初始化项目，由ModelHub XC社区提供模型
Model: LCoder/llama3.1-8B-Chinese-Instruct-DPO Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
53
README.md
Executable file
53
README.md
Executable file
@@ -0,0 +1,53 @@
|
||||
# Llama-3.1-8B 中文 DPO 模型
|
||||
|
||||
这是最新的 Llama-3.1-8B 模型的中文 DPO（Direct Preference Optimization）权重。该模型使用了[shareAI/DPO-zh-en-emoji 数据集](https://huggingface.co/datasets/shareAI/DPO-zh-en-emoji)进行训练，并在单机 8 卡 Ascend910B3 机器上完成训练。
|
||||
|
||||
## 模型概述
|
||||
|
||||
Llama-3.1-8B 中文 DPO 模型是基于 Llama-3.1-8B 进行微调的模型，专门针对中文环境进行了优化。通过 Direct Preference Optimization 技术，模型能够更好地理解和生成符合用户偏好的中文文本。
|
||||
|
||||
## 数据集
|
||||
|
||||
训练数据集使用了 [shareAI/DPO-zh-en-emoji](https://huggingface.co/datasets/shareAI/DPO-zh-en-emoji)。该数据集包含丰富的中英文以及表情符号混合数据，能够帮助模型在多样化的文本环境中进行学习。
|
||||
|
||||
## 训练配置
|
||||
|
||||
- 训练设备：单机 8 卡 Ascend910B3
|
||||
- 训练时长：1 小时
|
||||
|
||||
## 模型下载与使用
|
||||
|
||||
模型权重已发布在ModelScope 模型库中，您可以通过以下链接下载和使用：
|
||||
|
||||
### 使用示例
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
# 加载模型和分词器
|
||||
model_name = "xxx/llama-3.1-8b-dpo-zh" # 请替换为实际模型名称
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name)
|
||||
|
||||
# 编码输入文本
|
||||
input_text = "请输入您的中文文本"
|
||||
inputs = tokenizer(input_text, return_tensors="pt")
|
||||
|
||||
# 生成文本
|
||||
outputs = model.generate(**inputs, max_length=50)
|
||||
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
|
||||
print(generated_text)
|
||||
```
|
||||
|
||||
## 贡献
|
||||
|
||||
欢迎大家对本项目提出建议和贡献。如果您在使用过程中遇到任何问题，或者有改进建议，请通过以下方式联系我们：
|
||||
- 联系邮箱：18792195587@163.com
|
||||
|
||||
---
|
||||
|
||||
感谢您的关注和支持！希望该模型能为您的中文自然语言处理任务带来帮助。如果在使用模型过程中出现错误，提请issue。
|
||||
|
||||
---
|
||||
|
||||
请注意根据实际情况填写具体的数值和链接。
|
||||
39
config.json
Executable file
39
config.json
Executable file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"_name_or_path": "/home/data/Models/Meta-Llama-3.1-8B-Instruct",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.43.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
1
configuration.json
Executable file
1
configuration.json
Executable file
@@ -0,0 +1 @@
|
||||
{"task":"text-generation"}
|
||||
12
generation_config.json
Executable file
12
generation_config.json
Executable file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.43.1"
|
||||
}
|
||||
3
model-00001-of-00009.safetensors
Executable file
3
model-00001-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dc91817c93bb2ff97aa12880607842703b8d3b2e7bc0261b97702decd5a1c4e9
|
||||
size 1973455376
|
||||
3
model-00002-of-00009.safetensors
Executable file
3
model-00002-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:130c2b49bb1eedc818e9af6225c2aaa5ab2726a411224ae1e129c9b206bcc058
|
||||
size 1895895336
|
||||
3
model-00003-of-00009.safetensors
Executable file
3
model-00003-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:124a6550be664576ebd4bb271c0ce5c51d347b40cc3cec348c3ab0927933801e
|
||||
size 1979798040
|
||||
3
model-00004-of-00009.safetensors
Executable file
3
model-00004-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4f311dc51463cccf980582f540a8147011611b59fb6915ad9c876bdb1eef9a08
|
||||
size 1946227368
|
||||
3
model-00005-of-00009.safetensors
Executable file
3
model-00005-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bb243def5725821d1e09f6fdcb95d73f162167de6d4eb158ad6f0b2a9af0729e
|
||||
size 1979798064
|
||||
3
model-00006-of-00009.safetensors
Executable file
3
model-00006-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cce7392d334807b590afca53810da5483f2db975880faccd8fe0a174c62ef40a
|
||||
size 1946227368
|
||||
3
model-00007-of-00009.safetensors
Executable file
3
model-00007-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92c2140aebd12f3c995dabc093092ab019353cab7c10c1f7a0bcae4c217c34ce
|
||||
size 1979798064
|
||||
3
model-00008-of-00009.safetensors
Executable file
3
model-00008-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0f8c3aea32231420eb7975a8e6210e8b279c838da2338a74964701e49be29f51
|
||||
size 1308683424
|
||||
3
model-00009-of-00009.safetensors
Executable file
3
model-00009-of-00009.safetensors
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9bb7a5c6402e8a0f3838d4d45f59e5f3fff4f0f6375ef5c71b2b4604cccded4c
|
||||
size 1050673280
|
||||
298
model.safetensors.index.json
Executable file
298
model.safetensors.index.json
Executable file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00009-of-00009.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00009.safetensors"
|
||||
}
|
||||
}
|
||||
17
special_tokens_map.json
Executable file
17
special_tokens_map.json
Executable file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|eot_id|>"
|
||||
}
|
||||
410504
tokenizer.json
Executable file
410504
tokenizer.json
Executable file
File diff suppressed because it is too large
Load Diff
2065
tokenizer_config.json
Executable file
2065
tokenizer_config.json
Executable file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user