初始化项目，由ModelHub XC社区提供模型
Model: Undi95/MLewd-Chat-v2-13B 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
|
||||
79
README.md
Normal file
79
README.md
Normal file
@@ -0,0 +1,79 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
tags:
|
||||
- not-for-all-audiences
|
||||
- nsfw
|
||||
---
|
||||
|
||||
|
||||
|
||||
THIS MODEL IS MADE FOR LEWD
|
||||
|
||||
SEXUAL, CRUDE AND KINKY CONTENT IN OUTPUT CAN AND WILL HAPPEN. YOU'RE WARNED
|
||||
|
||||
This is an attempt to make an uncensored Llama2-chat that can RP.
|
||||
|
||||
Added the "magic touch" of MythoMax/Huginn/You call it.
|
||||
|
||||
In addition, [LimaRP v3](https://huggingface.co/lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT) was used, is it recommanded to read the documentation.
|
||||
|
||||
This was requested.
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- description start -->
|
||||
## Description
|
||||
|
||||
This repo contains fp16 files of MLewd-Chat-v2-13B, very hot and lewd model based on Llama2-chat.
|
||||
|
||||
<!-- description end -->
|
||||
<!-- description start -->
|
||||
## Models and loras used
|
||||
|
||||
- Undi95/MLewd-L2-13B-Part3 (checkpoint of MLewd without LORA)
|
||||
- posicube/Llama2-chat-AYT-13B
|
||||
- zattio770/120-Days-of-LORA-v2-13B
|
||||
- royallab/Pygmalion-2-13b-SuperCOT
|
||||
- Undi95/MMSoul-13b-lora
|
||||
- The-Face-Of-Goonery/Huginn-13b-FP16
|
||||
- lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
|
||||
|
||||
<!-- description end -->
|
||||
<!-- prompt-template start -->
|
||||
## Prompt template: Alpaca
|
||||
|
||||
```
|
||||
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
||||
|
||||
### Instruction:
|
||||
{prompt}
|
||||
|
||||
### Response:
|
||||
|
||||
```
|
||||
|
||||
## LimaRP v3 usage and suggested settings
|
||||
|
||||
|
||||
|
||||
You can follow these instruction format settings in SillyTavern. Replace tiny with your desired response length:
|
||||
|
||||
|
||||
|
||||
Special thanks to Sushi and Shena ♥ | I love U Kubernetes.
|
||||
|
||||
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__MLewd-Chat-v2-13B)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 52.72 |
|
||||
| ARC (25-shot) | 61.86 |
|
||||
| HellaSwag (10-shot) | 83.81 |
|
||||
| MMLU (5-shot) | 57.0 |
|
||||
| TruthfulQA (0-shot) | 54.51 |
|
||||
| Winogrande (5-shot) | 75.77 |
|
||||
| GSM8K (5-shot) | 10.46 |
|
||||
| DROP (3-shot) | 25.63 |
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "./Undi95_MLewd-L2-Chat-13B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 40,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.33.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.33.2"
|
||||
}
|
||||
3
pytorch_model-00001-of-00013.bin
Normal file
3
pytorch_model-00001-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2d0af899302c7dd28e0be538d98a58a85b6d9073ddba5005312cb9867504e1f4
|
||||
size 2089337041
|
||||
3
pytorch_model-00002-of-00013.bin
Normal file
3
pytorch_model-00002-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0956f46c073597e45787923c5ff4edfd6bd1374ca1b490ecdc23c1fffe33087f
|
||||
size 2044815083
|
||||
3
pytorch_model-00003-of-00013.bin
Normal file
3
pytorch_model-00003-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f6500fedbe104e19adaab5b51674378a7941a74741f5521c5f1d964c0890eaa3
|
||||
size 2060523307
|
||||
3
pytorch_model-00004-of-00013.bin
Normal file
3
pytorch_model-00004-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13618a150745e2ef25c22b123347c7c88fc56b871a9e0f160c0e140685ba91c8
|
||||
size 1955665095
|
||||
3
pytorch_model-00005-of-00013.bin
Normal file
3
pytorch_model-00005-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff7979d1351b84cc3a7137a01f33279629e78dd430b6634143558b5f83dbfa54
|
||||
size 2044794055
|
||||
3
pytorch_model-00006-of-00013.bin
Normal file
3
pytorch_model-00006-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8aefa7b04c3a155d3845fd55668ef566067662bd869b2e87079a3e6b536789e4
|
||||
size 2044794055
|
||||
3
pytorch_model-00007-of-00013.bin
Normal file
3
pytorch_model-00007-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ef1971fcddaa0c02f4ea0de16d35e15d8c14686aeefced839f2d55d622f67416
|
||||
size 2044815147
|
||||
3
pytorch_model-00008-of-00013.bin
Normal file
3
pytorch_model-00008-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:40618ca9629c855caeab78c66978f88e4ea675f474aa16f9066b3ec5d4b93ea1
|
||||
size 2060523307
|
||||
3
pytorch_model-00009-of-00013.bin
Normal file
3
pytorch_model-00009-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b72f1ed37d800f73c99e37f8623b5259a9c2bc7d50aa6e6e6e0ec57f925bde29
|
||||
size 1955665095
|
||||
3
pytorch_model-00010-of-00013.bin
Normal file
3
pytorch_model-00010-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:387157cb22f01a5d631386354ab5cd755202caafcfb5ca2fbbaedf664f03b83d
|
||||
size 2044794055
|
||||
3
pytorch_model-00011-of-00013.bin
Normal file
3
pytorch_model-00011-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ee8282df5788dae1a1173532593ca39c3fafbad1270c23d89f66ec569ba3290
|
||||
size 2044794055
|
||||
3
pytorch_model-00012-of-00013.bin
Normal file
3
pytorch_model-00012-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26455167d13a1409a632fa2df8605425f67cf8327c5c92473d1d5391910ee958
|
||||
size 2044815147
|
||||
3
pytorch_model-00013-of-00013.bin
Normal file
3
pytorch_model-00013-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cf3653e7c68be5e24688540c3679879f35203da7cda11a603584c21dac9de6ce
|
||||
size 1596514999
|
||||
370
pytorch_model.bin.index.json
Normal file
370
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,370 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26031728640
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.norm.weight": "pytorch_model-00013-of-00013.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"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.
34
tokenizer_config.json
Normal file
34
tokenizer_config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user