初始化项目，由ModelHub XC社区提供模型
Model: Undi95/Borealis-10.7B-DPO 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
|
||||
59
README.md
Normal file
59
README.md
Normal file
@@ -0,0 +1,59 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
tags:
|
||||
- not-for-all-audiences
|
||||
- nsfw
|
||||
---
|
||||
|
||||
## Borealis
|
||||
|
||||
|
||||
|
||||
Borealis-10.7B-DPO is a 10.7B model made of 48 Mistral 7B layers, finetuned for +70h on 2xA6000 on a big RP and Conversational dataset with llama2 configuration of Axolotl, like SOLAR.
|
||||
|
||||
This variant had a DPO train on top of it.
|
||||
|
||||
<!-- description start -->
|
||||
## Description
|
||||
|
||||
This repo contains fp16 files of Borealis-10.7B-DPO, a conversational model.
|
||||
|
||||
The goal of this model isn't to break all benchmark, but to have a better RP/ERP/Conversational model.
|
||||
|
||||
It was trained on multiple basic dataset to make it intelligent, but majority of the dataset was basic conversations.
|
||||
|
||||
<!-- description end -->
|
||||
<!-- description start -->
|
||||
## Dataset used
|
||||
|
||||
- NobodyExistsOnTheInternet/ToxicQAFinal
|
||||
- teknium/openhermes
|
||||
- unalignment/spicy-3.1
|
||||
- Doctor-Shotgun/no-robots-sharegpt
|
||||
- Undi95/toxic-dpo-v0.1-sharegpt
|
||||
- Aesir [1], [2], [3-SFW], [3-NSFW]
|
||||
- lemonilia/LimaRP
|
||||
- Squish42/bluemoon-fandom-1-1-rp-cleaned
|
||||
- Undi95/ConversationChronicles-sharegpt-SHARDED (2 sets, modified)
|
||||
|
||||
## DPO Dataset used
|
||||
|
||||
- Intel/orca_dpo_pairs
|
||||
- NobodyExistsOnTheInternet/ToxicDPOqa
|
||||
- Undi95/toxic-dpo-v0.1-NoWarning
|
||||
|
||||
<!-- description end -->
|
||||
<!-- prompt-template start -->
|
||||
## Prompt format: NsChatml
|
||||
```
|
||||
<|im_system|>
|
||||
{sysprompt}<|im_end|>
|
||||
<|im_user|>
|
||||
{input}<|im_end|>
|
||||
<|im_bot|>
|
||||
{output}<|im_end|>
|
||||
```
|
||||
|
||||
## Others
|
||||
|
||||
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
||||
6
added_tokens.json
Normal file
6
added_tokens.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"<|im_bot|>": 32003,
|
||||
"<|im_end|>": 32000,
|
||||
"<|im_system|>": 32001,
|
||||
"<|im_user|>": 32002
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "Undi95/Borealis-10.7B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 32000,
|
||||
"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": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.37.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32004
|
||||
}
|
||||
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,
|
||||
"transformers_version": "4.37.0.dev0",
|
||||
"use_cache": false
|
||||
}
|
||||
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:da17b9786e03ec37aa6f9e71ed3ffc12bee285a070742a963d522e98bb92a904
|
||||
size 4943216569
|
||||
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 sha256:9b72732ccd60d84de865b2eb35a047f01681ffa564b7a9fce93425af6346c86f
|
||||
size 4999842785
|
||||
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:bbf7da761c08b8de478f7a4f2aca7b8486b5021cb0fff759dc48dd979b5231e4
|
||||
size 4915938275
|
||||
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 sha256:55db0081508454aaff8e8b4b882268e0a88d51b73ed0289a51b2b3811e854b9e
|
||||
size 4915938275
|
||||
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 sha256:1834d664228450085777f2add4cd33e5091922533f6225da8f94f1e2723b9920
|
||||
size 1688324495
|
||||
442
pytorch_model.bin.index.json
Normal file
442
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,442 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 21463113728
|
||||
},
|
||||
"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-00001-of-00005.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-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-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-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-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-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-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-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-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-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-00003-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-00003-of-00005.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-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-00003-of-00005.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.39.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.40.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00005-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-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-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-00001-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-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.norm.weight": "pytorch_model-00005-of-00005.bin"
|
||||
}
|
||||
}
|
||||
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": "<|im_end|>",
|
||||
"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
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
76
tokenizer_config.json
Normal file
76
tokenizer_config.json
Normal file
@@ -0,0 +1,76 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"32000": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|im_system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32002": {
|
||||
"content": "<|im_user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32003": {
|
||||
"content": "<|im_bot|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"trust_remote_code": false,
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user