Upload tokenizer
This commit is contained in:
ai-modelscope
36
.gitattributes
vendored
36
.gitattributes
vendored
@@ -1,47 +1,41 @@
|
|||||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
*.arrow 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
|
||||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.bz2 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
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
*.lfs.* 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
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
*.msgpack 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
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pb 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
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
*.rar 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
|
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
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tgz 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
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zip 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
|
|
||||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|||||||
240
README.md
240
README.md
@@ -1,47 +1,201 @@
|
|||||||
---
|
---
|
||||||
license: Apache License 2.0
|
library_name: transformers
|
||||||
|
tags: []
|
||||||
#model-type:
|
|
||||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
|
||||||
#- gpt
|
|
||||||
|
|
||||||
#domain:
|
|
||||||
##如 nlp、cv、audio、multi-modal
|
|
||||||
#- nlp
|
|
||||||
|
|
||||||
#language:
|
|
||||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
|
||||||
#- cn
|
|
||||||
|
|
||||||
#metrics:
|
|
||||||
##如 CIDEr、Blue、ROUGE 等
|
|
||||||
#- CIDEr
|
|
||||||
|
|
||||||
#tags:
|
|
||||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
|
||||||
#- pretrained
|
|
||||||
|
|
||||||
#tools:
|
|
||||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
|
||||||
#- vllm
|
|
||||||
---
|
---
|
||||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
|
||||||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
|
||||||
|
|
||||||
SDK下载
|
# Model Card for Model ID
|
||||||
```bash
|
|
||||||
#安装ModelScope
|
<!-- Provide a quick summary of what the model is/does. -->
|
||||||
pip install modelscope
|
|
||||||
```
|
|
||||||
```python
|
|
||||||
#SDK模型下载
|
## Model Details
|
||||||
from modelscope import snapshot_download
|
|
||||||
model_dir = snapshot_download('arcee-ai/sec-mistral-7b-instruct-1.6-epoch')
|
### Model Description
|
||||||
```
|
|
||||||
Git下载
|
<!-- Provide a longer summary of what this model is. -->
|
||||||
```
|
|
||||||
#Git模型下载
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
||||||
git clone https://www.modelscope.cn/arcee-ai/sec-mistral-7b-instruct-1.6-epoch.git
|
|
||||||
```
|
- **Developed by:** [More Information Needed]
|
||||||
|
- **Funded by [optional]:** [More Information Needed]
|
||||||
|
- **Shared by [optional]:** [More Information Needed]
|
||||||
|
- **Model type:** [More Information Needed]
|
||||||
|
- **Language(s) (NLP):** [More Information Needed]
|
||||||
|
- **License:** [More Information Needed]
|
||||||
|
- **Finetuned from model [optional]:** [More Information Needed]
|
||||||
|
|
||||||
|
### Model Sources [optional]
|
||||||
|
|
||||||
|
<!-- Provide the basic links for the model. -->
|
||||||
|
|
||||||
|
- **Repository:** [More Information Needed]
|
||||||
|
- **Paper [optional]:** [More Information Needed]
|
||||||
|
- **Demo [optional]:** [More Information Needed]
|
||||||
|
|
||||||
|
## Uses
|
||||||
|
|
||||||
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||||
|
|
||||||
|
### Direct Use
|
||||||
|
|
||||||
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Downstream Use [optional]
|
||||||
|
|
||||||
|
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Out-of-Scope Use
|
||||||
|
|
||||||
|
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Bias, Risks, and Limitations
|
||||||
|
|
||||||
|
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Recommendations
|
||||||
|
|
||||||
|
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||||
|
|
||||||
|
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||||
|
|
||||||
|
## How to Get Started with the Model
|
||||||
|
|
||||||
|
Use the code below to get started with the model.
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Training Details
|
||||||
|
|
||||||
|
### Training Data
|
||||||
|
|
||||||
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Training Procedure
|
||||||
|
|
||||||
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||||
|
|
||||||
|
#### Preprocessing [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
|
||||||
|
#### Training Hyperparameters
|
||||||
|
|
||||||
|
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||||
|
|
||||||
|
#### Speeds, Sizes, Times [optional]
|
||||||
|
|
||||||
|
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Evaluation
|
||||||
|
|
||||||
|
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||||
|
|
||||||
|
### Testing Data, Factors & Metrics
|
||||||
|
|
||||||
|
#### Testing Data
|
||||||
|
|
||||||
|
<!-- This should link to a Dataset Card if possible. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Factors
|
||||||
|
|
||||||
|
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Metrics
|
||||||
|
|
||||||
|
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Results
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Summary
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Model Examination [optional]
|
||||||
|
|
||||||
|
<!-- Relevant interpretability work for the model goes here -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Environmental Impact
|
||||||
|
|
||||||
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||||
|
|
||||||
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||||
|
|
||||||
|
- **Hardware Type:** [More Information Needed]
|
||||||
|
- **Hours used:** [More Information Needed]
|
||||||
|
- **Cloud Provider:** [More Information Needed]
|
||||||
|
- **Compute Region:** [More Information Needed]
|
||||||
|
- **Carbon Emitted:** [More Information Needed]
|
||||||
|
|
||||||
|
## Technical Specifications [optional]
|
||||||
|
|
||||||
|
### Model Architecture and Objective
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Compute Infrastructure
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Hardware
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Software
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Citation [optional]
|
||||||
|
|
||||||
|
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||||
|
|
||||||
|
**BibTeX:**
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
**APA:**
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Glossary [optional]
|
||||||
|
|
||||||
|
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## More Information [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Model Card Authors [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Model Card Contact
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
|
||||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
|
||||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "/Users/gayalshamane/Desktop/checkpoint-1000",
|
||||||
|
"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": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float32",
|
||||||
|
"transformers_version": "4.39.2",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 32000
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
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": "4.39.2"
|
||||||
|
}
|
||||||
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b3d3ffc43c706d6b315b5077cf132dc2b2422aea8dee1afa3017d8bd6c44e082
|
||||||
|
size 4987196936
|
||||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a8a91b3a009233cda1824383d1cb64b33d9a12de0b9b1ceaa9ecb4f4a13fe80a
|
||||||
|
size 4899116440
|
||||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ed817afd310690d375b6733f33ba9508e08e3e5ab7cfe855815cc9fb15e64c12
|
||||||
|
size 4999813120
|
||||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7f90272ac67362fdc696d7177085d4459327dec81a2c19961643f844b066c2c0
|
||||||
|
size 4999813128
|
||||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:349e395930409eed03d0c387dac43f42efcefc5daea1a0cbcd685703ac667cef
|
||||||
|
size 4832007496
|
||||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7ec42db1f80ca9dfe9e4afd970e0f7e7b2a329d03858a7936c4b9cb7e50ec4a2
|
||||||
|
size 4249014896
|
||||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 28966928384
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||||
|
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
43
tokenizer_config.json
Normal file
43
tokenizer_config.json
Normal file
@@ -0,0 +1,43 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"add_eos_token": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"0": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"1": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [],
|
||||||
|
"bos_token": "<s>",
|
||||||
|
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "</s>",
|
||||||
|
"legacy": true,
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"pad_token": null,
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"spaces_between_special_tokens": false,
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"unk_token": "<unk>",
|
||||||
|
"use_default_system_prompt": false
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user