初始化项目，由ModelHub XC社区提供模型
Model: Uppaal/gpt-j-ProFS-toxicity Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
ProFS[[:space:]]Method.png filter=lfs diff=lfs merge=lfs -text
|
||||
3
ProFS Method.png
Normal file
3
ProFS Method.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:42fc4a5869b956315749c56714df0dbe687ec08ec29ed83ab5f977dfa4556fe3
|
||||
size 111388
|
||||
175
README.md
Normal file
175
README.md
Normal file
@@ -0,0 +1,175 @@
|
||||
---
|
||||
library_name: transformers
|
||||
tags:
|
||||
- generation
|
||||
- safety
|
||||
- model-editing
|
||||
- editing
|
||||
- activation-steering
|
||||
- activation-editing
|
||||
- dpo
|
||||
- rlhf
|
||||
- profs
|
||||
- detox
|
||||
- toxicity
|
||||
- iclr
|
||||
- iclr2025
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- EleutherAI/gpt-j-6b
|
||||
---
|
||||
|
||||
<p align="center">
|
||||
<a href="https://arxiv.org/abs/2405.13967">
|
||||
<img src="https://img.shields.io/badge/arXiv-2405.13967-B31B1B?logo=arxiv&logoColor=white" alt="arXiv">
|
||||
</a>
|
||||
<a href="https://uppaal.github.io/projects/profs/profs.html">
|
||||
<img src="https://img.shields.io/badge/Project_Webpage-1DA1F2?logo=google-chrome&logoColor=white&color=0A4D8C" alt="Project Webpage">
|
||||
</a>
|
||||
<a href="https://github.com/Uppaal/detox-edit">
|
||||
<img src="https://img.shields.io/badge/Code-F1C232?logo=github&logoColor=white&color=black" alt="Checkpoints">
|
||||
</a>
|
||||
</p>
|
||||
|
||||
|
||||
# ProFS Editing for Safety
|
||||
|
||||
This model is an edited version of [`EleutherAI/gpt-j-6b`](https://huggingface.co/EleutherAI/gpt-j-6b).
|
||||
Editing is applied through ProFS, to reduce toxicity.
|
||||
|
||||
ProFS (Projection Filter for Subspaces) is a tuning-free alignment method that removes undesired behaviors by identifying and projecting out harmful subspaces in model weights.
|
||||
The model accompanies the paper [Model Editing as a Robust and Denoised Variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967)
|
||||
published at ICLR 2025 (previously released under the preprint title “DeTox: Toxic Subspace Projection for Model Editing”; both refer to the same work).
|
||||
|
||||
**Key Features:**
|
||||
|
||||
- Training-free & plug-and-play: edits weights directly, no gradient steps or architectural changes needed.
|
||||
- Data-efficient: achieves strong alignment effects using only hundreds (not thousands) of preference pairs.
|
||||
- Label-robust: maintains performance even under substantial label noise, since projection directions remain stable.
|
||||
- Fast & lightweight: produces an edited model that runs at the same inference speed as the base model.
|
||||
- Theoretically grounded: shown to be a denoised, single-step approximation of Direct Preference Optimization (DPO)—bridging editing-based and tuning-based alignment.
