初始化项目，由ModelHub XC社区提供模型
Model: viethq188/LeoScorpius-7B-Chat-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
|
||||
26
README.md
Normal file
26
README.md
Normal file
@@ -0,0 +1,26 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
# Updated: 14th December 2023
|
||||
We are ranked 3th on the overall leaderboard and 1st in the 7B [Hugging Face Leaderboard!](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)! 🔥🔥🔥
|
||||
|
||||
|
||||
|
||||
Finetune DPO viethq188/LeoScorpius-7B with [Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar) dataset
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
You can use alpaca template.
|
||||
```
|
||||
template_format = """{system}
|
||||
### Instruction:
|
||||
{prompt}
|
||||
|
||||
### Response:
|
||||
"""
|
||||
```
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "/raid/viethq5/projects/mergekit/best_model_now",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.34.1",
|
||||
"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": "4.34.1"
|
||||
}
|
||||
3
pytorch_model-00001-of-00015.bin
Normal file
3
pytorch_model-00001-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bc34a543385e56be9b2c5c43cb11fc69fe61e729113d5c94e344871ac8415c03
|
||||
size 899700344
|
||||
3
pytorch_model-00002-of-00015.bin
Normal file
3
pytorch_model-00002-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8391f204891b57ba4ba16fe13eb2da69558d893646cece6f9ed216a3519d80c
|
||||
size 989895552
|
||||
3
pytorch_model-00003-of-00015.bin
Normal file
3
pytorch_model-00003-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e9cc23bf5d12dd66df82fc74eaf3e04d67164714a122739de288306d73c4640c
|
||||
size 989912548
|
||||
3
pytorch_model-00004-of-00015.bin
Normal file
3
pytorch_model-00004-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cbaa571fdc8f115cf46728e634860fb34b4769537b8d89b623e5ad2e2057403e
|
||||
size 956342070
|
||||
3
pytorch_model-00005-of-00015.bin
Normal file
3
pytorch_model-00005-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44729dbe72e7dc1a41d79014f1fb56c2e59aaba46bd17e376a50b129830be0a2
|
||||
size 989895552
|
||||
3
pytorch_model-00006-of-00015.bin
Normal file
3
pytorch_model-00006-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b313b789cbb9cfc843610599a962c28d5bd74f61420aa7b74c2b721809b4a336
|
||||
size 989895552
|
||||
3
pytorch_model-00007-of-00015.bin
Normal file
3
pytorch_model-00007-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cf1b4d33f2fb6d1f0dc143781cd9a968e3ecbf038dad0db78eb3c2a045ffa557
|
||||
size 989912548
|
||||
3
pytorch_model-00008-of-00015.bin
Normal file
3
pytorch_model-00008-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bfe503932dbea3c504b5fb7ed90c48f563a7b3c39d5ef4a20c87d705f6c674bd
|
||||
size 956342070
|
||||
3
pytorch_model-00009-of-00015.bin
Normal file
3
pytorch_model-00009-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:18bc1a955e1f5f939e88ca4c92d936e1b9a402afe83fdac3aa7fb3c7294f58fc
|
||||
size 989895552
|
||||
3
pytorch_model-00010-of-00015.bin
Normal file
3
pytorch_model-00010-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:718c0e9cb111d86097542447cbce699dbd28fb0ec19b9d9abea1a0182158c69e
|
||||
size 989895552
|
||||
3
pytorch_model-00011-of-00015.bin
Normal file
3
pytorch_model-00011-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a0641a1a910de5b524047c00e9b1238cb4ad7c4453e57494748b6f77f416188d
|
||||
size 989912548
|
||||
3
pytorch_model-00012-of-00015.bin
Normal file
3
pytorch_model-00012-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fc39a1b9f6f699d29572b37377da6bb64410b584a2b8df72e5938b93eb6af7a9
|
||||
size 956342070
|
||||
3
pytorch_model-00013-of-00015.bin
Normal file
3
pytorch_model-00013-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3f9dd1b766fe56aed02a5ba92bd4854bd8dcdd3c9798cc135fc5fc90433cec71
|
||||
size 989895552
|
||||
3
pytorch_model-00014-of-00015.bin
Normal file
3
pytorch_model-00014-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:36ae37a34e5f1deb05c043c2e3d693ba3f21dc5fabea5ba68b91eeb76abdecf9
|
||||
size 989895552
|
||||
3
pytorch_model-00015-of-00015.bin
Normal file
3
pytorch_model-00015-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1c100b8de5b6eb7f0547067b2715de24c2783caf4ae851a155a0fe929e8fe750
|
||||
size 815838502
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483464192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.norm.weight": "pytorch_model-00015-of-00015.bin"
|
||||
}
|
||||
}
|
||||
28
special_tokens_map.json
Normal file
28
special_tokens_map.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"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
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
46
tokenizer_config.json
Normal file
46
tokenizer_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user