初始化项目，由ModelHub XC社区提供模型
Model: ahmiershadowman/GPT-Para 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
|
||||
29
README.md
Normal file
29
README.md
Normal file
@@ -0,0 +1,29 @@
|
||||
---
|
||||
language: en
|
||||
tags:
|
||||
- neuroforge
|
||||
- text-generation
|
||||
- causal-lm
|
||||
---
|
||||
|
||||
# NeuroForge Exported Model
|
||||
|
||||
This model was exported using NeuroForge v1.1.
|
||||
|
||||
## Export Information
|
||||
|
||||
- **Export Date**: 2026-03-30T14:29:40.236297
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("ahmiershadowman/GPT-Para")
|
||||
tokenizer = AutoTokenizer.from_pretrained("ahmiershadowman/GPT-Para")
|
||||
|
||||
# Generate text
|
||||
inputs = tokenizer("Your prompt here", return_tensors="pt")
|
||||
outputs = model.generate(**inputs)
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
```
|
||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"dtype": "float32",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 1600,
|
||||
"n_head": 25,
|
||||
"n_inner": null,
|
||||
"n_layer": 48,
|
||||
"n_positions": 1024,
|
||||
"output_past": true,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"task_specific_params": {
|
||||
"text-generation": {
|
||||
"do_sample": true,
|
||||
"max_length": 50
|
||||
}
|
||||
},
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50257
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:db5aea82f4886987de92f76286b5fb3f1f370ac4559e8ba16c53892aebaed870
|
||||
size 4959881464
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:87a30d09e0eab8dedbf5c03e51ac5bebc412e7594af5ab27eeda645bc3b2f627
|
||||
size 1270624096
|
||||
588
model.safetensors.index.json
Normal file
588
model.safetensors.index.json
Normal file
@@ -0,0 +1,588 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 1557611200,
|
||||
"total_size": 6230444800
|
||||
},
|
||||
"weight_map": {
|
||||
"transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.24.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.25.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.26.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.27.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.28.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.29.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.31.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.32.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.33.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.34.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.35.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.36.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.37.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.38.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.40.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.40.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.41.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.42.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.43.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.44.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.45.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.46.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.ln_1.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.ln_1.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.ln_2.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.ln_2.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.47.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.ln_f.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.ln_f.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.wpe.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.wte.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0893b8ad2535afd0ff7483ee17758155950c7f57322ecfc80d6f7fe046f1d560
|
||||
size 425785
|
||||
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
250306
tokenizer.json
Normal file
250306
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
21
tokenizer_config.json
Normal file
21
tokenizer_config.json
Normal file
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"50256": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user