|
||||
|
||||
<div align="center">
|
||||
<img src="ProFS Method.png" width="950">
|
||||
<i><b>Figure.</b> Schematic of ProFS (previously called DeTox). Toxic directions (in red) are projected out of the model’s MLP-value matrices, leaving other representational directions intact. </i>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
- **Model type:** Edited Causal Language Model (LLM)
|
||||
- **Base model:** [`EleutherAI/gpt-j-6b`](https://huggingface.co/EleutherAI/gpt-j-6b)
|
||||
- **Language(s) (NLP):** English
|
||||
- **License:** MIT
|
||||
- **Repository:** [GitHub](https://github.com/Uppaal/detox-edit)
|
||||
- **Paper:** [Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967)
|
||||
|
||||
## Uses
|
||||
|
||||
### Direct Use
|
||||
ProFS-edited GPT-2 can be used for:
|
||||
- Safe text generation and alignment research
|
||||
- Studying lightweight alignment via model editing rather than fine-tuning
|
||||
- Interpretability studies of activation subspaces and toxicity directions
|
||||
|
||||
### Downstream Use
|
||||
ProFS serves as a reproducible starting point for work on:
|
||||
- Safety alignment without gradient updates
|
||||
- Robustness to label noise and limited data regimes
|
||||
- Educational demonstrations of representation-level interventions
|
||||
|
||||
### Out-of-Scope Use
|
||||
Not a fully aligned conversational model.
|
||||
Not evaluated for fairness or demographic bias beyond toxicity.
|
||||
|
||||
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
```
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
model_id = "Uppaal/gpt-j-ProFS-toxicity"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id)
|
||||
|
||||
prompt = "The internet has changed the way people communicate by"
|
||||
out = model.generate(**tokenizer(prompt, return_tensors="pt"), max_new_tokens=20)
|
||||
print(tokenizer.decode(out[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
|
||||
|
||||
## Training (Editing) Details
|
||||
|
||||
### Data
|
||||
We use the pairwise toxicity preference dataset introduced by [Lee et al. (2024)](https://arxiv.org/abs/2401.01967).
|
||||
|
||||
- Non-toxic sequences: sampled from WikiText-2.
|
||||
- Toxic counterparts: generated using the Plug-and-Play Language Model (PPLM) method to inject toxic content.
|
||||
- Data format: (toxic, non-toxic) sentence pairs.
|
||||
- Sample size: 500 pairs for ProFS editing (compared to 2,000 pairs used for DPO fine-tuning).
|
||||
|
||||
### Preprocessing
|
||||
|
||||
No preprocessing or filtering was applied beyond tokenization by the base model tokenizer.
|
||||
|
||||
### Editing Hyperparameters
|
||||
|
||||
- Top-k singular vectors:
|
||||
- GPT-2: k = 2
|
||||
- Mistral, Mistral-SFT, OPT, GPT-J: k = 10
|
||||
- Selected via ScreeNot and validated with cross-validation.
|
||||
- Edited layers:
|
||||
- GPT-2 / GPT-J: layers 11–24
|
||||
- Mistral, Mistral-SFT, OPT: layers 15–L
|
||||
- Projection step: edit applied once to the MLP-Value matrices only.
|
||||
- Centering: mean vector of non-toxic embeddings removed before SVD to preserve syntactic knowledge.
|
||||
|
||||
|
||||
|
||||
## Evaluation
|
||||
|
||||
### Metrics and Testing Data
|
||||
|
||||
- Perplexity (fluency): evaluated on the WikiText-2 dev split.
|
||||
- Toxicity: measured on the [Real Toxicity Prompts](https://huggingface.co/datasets/allenai/real-toxicity-prompts) challenge subset. Scored using [Detoxify](https://github.com/unitaryai/detoxify). Lower Detoxify score = lower toxicity.
|
||||
- Capability (for larger models): zero-shot accuracy across 7 EleutherAI LM Harness tasks: BoolQ, RTE, HellaSwag, WinoGrande, ARC-Easy, ARC-Challenge, and OpenBookQA.
