初始化项目，由ModelHub XC社区提供模型
Model: IlyaGusev/saiga_nemo_12b Source: Original Platform
This commit is contained in:
ModelHub XC
42
.gitattributes
vendored
Normal file
42
.gitattributes
vendored
Normal file
@@ -0,0 +1,42 @@
|
||||
*.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
|
||||
model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
orig_adapter/adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
167
README.md
Normal file
167
README.md
Normal file
@@ -0,0 +1,167 @@
|
||||
---
|
||||
language:
|
||||
- ru
|
||||
datasets:
|
||||
- IlyaGusev/saiga_scored
|
||||
- IlyaGusev/saiga_preferences
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
|
||||
# Saiga/MistralNemo 12B, Russian fine-tune of Mistral Nemo
|
||||
|
||||
Based on [an abliterated version](https://huggingface.co/natong19/Mistral-Nemo-Instruct-2407-abliterated) of [Mistral Nemo](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407).
|
||||
|
||||
Llama.cpp version: [link](https://huggingface.co/IlyaGusev/saiga_nemo_12b_gguf)
|
||||
|
||||
Colab: [link](https://colab.research.google.com/drive/1vNzMyPqx2GB7zk3ANDtZEfvhzgYOWu0B)
|
||||
|
||||
## Prompt format
|
||||
|
||||
v3: Original Misral Nemo prompt format, but the system prompt is in the beginning:
|
||||
```
|
||||
<s>Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.
|
||||
|
||||
[INST]Как дела?[/INST]Отлично, а у тебя?</s>[INST]Шикарно. Как пройти в библиотеку?[/INST]
|
||||
```
|
||||
|
||||
v1, v2: Original Misral Nemo prompt format, but the system prompt is in the beginning and there are additional spaces:
|
||||
```
|
||||
<s>Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.
|
||||
|
||||
[INST] Как дела? [/INST] Отлично, а у тебя? </s>[INST] Шикарно. Как пройти в библиотеку? [/INST]
|
||||
```
|
||||
|
||||
## Code example
|
||||
```python
|
||||
# Исключительно ознакомительный пример.
|
||||
# НЕ НАДО ТАК ИНФЕРИТЬ МОДЕЛЬ В ПРОДЕ.
|
||||
# См. https://github.com/vllm-project/vllm или https://github.com/huggingface/text-generation-inference
|
||||
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
|
||||
|
||||
MODEL_NAME = "IlyaGusev/saiga_nemo_12b"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
MODEL_NAME,
|
||||
load_in_8bit=True,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto"
|
||||
)
|
||||
model.eval()
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
|
||||
generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
|
||||
print(generation_config)
|
||||
|
||||
inputs = ["Почему трава зеленая?", "Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч"]
|
||||
for query in inputs:
|
||||
prompt = tokenizer.apply_chat_template([{
|
||||
"role": "user",
|
||||
"content": query
|
||||
}], tokenize=False, add_generation_prompt=True)
|
||||
data = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
|
||||
data = {k: v.to(model.device) for k, v in data.items()}
|
||||
data.pop("token_type_ids", None)
|
||||
output_ids = model.generate(**data, generation_config=generation_config)[0]
|
||||
output_ids = output_ids[len(data["input_ids"][0]):]
|
||||
output = tokenizer.decode(output_ids, skip_special_tokens=True).strip()
|
||||
print(query)
|
||||
print(output)
|
||||
print()
|
||||
print("==============================")
|
||||
print()
|
||||
```
|
||||
|
||||
## Output examples
|
||||
```
|
||||
User: Почему трава зеленая?
|
||||
Saiga: Трава зеленая из-за содержания хлорофилла. Hлорофилл — это пигмент, основной компонент системы фотосинтеза в растениях (а также водорослях и некоторых бактериях). Функционирование хлорофилла обеспечивает следующие особенности:
|
||||
1. **Абсорбция света**: Хлорофилл поглощает свет в определенном диапазоне спектра, в основном синий и красный цвета. Зеленый цвет отражается обратно к нашему глазу, поскольку именно этот цвет не поглощается хлорофиллом.
|
||||
2. **Фотосинтез**: В процессе фотосинтеза хлорофилл преобразует энергию солнечного света в химическую энергию, необходимую для синтеза органических веществ (главным образом глюкозы) из углекислого газа и воды. Этот процесс поддерживает жизнь растений и является источником пищи для многих живых существ на Земле.
|
||||
3. **Структурная роль**: Хлорофилл расположен в особой структуре клеток растений – хлоропластах, которые играют ключевую роль в организации клетки.
|
||||
Таким образом, трава зеленая потому, что хлорофилл выполняет жизненно важную функцию в растении и отражает именно тот цвет света, который он не использует в своем процессе работы.
