初始化项目，由ModelHub XC社区提供模型
Model: DopeorNope/You_can_cry_Snowman-13B 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
|
||||
65
README.md
Normal file
65
README.md
Normal file
@@ -0,0 +1,65 @@
|
||||
---
|
||||
language:
|
||||
- ko
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
license: cc-by-nc-sa-4.0
|
||||
---
|
||||
**The license is `cc-by-nc-sa-4.0`.**
|
||||
|
||||
# **🐻❄️You_can_cry_Snowman-13B🐻❄️**
|
||||
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
**Model Developers** Seungyoo Lee(DopeorNope)
|
||||
|
||||
I am in charge of Large Language Models (LLMs) at Markr AI team in South Korea.
|
||||
|
||||
**Input** Models input text only.
|
||||
|
||||
**Output** Models generate text only.
|
||||
|
||||
**Model Architecture**
|
||||
You_can_cry_Snowman-13B is an auto-regressive language model based on the SOLAR architecture.
|
||||
|
||||
---
|
||||
|
||||
## **Base Model**
|
||||
|
||||
[kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
|
||||
|
||||
[Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct](https://huggingface.co/Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct)
|
||||
|
||||
|
||||
## **Implemented Method**
|
||||
|
||||
I have merged two models by increasing the parameter size to create a larger model.
|
||||
|
||||
I wanted to check how much the performance of the SOLAR base model changes when the scale of the parameters is increased.
|
||||
|
||||
---
|
||||
|
||||
# Implementation Code
|
||||
|
||||
|
||||
## Load model
|
||||
```python
|
||||
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
|
||||
repo = "DopeorNope/You_can_cry_Snowman-13B"
|
||||
OpenOrca = AutoModelForCausalLM.from_pretrained(
|
||||
repo,
|
||||
return_dict=True,
|
||||
torch_dtype=torch.float16,
|
||||
device_map='auto'
|
||||
)
|
||||
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
|
||||
```
|
||||
|
||||
|
||||
---
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "solar-scaled-up",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 60,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.36.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
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": 2,
|
||||
"transformers_version": "4.36.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00011.safetensors
Normal file
3
model-00001-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cec3b481edf5c9b1da28e5d65f008dae7e53430df908b7b1315b7d9c46e27067
|
||||
size 4987196936
|
||||
3
model-00002-of-00011.safetensors
Normal file
3
model-00002-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d0a8aa7f27526f6495fd859da04153939e472fbfdbc938650afd63ead373d8bc
|
||||
size 4899116440
|
||||
3
model-00003-of-00011.safetensors
Normal file
3
model-00003-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cf1d62da4f740b0faa76a0af2588829dbad025b0c4d78b0358d2fa7532ead82c
|
||||
size 4999813120
|
||||
3
model-00004-of-00011.safetensors
Normal file
3
model-00004-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:77e8e0b90e1a9f0855080202322dcc417bde6c616097b7b995685cc35e62110c
|
||||
size 4999813128
|
||||
3
model-00005-of-00011.safetensors
Normal file
3
model-00005-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:02f365fd27090fa6da0ffb78eebab28d66ebf80c03fa0a293aaa37749b0cba76
|
||||
size 4832007496
|
||||
3
model-00006-of-00011.safetensors
Normal file
3
model-00006-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8416d1ea9fcb1506deb9b2191b29a9ce616056e4d8dbe8b752a66e76797b6fff
|
||||
size 4999813120
|
||||
3
model-00007-of-00011.safetensors
Normal file
3
model-00007-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:21cc746d6ffa2cafb7dcab63871551844d36eac48007ce7c3619034e24146e1b
|
||||
size 4999813128
|
||||
3
model-00008-of-00011.safetensors
Normal file
3
model-00008-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:48289a1cef5e9d3883447384dc1ac9d525e8fbe64fb8577b62dd47bd6512dca5
|
||||
size 4832007496
|
||||
3
model-00009-of-00011.safetensors
Normal file
3
model-00009-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:48eee3d4c510cdb229cac86448d520e4c9ccae8f4fc7458313373f8e14675f0f
|
||||
size 4999813120
|
||||
3
model-00010-of-00011.safetensors
Normal file
3
model-00010-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ec75aef5fabf845fd67110a882eb35a79a2a1c04eedf7e26eb89ef82d2da0e34
|
||||
size 4999813128
|
||||
3
model-00011-of-00011.safetensors
Normal file
3
model-00011-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:43aa352ec09a8be3d57fa1c1cdd68c4576073ff6660329dd8031d1822c4a523e
|
||||
size 3846328136
|
||||
550
model.safetensors.index.json
Normal file
550
model.safetensors.index.json
Normal file
@@ -0,0 +1,550 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 53395472384
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00011-of-00011.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.norm.weight": "model-00011-of-00011.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
43
tokenizer_config.json
Normal file
43
tokenizer_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user