|
||||
|
||||
### Results
|
||||
| **Model** | **Method** | **Toxicity ↓** | **Perplexity ↓** | **Capability ↑** |
|
||||
|:-----------|:------------|:---------------|:-----------------|:-----------------|
|
||||
| **GPT-2 Medium** | Original | 48.00 (0.00) | 29.70 (0.00) | – |
|
||||
| | DPO | 36.36 (0.58) | 29.86 (0.22) | – |
|
||||
| | **ProFS** | **26.83 (0.89)** | 32.50 (0.28) | – |
|
||||
| **Mistral 7B** | Original | 42.45 (0.00) | 7.49 (0.00) | 64.23 |
|
||||
| | DPO | 36.42 (0.62) | 7.52 (0.26) | 65.32 |
|
||||
| | **ProFS** | **30.40 (0.71)** | 7.99 (0.21) | 63.59 |
|
||||
| **Mistral-SFT 7B** | Original | 33.45 (0.00) | 8.22 (0.00) | 63.59 |
|
||||
| | DPO | 23.96 (0.50) | 8.38 (0.34) | 63.66 |
|
||||
| | **ProFS** | **26.03 (1.25)** | 8.83 (0.57) | 63.23 |
|
||||
| **OPT 6.7B** | Original | 46.47 (0.00) | 14.67 (0.00) | 51.57 |
|
||||
| | DPO | 45.31 (0.74) | 14.37 (0.61) | 51.55 |
|
||||
| | **ProFS** | **43.49 (1.38)** | 13.83 (0.46) | 51.80 |
|
||||
| **GPT-J 6B** | Original | 45.31 (0.00) | 13.24 (0.00) | 51.92 |
|
||||
| | DPO | 43.67 (1.11) | 13.96 (0.53) | 52.46 |
|
||||
| | **ProFS** | **37.36 (2.28)** | 14.53 (0.30) | 52.48 |
|
||||
## Citation
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
@inproceedings{uppaalmodel,
|
||||
title={Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity},
|
||||
author={Uppaal, Rheeya and Dey, Apratim and He, Yiting and Zhong, Yiqiao and Hu, Junjie},
|
||||
booktitle={The Thirteenth International Conference on Learning Representations}
|
||||
}
|
||||
|
||||
**APA:**
|
||||
|
||||
Uppaal, R., Dey, A., He, Y., Zhong, Y., & Hu, J. Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity. In The Thirteenth International Conference on Learning Representations.
|
||||
145
added_tokens.json
Normal file
145
added_tokens.json
Normal file
@@ -0,0 +1,145 @@
|
||||
{
|
||||
"<|extratoken_100|>": 50356,
|
||||
"<|extratoken_101|>": 50357,
|
||||
"<|extratoken_102|>": 50358,
|
||||
"<|extratoken_103|>": 50359,
|
||||
"<|extratoken_104|>": 50360,
|
||||
"<|extratoken_105|>": 50361,
|
||||
"<|extratoken_106|>": 50362,
|
||||
"<|extratoken_107|>": 50363,
|
||||
"<|extratoken_108|>": 50364,
|
||||
"<|extratoken_109|>": 50365,
|
||||
"<|extratoken_10|>": 50266,
|
||||
"<|extratoken_110|>": 50366,
|
||||
"<|extratoken_111|>": 50367,
|
||||
"<|extratoken_112|>": 50368,
|
||||
"<|extratoken_113|>": 50369,
|
||||
"<|extratoken_114|>": 50370,
|
||||
"<|extratoken_115|>": 50371,
|
||||
"<|extratoken_116|>": 50372,
|
||||
"<|extratoken_117|>": 50373,
|
||||
"<|extratoken_118|>": 50374,
|
||||
"<|extratoken_119|>": 50375,
|
||||
"<|extratoken_11|>": 50267,
|
||||
"<|extratoken_120|>": 50376,
|
||||
"<|extratoken_121|>": 50377,
|
||||
"<|extratoken_122|>": 50378,
|
||||
"<|extratoken_123|>": 50379,
|
||||
"<|extratoken_124|>": 50380,
|
||||
"<|extratoken_125|>": 50381,
|
||||
"<|extratoken_126|>": 50382,
|
||||
"<|extratoken_127|>": 50383,
|
||||
"<|extratoken_128|>": 50384,
|
||||
"<|extratoken_129|>": 50385,
|
||||
"<|extratoken_12|>": 50268,
|
||||
"<|extratoken_130|>": 50386,
