/glaive-code-assistant-v3-small.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/glaive-function-calling-v2.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
- tool
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/InstructTranslation-EN-ES.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/lenguaje-claro-dataset.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/LingComp_QA.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/lr-sum-es.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/NoticIA.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/NoticIA-large.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/NoticIA-summary.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/oasst2_es_gpt.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/OpenHermes-2.5-English.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/OpenHermes-2.5-Spanish.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/opus-100-en-es.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/RAG_Multilingual-es.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/sem_eval_2018_task_1.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/ted_talks-es_en.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/This-is-not-a-dataset.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
- path: /ikerlariak/igarcia945/InstructDatasets/wikipedia-es.jsonl
|
||||
type: sharegpt
|
||||
conversation: llama3
|
||||
field: conversations
|
||||
roles:
|
||||
input:
|
||||
- system
|
||||
- gpt
|
||||
output:
|
||||
- human
|
||||
|
||||
chat_template: llama3
|
||||
|
||||
dataset_prepared_path: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Instruct-Spanish/dataset
|
||||
|
||||
shuffle_merged_datasets: true
|
||||
|
||||
val_set_size: 0.005
|
||||
|
||||
output_dir: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Instruct-Spanish
|
||||
|
||||
adapter:
|
||||
lora_model_dir:
|
||||
|
||||
sequence_len: 8192
|
||||
sample_packing: true
|
||||
eval_sample_packing: false
|
||||
pad_to_sequence_len: false
|
||||
|
||||
tokens:
|
||||
- "<tool_call>"
|
||||
- "<tool_response>"
|
||||
- "<tools>"
|
||||
- "</tool_call>"
|
||||
- "</tool_response>"
|
||||
- "</tools>"
|
||||
- "<reserved1>"
|
||||
- "<reserved2>"
|
||||
|
||||
special_tokens:
|
||||
pad_token: <|end_of_text|>
|
||||
|
||||
neftune_noise_alpha: 5
|
||||
|
||||
wandb_project: Mortadelo&Filemon
|
||||
wandb_entity: igarciaf
|
||||
wandb_watch:
|
||||
wandb_name: Meta-Llama-3-8B-Instruct-Spanish
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 32
|
||||
micro_batch_size: 2
|
||||
eval_batch_size: 2
|
||||
num_epochs: 2
|
||||
optimizer: adamw_torch_fused
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 0.00007
|
||||
|
||||
|
||||
train_on_inputs: false
|
||||
group_by_length: false
|
||||
bf16: true
|
||||
fp16: false
|
||||
tf32: false
|
||||
|
||||
gradient_checkpointing: true
|
||||
early_stopping_patience:
|
||||
resume_from_checkpoint:
|
||||
local_rank:
|
||||
logging_steps: 1
|
||||
xformers_attention:
|
||||
flash_attention: true
|
||||
|
||||
warmup_ratio: 0.03
|
||||
evals_per_epoch: 4
|
||||
eval_table_size:
|
||||
save_strategy: "no"
|
||||
debug:
|
||||
deepspeed: /ikerlariak/igarcia945/Mortadelo-Filemon/train_configs/deepspeed_zero3.json
|
||||
weight_decay: 0.0
|
||||
fsdp:
|
||||
fsdp_config:
|
||||
|
||||
seed: 33
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/tartalo01/users/igarcia945/ikerlariak/Mortadelo-Filemon/Meta-Llama-3-8B-Instruct-Spanish",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128009,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128264
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128009
|
||||
],
|
||||
"max_length": 4096,
|
||||
"pad_token_id": 128001,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.40.0"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:021494d68d730e359ed08c105397899042c4429e287bf94b59d2c2665b271746
|
||||
size 4976764208
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:536b68dd84463ac24c755ae0b7ab93b4e0213d470c912f5b8367beaa951451f3
|
||||
size 4999802720
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c838c2e9c59feeb205051144bf461c7da20cad695ddef5bc31bbeaafdbd63133
|
||||
size 4915916176
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd1e39b47ca1e7443f0ac3f55eae0cfb8fc7ec436706ad4b10c79d6cb1e6f56f
|
||||
size 1168204344
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060653568
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
410635
tokenizer.json
Normal file
410635
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2129
tokenizer_config.json
Normal file
2129
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user