|
||||
```
|
||||
|
||||
```
|
||||
User: Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч
|
||||
Saiga: Таня и Мяч
|
||||
В далеком приморском городке, где ласковое солнце играло на волнах и свежий морской ветер наполнял воздух солью и свободой, жила девушка по имени Таня. Ее жизнь была полна ярких красок и незабываемых историй — и все благодаря одному простому предмету: мячу.
|
||||
Таня появилась в этом мире уже с мячом под мышкой. Ее отец, заядлый футбольный фанат, еще до рождения дочери решил, что она продолжит семейную спортивную традицию. И вот, когда маленькая Таня впервые сделала свои неуверенные шаги, в ее ручке оказался тот самый мяч — бледно-голубой, как небо над морем, с рисунком в виде волны, словно приглашая к приключениям.
|
||||
С тех пор мяч стал для Тани настоящим другом и спутником жизни. Они начинали каждое утро вместе: на песке у пляжа, где отпечатки ног смешивались с влажными линиями прилива; иногда на стадионе, где запахи травы и свежей росы сопровождали первые удары об мяч; а зимними днями — в просторном школьном коридоре, куда Таня выносила мяч, чтобы тренироваться прямо там, среди шумных перерывов и звонков.
|
||||
Мяч был свидетелем всех ключевых моментов ее жизни. Когда Таня в первый раз забила гол в школьной команде, он, казалось, излучал радость и гордость. Этот мяч побывал в каждом уголке города: они исследовали заброшенные склады, где Таня представляла себя героиней фильма о футболе; забрались на вершину старого маяка, откуда открывался вид на бескрайнее море; даже однажды ночью пытались пройти через весь город, запуская мяч от стены к стене, создавая свой собственный «марафон».
|
||||
Самый значительный эпизод их совместного пути произошел летом, когда Таня решила принять участие в региональных соревнованиях по футболу. Мяч, который уже успел потерять немного своей первоначальной гладкости и белизны, приобрел особое значение. Это был не просто мяч — это символ мечты, которую она носила внутри себя. В день финального матча Таня почувствовала, как каждый удар об этот мяч наполняет ее уверенностью и теплом воспоминаний. На последних минутах встречи, когда счет был равным, Таня ловко обвела соперниц и, сделав красивый финт, послала мяч точно в ворота противника. Зрители взорвались аплодисментами, а Таня упала на колени, крепко обнимая своего верного друга.
|
||||
После победы Таня поняла, что мяч стал частью её души. Его история переплеталась со всеми важными моментами её жизни. Она решила сохранить его таким, какой он есть — слегка потрепанным, но полным истории и воспоминаний. Таня повесила мяч на стену в своей комнате, рядом с фотографиями друзей, трофеев и других дорогих сердцу предметов. Теперь он смотрел на неё, напоминая о том, что путь к мечтам долгий, но каждая ступень этого пути полна смысла и радости.
|
||||
И хотя со временем Таня увлеклась другими аспектами жизни — путешествиями, учебой, новыми увлечениями — мяч всегда оставался напоминанием о том, как важно сохранять искренность намерений и верность своим мечтам. А иногда, поздними вечерами, когда в городе наступала тишина, Таня доставала мяч из коробки, где он хранился, и несколько минут просто крутила его в руках, возвращаясь в те золотые дни детства и юности, наполненные беззаботностью и радостью первого большого приключения.