|
||||
"<|extratoken_131|>": 50387,
|
||||
"<|extratoken_132|>": 50388,
|
||||
"<|extratoken_133|>": 50389,
|
||||
"<|extratoken_134|>": 50390,
|
||||
"<|extratoken_135|>": 50391,
|
||||
"<|extratoken_136|>": 50392,
|
||||
"<|extratoken_137|>": 50393,
|
||||
"<|extratoken_138|>": 50394,
|
||||
"<|extratoken_139|>": 50395,
|
||||
"<|extratoken_13|>": 50269,
|
||||
"<|extratoken_140|>": 50396,
|
||||
"<|extratoken_141|>": 50397,
|
||||
"<|extratoken_142|>": 50398,
|
||||
"<|extratoken_143|>": 50399,
|
||||
"<|extratoken_14|>": 50270,
|
||||
"<|extratoken_15|>": 50271,
|
||||
"<|extratoken_16|>": 50272,
|
||||
"<|extratoken_17|>": 50273,
|
||||
"<|extratoken_18|>": 50274,
|
||||
"<|extratoken_19|>": 50275,
|
||||
"<|extratoken_1|>": 50257,
|
||||
"<|extratoken_20|>": 50276,
|
||||
"<|extratoken_21|>": 50277,
|
||||
"<|extratoken_22|>": 50278,
|
||||
"<|extratoken_23|>": 50279,
|
||||
"<|extratoken_24|>": 50280,
|
||||
"<|extratoken_25|>": 50281,
|
||||
"<|extratoken_26|>": 50282,
|
||||
"<|extratoken_27|>": 50283,
|
||||
"<|extratoken_28|>": 50284,
|
||||
"<|extratoken_29|>": 50285,
|
||||
"<|extratoken_2|>": 50258,
|
||||
"<|extratoken_30|>": 50286,
|
||||
"<|extratoken_31|>": 50287,
|
||||
"<|extratoken_32|>": 50288,
|
||||
"<|extratoken_33|>": 50289,
|
||||
"<|extratoken_34|>": 50290,
|
||||
"<|extratoken_35|>": 50291,
|
||||
"<|extratoken_36|>": 50292,
|
||||
"<|extratoken_37|>": 50293,
|
||||
"<|extratoken_38|>": 50294,
|
||||
"<|extratoken_39|>": 50295,
|
||||
"<|extratoken_3|>": 50259,
|
||||
"<|extratoken_40|>": 50296,
|
||||
"<|extratoken_41|>": 50297,
|
||||
"<|extratoken_42|>": 50298,
|
||||
"<|extratoken_43|>": 50299,
|
||||
"<|extratoken_44|>": 50300,
|
||||
"<|extratoken_45|>": 50301,
|
||||
"<|extratoken_46|>": 50302,
|
||||
"<|extratoken_47|>": 50303,
|
||||
"<|extratoken_48|>": 50304,
|
||||
"<|extratoken_49|>": 50305,
|
||||
"<|extratoken_4|>": 50260,
|
||||
"<|extratoken_50|>": 50306,
|
||||
"<|extratoken_51|>": 50307,
|
||||
"<|extratoken_52|>": 50308,
|
||||
"<|extratoken_53|>": 50309,
|
||||
"<|extratoken_54|>": 50310,
|
||||
"<|extratoken_55|>": 50311,
|
||||
"<|extratoken_56|>": 50312,
|
||||
"<|extratoken_57|>": 50313,
|
||||
"<|extratoken_58|>": 50314,
|
||||
"<|extratoken_59|>": 50315,
|
||||
"<|extratoken_5|>": 50261,
|
||||
"<|extratoken_60|>": 50316,
|
||||
"<|extratoken_61|>": 50317,
|
||||
"<|extratoken_62|>": 50318,
|
||||
"<|extratoken_63|>": 50319,
|
||||
"<|extratoken_64|>": 50320,
|
||||
"<|extratoken_65|>": 50321,
|
||||
"<|extratoken_66|>": 50322,
|
||||
"<|extratoken_67|>": 50323,
|
||||
"<|extratoken_68|>": 50324,
|
||||
"<|extratoken_69|>": 50325,
|
||||
"<|extratoken_6|>": 50262,
|
||||
"<|extratoken_70|>": 50326,
|
||||
"<|extratoken_71|>": 50327,
|
||||
"<|extratoken_72|>": 50328,
|
||||
"<|extratoken_73|>": 50329,
|
||||
"<|extratoken_74|>": 50330,
|
||||
"<|extratoken_75|>": 50331,
|
||||
"<|extratoken_76|>": 50332,
|
||||
"<|extratoken_77|>": 50333,
|
||||
"<|extratoken_78|>": 50334,
|
||||
"<|extratoken_79|>": 50335,
|
||||
"<|extratoken_7|>": 50263,
