初始化项目，由ModelHub XC社区提供模型
Model: beomi/Yi-Ko-6B 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
|
||||
5
LICENSE.md
Normal file
5
LICENSE.md
Normal file
@@ -0,0 +1,5 @@
|
||||
[Yi Series Models Community License Agreement](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE)
|
||||
|
||||
> For commercial purpose,
|
||||
> Follow [Yi Series Models Community License Agreement](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) to acquire Yi Series commercial license,
|
||||
> and mailto: jun@beomi.net to acquire Yi-Ko sereis commercial license.
|
||||
238
README.md
Normal file
238
README.md
Normal file
@@ -0,0 +1,238 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
- ko
|
||||
library_name: transformers
|
||||
tags:
|
||||
- pytorch
|
||||
- Yi-Ko
|
||||
- 01-ai
|
||||
- Yi
|
||||
extra_gated_heading: Access beomi/Yi-Ko-6B on Hugging Face
|
||||
extra_gated_button_content: Submit
|
||||
extra_gated_fields:
|
||||
I agree to share my name, email address and username: checkbox
|
||||
? I confirm that I understand this project is for research purposes only, and confirm
|
||||
that I agree to follow the LICENSE of this model
|
||||
: checkbox
|
||||
pipeline_tag: text-generation
|
||||
inference: false
|
||||
model-index:
|
||||
- name: Yi-Ko-6B
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 48.89
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 74.48
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 55.72
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 37.09
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 72.93
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 12.51
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B
|
||||
name: Open LLM Leaderboard
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
> Update @ 2024.01.29 New Model [beomi/Yi-Ko-DUS-9B](https://huggingface.co/beomi/Yi-Ko-DUS-9B) Released! 🎉
|
||||
|
||||
> Update @ 2023.12.03 Yi-Ko(KoEN)-6B Achieved #1🥇 Pretrained Models at [Open Korean LLM Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)! 🎉
|
||||
|
||||
> Update @ 2023.12.01 Alpha Release of Yi-Ko(KoEN)-6B model 🎉
|
||||
|
||||
# **beomi/Yi-Ko-6B**
|
||||
|
||||
Yi-Ko series models serve as advanced iterations of 01-ai/Yi models,
|
||||
benefiting from an expanded vocabulary and the inclusion of Korean/English corpus in its further pretraining.
|
||||
Just like its predecessor, Yi-Ko series models operate within the broad range of generative text models that stretch from 6 billion to 34 billion parameters.
|
||||
This repository focuses on the **6B** pretrained version,
|
||||
which is tailored to fit the Hugging Face Transformers format.
|
||||
For access to the other models, feel free to consult the index provided below.
|
||||
|
||||
## Model Details
|
||||
|
||||
**Model Developers** Junbum Lee (Beomi)
|
||||
|
||||
**Variations** Yi-Ko series will come in a range of parameter sizes — 6B and 34B variations.
|
||||
|
||||
**Input** Models input text only.
|
||||
|
||||
**Output** Models generate text only.
|
||||
|
||||
**Model Architecture**
|
||||
|
||||
Yi-Ko series models are an auto-regressive language model that uses an optimized transformer architecture based on Llama-2*.
|
||||
|
||||
<small>*Yi model architecture is based on Llama2, so it can be loaded via `LlamaForCausalLM` class on HF.</small>
|
||||
|
||||
|Model Name|Training Data|Params|Context Length|GQA|Trained Tokens|LR|Batch Size(per step)|
|
||||
|---|---|---|---|---|---|---|---|
|
||||
|Yi-Ko-6B|*A mix of Korean + English online data*|6B|4k|O|>60B|5e<sup>-5</sup>|2048|
|
||||
|
||||
