luffycodes/vicuna-class-shishya-13b-ep3
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: luffycodes/vicuna-class-shishya-13b-ep3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-17 07:22:35 +08:00
commit 03d88efa95
15 changed files with 93930 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

16
README.md Normal file
View File

@@ -0,0 +1,16 @@
---
license: llama2
---
If you use this work, please cite:
CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles
https://arxiv.org/abs/2305.13272
```
@misc{sonkar2023class,
title={CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles},
author={Shashank Sonkar and Lucy Liu and Debshila Basu Mallick and Richard G. Baraniuk},
year={2023},
eprint={2305.13272},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```

5
added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"</s>": 2,
"<s>": 1,
"<unk>": 0
}

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "vicuna-class-shishya-13b-ep3",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_length": 4096,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.34.0",
"use_cache": true,
"vocab_size": 32000
}

8
generation_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"max_length": 4096,
"pad_token_id": 0,
"transformers_version": "4.34.0"
}

3
pytorch_model-00001-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:27d65d3168cf4d387622b4d097631c97df62cb24b245e3719d45fcf1d6514a9c
size 9956539570

3
pytorch_model-00002-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c49f68c1002fb41555502e96436747eb030c6a0ada24b4f238d6602ea4f3225a
size 9940852630

3
pytorch_model-00003-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a54c43fcea087543c6b73fd332c76d9c2728622413831b7445f0cabc0566b1b
size 9940852642

3
pytorch_model-00004-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9645ab32494a48cfd2a5bc2cef04d65b4891a83cb8bd3eed6379520ac5b0c8e6
size 9867410976

3
pytorch_model-00005-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:233836136085f38e86927ca96b318c8d3b3220ecd36b472c571dfacf190ea3b4
size 9867452612

3
pytorch_model-00006-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f334c8edcbf1862726e3162552f966f09568bff1cf53fb9ad30fe29fd3e7cd6b
size 2490476152

370
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,370 @@
{
"metadata": {
"total_size": 52063457280
},
"weight_map": {
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.norm.weight": "pytorch_model-00006-of-00006.bin"
}
}

11
special_tokens_map.json Normal file
View File

@@ -0,0 +1,11 @@
{
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"eos_token": "</s>",
"pad_token": "<unk>",
"unk_token": "<unk>"
}

93391
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

47
tokenizer_config.json Normal file
View File

@@ -0,0 +1,47 @@
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 4096,
"pad_token": "<unk>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}