初始化项目，由ModelHub XC社区提供模型
Model: qqggez/deepseek-parlay-6.7b 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
|
||||
72
README.md
Normal file
72
README.md
Normal file
@@ -0,0 +1,72 @@
|
||||
---
|
||||
base_model: deepseek-ai/deepseek-coder-6.7b-base
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- deepseek
|
||||
- code
|
||||
- finetuned
|
||||
- cpp
|
||||
- parallel-computing
|
||||
dtype: float16
|
||||
pipeline_tag: text-generation
|
||||
license: other
|
||||
---
|
||||
|
||||
# Model Card for deepseek-parlay-6.7b
|
||||
|
||||
This model is part of the **ParEVO** framework, introduced in the paper [ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution](https://huggingface.co/papers/2603.02510).
|
||||
|
||||
- **Project Website:** [https://quanquancliu.com/ParEVO/index.html](https://quanquancliu.com/ParEVO/index.html)
|
||||
- **GitHub Repository:** [https://github.com/WildAlg/ParEVO](https://github.com/WildAlg/ParEVO)
|
||||
|
||||
## Model Details
|
||||
- **Base Model:** `deepseek-ai/deepseek-coder-6.7b-base`
|
||||
- **Model Type:** C++ Parallel Code Generation Model
|
||||
- **Language:** C++
|
||||
- **Parameters:** 6.7B
|
||||
|
||||
## Intended Use
|
||||
The model is specifically fine-tuned for generating high-performance parallel algorithms for irregular data structures in C++. It understands and utilizes the composable primitives of the **ParlayLib** parallel data structures library (e.g., `filter`, `pack`, `scan`, `sort`, `reduce`) to output mathematically scalable and safe parallel code.
|
||||
|
||||
## Training Data
|
||||
The model was trained on the **Parlay-Instruct Corpus**, a dataset containing 13,820 verified tasks synthesized via an Evolutionary "Teacher-Student-Critic" pipeline. The training dataset includes:
|
||||
- Ground-truth samples covering ParlayLib's core primitives.
|
||||
- DMOJ "slow-fast" code comparison pairs, constructed to identify optimal performance transformations rather than just functional correctness.
|
||||
- Code validated with execution-based verification against a ground-truth C++ compiler oracle.
|
||||
|
||||
Training data can be found at this Github link: https://github.com/WildAlg/ParEVO
|
||||
|
||||
## Training Procedure
|
||||
- **Algorithm:** Single-stage Supervised Fine-Tuning (SFT)
|
||||
- **Method:** LoRA ($r=8$, $\alpha=16$) targeting the query and value projections
|
||||
- **Learning Rate:** $2\text{e-}4$
|
||||
- **Precision:** FP16
|
||||
- **Hardware:** NVIDIA RTX 5000 Ada
|
||||
|
||||
## License
|
||||
|
||||
The ParEVO framework and datasets use a modular licensing structure to maximize open-source adoption, while the fine-tuned model weights inherit the license of their base model.
|
||||
|
||||
### 1. Model Weights License
|
||||
The fine-tuned **`deepseek-parlay-6.7b`** model weights are a derivative work of `deepseek-ai/deepseek-coder-6.7b-base`. As such, the model weights and inference outputs are governed by the [DeepSeek License](https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL). Users must comply with the original use-case restrictions and terms set by DeepSeek when using this model.
|
||||
|
||||
### 2. Software License (MIT License)
|
||||
All software, scripts, the Evolutionary Coding Agent (ECA), and analysis code located in the [ParEVO repository](https://github.com/WildAlg/ParEVO) are licensed under the MIT License. Copyright (c) 2026 ParEVO Authors.
|
||||
|
||||
### 3. Dataset License (CC BY 4.0)
|
||||
The Parlay-Instruct Corpus, ParEval evaluation trajectories, and DMOJ problem-solution datasets are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
|
||||
|
||||
## Citation
|
||||
|
||||
If you use this model or the ParEVO framework in your research, please cite:
|
||||
|
||||
```bibtex
|
||||
@inproceedings{yang2026parevo,
|
||||
title={ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution},
|
||||
author={Yang, Liu and Nie, Zeyu and Liu, Andrew and Zou, Felix and Altinb{\u{k}}en, Deniz and Yazdanbakhsh, Amir and Liu, Quanquan C.},
|
||||
booktitle={arXiv Preprint},
|
||||
year={2026}
|
||||
}
|
||||
```
|
||||
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 32013,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": 32014,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 16384,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"factor": 4.0,
|
||||
"rope_type": "linear",
|
||||
"type": "linear"
|
||||
},
|
||||
"rope_theta": 100000,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32256
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 32013,
|
||||
"eos_token_id": 32014,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
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:d027585106a3272e1452800545449f6c4b08b241313efbaebb1fe7308ed86feb
|
||||
size 4941082400
|
||||
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 sha256:7c6076628fe8c499c80d8035a8f1c73e2d384ecd2ad1a3049b45b083266db374
|
||||
size 4947390768
|
||||
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:cc9d1120613a8afb6de22a2a14908d92f4347f22764dc9d4435289f2e83710cd
|
||||
size 3592585888
|
||||
299
model.safetensors.index.json
Normal file
299
model.safetensors.index.json
Normal file
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 6740512768,
|
||||
"total_size": 13481025536
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
159358
tokenizer.json
Normal file
159358
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
194
tokenizer_config.json
Normal file
194
tokenizer_config.json
Normal file
@@ -0,0 +1,194 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"32000": {
|
||||
"content": "õ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32001": {
|
||||
"content": "÷",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32002": {
|
||||
"content": "Á",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32003": {
|
||||
"content": "ý",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32004": {
|
||||
"content": "À",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32005": {
|
||||
"content": "ÿ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32006": {
|
||||
"content": "ø",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32007": {
|
||||
"content": "ú",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32008": {
|
||||
"content": "þ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32009": {
|
||||
"content": "ü",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32010": {
|
||||
"content": "ù",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32011": {
|
||||
"content": "ö",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32012": {
|
||||
"content": "û",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32013": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32014": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32015": {
|
||||
"content": "<｜fim▁hole｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32016": {
|
||||
"content": "<｜fim▁begin｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32017": {
|
||||
"content": "<｜fim▁end｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32018": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32019": {
|
||||
"content": "<|User|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32020": {
|
||||
"content": "<|Assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32021": {
|
||||
"content": "<|EOT|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<｜end▁of▁sentence｜>",
|
||||
"extra_special_tokens": {},
|
||||
"legacy": true,
|
||||
"model_max_length": 16384,
|
||||
"pad_token": "<｜end▁of▁sentence｜>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizerFast",
|
||||
"unk_token": null,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user