**Vocab Expansion**
|
||||
|
||||
| Model Name | Vocabulary Size | Description |
|
||||
| --- | --- | --- |
|
||||
| Original Yi-Series | 64000 | Sentencepiece BPE |
|
||||
| **Expanded Yi-Ko Series** | 78464 | Sentencepiece BPE. Added Korean vocab and merges |
|
||||
|
||||
**Tokenizing "안녕하세요, 오늘은 날씨가 좋네요.ㅎㅎ"**
|
||||
|
||||
| Model | # of tokens | Tokens |
|
||||
| --- | --- | --- |
|
||||
| Original Yi-Series | 47 | `['<0xEC>', '<0x95>', '<0x88>', '<0xEB>', '<0x85>', '<0x95>', '하', '<0xEC>', '<0x84>', '<0xB8>', '<0xEC>', '<0x9A>', '<0x94>', ',', '▁', '<0xEC>', '<0x98>', '<0xA4>', '<0xEB>', '<0x8A>', '<0x98>', '은', '▁', '<0xEB>', '<0x82>', '<0xA0>', '<0xEC>', '<0x94>', '<0xA8>', '가', '▁', '<0xEC>', '<0xA2>', '<0x8B>', '<0xEB>', '<0x84>', '<0xA4>', '<0xEC>', '<0x9A>', '<0x94>', '.', '<0xE3>', '<0x85>', '<0x8E>', '<0xE3>', '<0x85>', '<0x8E>']` |
|
||||
| **Expanded Yi-Ko Series** | 10 | `['▁안녕', '하세요', ',', '▁오늘은', '▁날', '씨가', '▁좋네요', '.', 'ㅎ', 'ㅎ']` |
|
||||
|<small>*Equal Korean vocab with Llama-2-Ko Series</small>||
|
||||
|
||||
**Tokenizing "Llama 2: Open Foundation and Fine-Tuned Chat Models"**
|
||||
|
||||
| Model | # of tokens | Tokens |
|
||||
| --- | --- | --- |
|
||||
| Original Yi-Series | 21 | `['The', '▁Y', 'i', '▁series', '▁models', '▁are', '▁large', '▁language', '▁models', '▁trained', '▁from', '▁scratch', '▁by', '▁developers', '▁at', '▁', '0', '1', '.', 'AI', '.']` |
|
||||
| **Expanded Yi-Ko Series** | 21 | `['▁The', '▁Y', 'i', '▁series', '▁models', '▁are', '▁large', '▁language', '▁models', '▁trained', '▁from', '▁scratch', '▁by', '▁developers', '▁at', '▁', '0', '1', '.', 'AI', '.']` |
|
||||
|<small>*Equal Korean vocab with Llama-2-Ko Series</small>| | <small>*Since **Expanded Yi-Ko Series** prepends `_` at the beginning of the text(to ensure same tokenization for Korean sentences), it shows negilible difference for the first token on English tokenization. </small>|
|
||||
|
||||
# **Model Benchmark**
|
||||
|
||||
## LM Eval Harness - Korean (polyglot branch)
|
||||
|
||||
| beomi/Yi-Ko-6B | 0 | 5 | 10 | 50 |
|
||||
|:---------------------------------|---------:|---------:|---------:|---------:|
|
||||
| kobest_boolq (macro_f1) | 0.705806 | 0.79905 | 0.814299 | 0.81704 |
|
||||
| kobest_copa (macro_f1) | 0.775604 | 0.808899 | 0.816866 | 0.842943 |
|
||||
| kobest_hellaswag (macro_f1) | 0.500876 | 0.498673 | 0.493507 | 0.492183 |
|
||||
| kobest_sentineg (macro_f1) | 0.404371 | 0.967254 | 0.982368 | 0.974811 |
|
||||
| kohatespeech (macro_f1) | 0.353428 | 0.351804 | 0.402423 | 0.503764 |
|
||||
| kohatespeech_apeach (macro_f1) | 0.337667 | 0.498679 | 0.471962 | 0.608401 |
|
||||
| kohatespeech_gen_bias (macro_f1) | 0.124535 | 0.484745 | 0.474475 | 0.461714 |
|
||||
| korunsmile (f1) | 0.382804 | 0.349344 | 0.391383 | 0.432875 |
|
||||
| nsmc (acc) | 0.55064 | 0.8801 | 0.89866 | 0.9071 |
|
||||
| pawsx_ko (acc) | 0.5145 | 0.54 | 0.538 | 0.5165 |
|
||||
|
||||
## LICENSE
|
||||
|
||||
Apache 2.0 (for research)
|
||||
|
||||
> For commercial purpose,
|
||||
> mailto: jun@beomi.net to acquire Yi-Ko sereis commercial license.
|
||||
|
||||
## Citation
|
||||
|
||||
Please use this bibtex below:
|
||||
|
||||
```
|
||||
@misc {lee_junbum_2024,
|
||||
author = { {Lee Junbum} },
|
||||
title = { Yi-Ko-6B (Revision 205083a) },
|
||||
year = 2024,
|
||||
url = { https://huggingface.co/beomi/Yi-Ko-6B },
|
||||
doi = { 10.57967/hf/1708 },
|
||||
publisher = { Hugging Face }
|
||||
}
|
||||
```
|
||||
|
||||
## Acknowledgement
|
||||
|
||||
The training is supported by [TPU Research Cloud](https://sites.research.google/trc/) program.