|
||||
"<|extratoken_80|>": 50336,
|
||||
"<|extratoken_81|>": 50337,
|
||||
"<|extratoken_82|>": 50338,
|
||||
"<|extratoken_83|>": 50339,
|
||||
"<|extratoken_84|>": 50340,
|
||||
"<|extratoken_85|>": 50341,
|
||||
"<|extratoken_86|>": 50342,
|
||||
"<|extratoken_87|>": 50343,
|
||||
"<|extratoken_88|>": 50344,
|
||||
"<|extratoken_89|>": 50345,
|
||||
"<|extratoken_8|>": 50264,
|
||||
"<|extratoken_90|>": 50346,
|
||||
"<|extratoken_91|>": 50347,
|
||||
"<|extratoken_92|>": 50348,
|
||||
"<|extratoken_93|>": 50349,
|
||||
"<|extratoken_94|>": 50350,
|
||||
"<|extratoken_95|>": 50351,
|
||||
"<|extratoken_96|>": 50352,
|
||||
"<|extratoken_97|>": 50353,
|
||||
"<|extratoken_98|>": 50354,
|
||||
"<|extratoken_99|>": 50355,
|
||||
"<|extratoken_9|>": 50265
|
||||
}
|
||||
41
config.json
Normal file
41
config.json
Normal file
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPTJForCausalLM"
|
||||
],
|
||||
"attn_pdrop": 0.0,
|
||||
"bos_token_id": 50256,
|
||||
"dtype": "float16",
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 50256,
|
||||
"gradient_checkpointing": false,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gptj",
|
||||
"n_embd": 4096,
|
||||
"n_head": 16,
|
||||
"n_inner": null,
|
||||
"n_layer": 28,
|
||||
"n_positions": 2048,
|
||||
"resid_pdrop": 0.0,
|
||||
"rotary": true,
|
||||
"rotary_dim": 64,
|
||||
"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,
|
||||
"temperature": 1.0
|
||||
}
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50400
|
||||
}
|
||||
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": "4.57.1"
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2518d0fdd3537dfba1fc40a9038a0c9a4e4381989741ab3a566ec544f722fe4d
|
||||
size 4976939328
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:175502284af3f318795d249d16a118c4e0b89b32e38652b3861d29919d060160
|
||||
size 4966790096
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:221c28664694e91c1eebe6256c7337c0f572cda4a5e8e56df65116177d4dbdc6
|
||||
size 2158066960
|
||||
293
model.safetensors.index.json
Normal file
293
model.safetensors.index.json
Normal file
@@ -0,0 +1,293 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 6050882784,
|
||||
"total_size": 12101765568
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.bias": "model-00003-of-00003.safetensors",
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.0.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.2.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.20.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.3.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.ln_f.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.ln_f.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.wte.weight": "model-00001-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
251605
tokenizer.json
Normal file
251605
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
1167
tokenizer_config.json
Normal file
1167
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
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