|
||||
```
|
||||
|
||||
|
||||
## Versions
|
||||
|
||||
v3:
|
||||
- [d4f395741d0d363665e86533b53d5a2ec14477eb](https://huggingface.co/IlyaGusev/saiga_nemo_12b/commit/d4f395741d0d363665e86533b53d5a2ec14477eb)
|
||||
- Other names: saiga_nemo_12b_sft_m10_d16_simpo_m23_d38
|
||||
- SFT dataset config: [sft_d16.json](https://github.com/IlyaGusev/saiga/blob/main/configs/datasets/sft_d16.json)
|
||||
- SFT model config: [saiga_nemo_12b_sft_m10.json](https://github.com/IlyaGusev/saiga/blob/main/configs/models/saiga_nemo_12b_sft_m10.json)
|
||||
- SimPO dataset config: [pref_d38.json](https://github.com/IlyaGusev/saiga/blob/main/configs/datasets/pref_d38.json)
|
||||
- SimPO model config: [saiga_nemo_12b_simpo_m23.json](https://github.com/IlyaGusev/saiga/blob/main/configs/models/saiga_nemo_12b_simpo_m23.json)
|
||||
- SFT wandb: [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/hzs68let)
|
||||
- SimPO wandb: [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/hyz52bom)
|
||||
|
||||
v2:
|
||||
- [2ae4ce589c6c1c0ef3ba26521d78882ae1ae2930](https://huggingface.co/IlyaGusev/saiga_nemo_12b/commit/2ae4ce589c6c1c0ef3ba26521d78882ae1ae2930)
|
||||
- Other names: saiga_nemo_12b_sft_m9_d16_slerp, saiga_nemo_12b_sft_m9_d16_simpo_m21_d36_doestoevsky_orpo_m1_slerp
|
||||
- SFT dataset config: [sft_d16.json](https://github.com/IlyaGusev/saiga/blob/main/configs/datasets/sft_d16.json)
|
||||
- SFT model config: [saiga_nemo_12b_sft_m9.json](https://github.com/IlyaGusev/saiga/blob/main/configs/models/saiga_nemo_12b_sft_m9.json)
|
||||
- SimPO dataset config: [pref_d36.json](https://github.com/IlyaGusev/saiga/blob/main/configs/datasets/pref_d36.json)
|
||||
- SimPO model config: [saiga_nemo_12b_simpo_m21.json](https://github.com/IlyaGusev/saiga/blob/main/configs/models/saiga_nemo_12b_simpo_m21.json)
|
||||
- SFT wandb: [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/yod78hiq)
|
||||
- SimPO wandb: [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/bv5w0lxl)
|
||||
- Dostoevsky wandb: [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/senqj9t1)
|
||||
- Merge config: [link](https://huggingface.co/IlyaGusev/saiga_nemo_12b_sft_m9_d16_slerp/blob/main/mergekit_config.yml)
|
||||
|
||||
v1:
|
||||
- [1c13507be4b5b5edd5586e48c902ef61c0343299](https://huggingface.co/IlyaGusev/saiga_nemo_12b/commit/1c13507be4b5b5edd5586e48c902ef61c0343299)
|
||||
- Other name: saiga_nemo_12b_sft_m9_d14_simpo_m19_d31
|
||||
- SFT dataset config: [sft_d14.json](https://github.com/IlyaGusev/saiga/blob/main/configs/datasets/sft_d14.json)
|
||||
- SFT model config: [saiga_nemo_12b_sft_m9.json](https://github.com/IlyaGusev/saiga/blob/main/configs/models/saiga_nemo_12b_sft_m9.json)
|
||||
- SimPO dataset config: [pref_d31.json](https://github.com/IlyaGusev/saiga/blob/main/configs/datasets/pref_d31.json)
|
||||
- SimPO model config: [saiga_nemo_12b_simpo_m19.json](https://github.com/IlyaGusev/saiga/blob/main/configs/models/saiga_nemo_12b_simpo_m19.json)
|
||||
- SFT wandb: [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/e74ozfzh)
|
||||
- SimPO wandb: [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/b094iiej)
|
||||
|
||||
|
||||
## Evaluation
|
||||
|
||||
### v3:
|
||||
|
||||
RuArenaHard:
|
||||
|
||||
|
||||
|
||||
PingPong:
|
||||
|
||||
|
||||
|
||||
### v2
|
||||
|
||||
RuArenaHard:
|
||||
|
||||
|
||||
|
||||
PingPong:
|
||||
|
||||
|
||||
|
||||
### v1
|
||||
|
||||
RuArenaHard:
|
||||
|
||||
|
||||
|
||||
|
||||
PingPong:
|
||||
|
||||
|
||||
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "models/saiga_nemo_12b_sft_m10_d16",
|
||||
"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": 1024000,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 10,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.46.2",
|
||||
"unsloth_version": "2024.8",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 10,
|
||||
"max_length": 1024000,
|
||||
"max_new_tokens": 2048,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.95,
|
||||
"repetition_penalty": 1.1,
|
||||
"do_sample": true,
|
||||
"transformers_version": "4.45.1"
|
||||
}
|
||||
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 sha256:4e01174f502e70bdc4c223035c4657127389a858ef1f6781d294c22cfe9a4f4c
|
||||
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 sha256:6639be35ecdb13774edf4e31d8b09b9d471c8574786050f2d8dfa0f8e52c917c
|
||||
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 sha256:3462d55ba58de699d910d15836f25804ac82b9ddb97e0dead165ec7a78c34b6d
|
||||
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 sha256:871b498172b76841b3107fc6d0bd105b8d57a299a2bbf7ace04ed328fde75ebe
|
||||
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 sha256:13f65285e4b93b0d415d101b93eabc7edf1c09786b19811bdeed3632ef0c3984
|
||||
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"
|
||||
}
|
||||
}
|
||||
12
special_tokens_map.json
Normal file
12
special_tokens_map.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "<pad>",
|
||||
"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
|
||||
8016
tokenizer_config.json
Normal file
8016
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user