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_beomi__Yi-Ko-6B)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |50.27|
|
||||
|AI2 Reasoning Challenge (25-Shot)|48.89|
|
||||
|HellaSwag (10-Shot) |74.48|
|
||||
|MMLU (5-Shot) |55.72|
|
||||
|TruthfulQA (0-shot) |37.09|
|
||||
|Winogrande (5-shot) |72.93|
|
||||
|GSM8k (5-shot) |12.51|
|
||||
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "./yi-ko-6b/",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.33.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 78464
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.33.1"
|
||||
}
|
||||
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 sha256:348afd653b69d31657d6032c428005d466795bccd695646d719148f03b50c7e2
|
||||
size 2974915464
|
||||
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 sha256:089bfbe2889e412b999d21fa7bb979c961ff5c115f260edf3f6390a4d59a1f38
|
||||
size 2934072256
|
||||
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 sha256:5418137ecfb05ce39a0ab22df28cd4c287462e73d6da8416d7498014ee1cc9ff
|
||||
size 2948735384
|
||||
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 sha256:734e99412144fdc143d17e39776169e6f0eff0a77b0073d67df21c000d4163ba
|
||||
size 2858582624
|
||||
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:bbed44aab918ccf264bbf61ab8844a8b76636fe39987c13e90ebceec42698896
|
||||
size 642777216
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 12359049216
|
||||
},
|
||||
"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-00003-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-00004-of-00005.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-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-00004-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-00004-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-00004-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-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.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-00001-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-00004-of-00005.safetensors"
|
||||
}
|
||||
}
|
||||
3
pytorch_model-00001-of-00005.bin
Normal file
3
pytorch_model-00001-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:85bf7c61e8fd849ec985e0d99a8edba68b761796807cf23c0a35bea0c46100d2
|
||||
size 2974928793
|
||||
3
pytorch_model-00002-of-00005.bin
Normal file
3
pytorch_model-00002-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:73e5599ddefd3aa5878d1594a11b9ee4acdd19d5873654ee12653da923a39154
|
||||
size 2934089629
|
||||
3
pytorch_model-00003-of-00005.bin
Normal file
3
pytorch_model-00003-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:63950f690c75655ffa5162ae2c923924e4a8f3f68589c3a7ae9bd7bb421745b5
|
||||
size 2948751619
|
||||
3
pytorch_model-00004-of-00005.bin
Normal file
3
pytorch_model-00004-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c072ac72bd2402f20662eb6d3432d0a25ddbb1a186eac1b8f72798c4cb8e87c2
|
||||
size 2858599335
|
||||
3
pytorch_model-00005-of-00005.bin
Normal file
3
pytorch_model-00005-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:76f46cfb432796fc8fe69c23ceeba2bdeba263c652a6e7d422d81bb9cb37ebd3
|
||||
size 642778026
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 12359049216
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.norm.weight": "pytorch_model-00004-of-00005.bin"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|startoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
205530
tokenizer.json
Normal file
205530
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
447
tokenizer_config.json
Normal file
447
tokenizer_config.json
Normal file
@@ -0,0 +1,447 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|startoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78413": {
|
||||
"content": "<|sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"78414": {
|
||||
"content": "<|acc|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"78415": {
|
||||
"content": "<|rrn|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"78416": {
|
||||
"content": "<|tel|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"78417": {
|
||||
"content": "ㄱ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78418": {
|
||||
"content": "ㄴ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78419": {
|
||||
"content": "ㄷ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78420": {
|
||||
"content": "ㄹ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78421": {
|
||||
"content": "ㅁ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78422": {
|
||||
"content": "ㅂ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78423": {
|
||||
"content": "ㅅ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78424": {
|
||||
"content": "ㅇ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78425": {
|
||||
"content": "ㅈ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78426": {
|
||||
"content": "ㅊ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78427": {
|
||||
"content": "ㅋ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78428": {
|
||||
"content": "ㅌ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78429": {
|
||||
"content": "ㅍ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78430": {
|
||||
"content": "ㅎ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78431": {
|
||||
"content": "ㅏ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78432": {
|
||||
"content": "ㅐ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78433": {
|
||||
"content": "ㅑ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78434": {
|
||||
"content": "ㅒ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78435": {
|
||||
"content": "ㅓ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78436": {
|
||||
"content": "ㅔ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78437": {
|
||||
"content": "ㅕ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78438": {
|
||||
"content": "ㅖ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78439": {
|
||||
"content": "ㅗ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78440": {
|
||||
"content": "ㅘ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78441": {
|
||||
"content": "ㅙ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78442": {
|
||||
"content": "ㅚ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78443": {
|
||||
"content": "ㅛ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78444": {
|
||||
"content": "ㅜ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78445": {
|
||||
"content": "ㅝ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78446": {
|
||||
"content": "ㅞ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78447": {
|
||||
"content": "ㅟ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78448": {
|
||||
"content": "ㅠ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78449": {
|
||||
"content": "ㅡ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78450": {
|
||||
"content": "ㅢ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78451": {
|
||||
"content": "ㅣ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78452": {
|
||||
"content": "ㄲ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78453": {
|
||||
"content": "ㄳ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78454": {
|
||||
"content": "ㄵ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78455": {
|
||||
"content": "ㄶ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78456": {
|
||||
"content": "ㄺ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78457": {
|
||||
"content": "ㄻ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78458": {
|
||||
"content": "ㄼ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78459": {
|
||||
"content": "ㄽ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78460": {
|
||||
"content": "ㄾ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78461": {
|
||||
"content": "ㄿ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78462": {
|
||||
"content": "ㅀ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"78463": {
|
||||
"content": "ㅄ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|startoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"fast": true,
|
||||
"legacy": true,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<unk>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user