croissantllm/CroissantCool-v0.2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: croissantllm/CroissantCool-v0.2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-25 00:06:52 +08:00
commit 256e524082
8 changed files with 64979 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

74
README.md Normal file
View File

@@ -0,0 +1,74 @@
---
license: mit
datasets:
- cerebras/SlimPajama-627B
- uonlp/CulturaX
- pg19
- bigcode/starcoderdata
language:
- fr
- en
pipeline_tag: text-generation
tags:
- legal
- code
- text-generation-inference
- art
---
# CroissantCool (190k steps + Cooldown)
This model is part of the CroissantLLM initiative, and corresponds to the checkpoint after 190k steps (2.99 T) tokens and a final Cooldown phase on non-templated instruction data.
It is the strongest "base" model available on various benchmarks.
Compared to croissantllm/CroissantCool-v0.1, the tokenizer is slightly changed to force solo "\n" tokenization.
To play with the final model, we recommend using the Chat version: https://huggingface.co/croissantllm/CroissantLLMChat-v0.1.
## Abstract
We introduce CroissantLLM, a 1.3B language model pretrained on a set of 3T English and French tokens, to bring to the research and industrial community a high-performance, fully open-sourced bilingual model that runs swiftly on consumer-grade local hardware.
To that end, we pioneer the approach of training an intrinsically bilingual model with a 1:1 English-to-French pretraining data ratio, a custom tokenizer, and bilingual finetuning datasets. We release the training dataset, notably containing a French split with manually curated, high-quality, and varied data sources.
To assess performance outside of English, we craft a novel benchmark, FrenchBench, consisting of an array of classification and generation tasks, covering various orthogonal aspects of model performance in the French Language. Additionally, rooted in transparency and to foster further Large Language Model research, we release codebases, and dozens of checkpoints across various model sizes, training data distributions, and training steps, as well as fine-tuned Chat models, and strong translation models. We evaluate our model through the FMTI framework, and validate 81% of the transparency criteria, far beyond the scores of even most open initiatives.
This work enriches the NLP landscape, breaking away from previous English-centric work in order to strengthen our understanding of multilinguality in language models.
## Citation
Our work can be cited as:
```bibtex
@misc{faysse2024croissantllm,
title={CroissantLLM: A Truly Bilingual French-English Language Model},
author={Manuel Faysse and Patrick Fernandes and Nuno M. Guerreiro and António Loison and Duarte M. Alves and Caio Corro and Nicolas Boizard and João Alves and Ricardo Rei and Pedro H. Martins and Antoni Bigata Casademunt and François Yvon and André F. T. Martins and Gautier Viaud and Céline Hudelot and Pierre Colombo},
year={2024},
eprint={2402.00786},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## Usage
This model is a base model, that is, it is not finetuned for Chat function and works best with few-shot prompting strategies. It's cooldown phase however enables it to function quite well without few-shots as well.
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "croissantllm/CroissantCool-v0.2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
inputs = tokenizer("I am so tired I could sleep right now. -> Je suis si fatigué que je pourrais m'endormir maintenant.\nHe is heading to the market. -> Il va au marché.\nWe are running on the beach. ->", return_tensors="pt").to(model.device)
tokens = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.95, top_k=60, temperature=0.5)
print(tokenizer.decode(tokens[0]))
# remove bos token
inputs = tokenizer("Capitales: France -> Paris, Italie -> Rome, Allemagne -> Berlin, Espagne ->", return_tensors="pt", add_special_tokens=True).to(model.device)
tokens = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.95, top_k=60)
print(tokenizer.decode(tokens[0]))
```

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "/mnt/data/nunomg/axolotl/croissantllm-2201-cooldown",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5504,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0.dev0",
"use_cache": false,
"vocab_size": 32000
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.37.0.dev0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ba1d9955cc012d42eb97787a669ef39bd585fda65365ebf3b583ffedb4cbbde
size 2690871976

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

63955
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

848
tokenizer_config.json Normal file
View File

@@ -0,0 +1,848 @@
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<extra_id_0>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<extra_id_1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<extra_id_2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<extra_id_3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<extra_id_4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<extra_id_5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<extra_id_6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<extra_id_7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "<extra_id_8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "<extra_id_9>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "<extra_id_10>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"15": {
"content": "<extra_id_11>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16": {
"content": "<extra_id_12>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17": {
"content": "<extra_id_13>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"18": {
"content": "<extra_id_14>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"19": {
"content": "<extra_id_15>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20": {
"content": "<extra_id_16>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21": {
"content": "<extra_id_17>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"22": {
"content": "<extra_id_18>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"23": {
"content": "<extra_id_19>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"24": {
"content": "<extra_id_20>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"25": {
"content": "<extra_id_21>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"26": {
"content": "<extra_id_22>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"27": {
"content": "<extra_id_23>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"28": {
"content": "<extra_id_24>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"29": {
"content": "<extra_id_25>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30": {
"content": "<extra_id_26>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31": {
"content": "<extra_id_27>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32": {
"content": "<extra_id_28>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"33": {
"content": "<extra_id_29>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"34": {
"content": "<extra_id_30>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"35": {
"content": "<extra_id_31>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"36": {
"content": "<extra_id_32>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"37": {
"content": "<extra_id_33>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"38": {
"content": "<extra_id_34>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"39": {
"content": "<extra_id_35>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"40": {
"content": "<extra_id_36>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"41": {
"content": "<extra_id_37>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"42": {
"content": "<extra_id_38>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"43": {
"content": "<extra_id_39>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"44": {
"content": "<extra_id_40>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"45": {
"content": "<extra_id_41>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"46": {
"content": "<extra_id_42>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"47": {
"content": "<extra_id_43>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"48": {
"content": "<extra_id_44>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49": {
"content": "<extra_id_45>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50": {
"content": "<extra_id_46>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"51": {
"content": "<extra_id_47>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"52": {
"content": "<extra_id_48>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"53": {
"content": "<extra_id_49>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"54": {
"content": "<extra_id_50>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"55": {
"content": "<extra_id_51>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"56": {
"content": "<extra_id_52>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"57": {
"content": "<extra_id_53>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"58": {
"content": "<extra_id_54>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"59": {
"content": "<extra_id_55>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60": {
"content": "<extra_id_56>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"61": {
"content": "<extra_id_57>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"62": {
"content": "<extra_id_58>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"63": {
"content": "<extra_id_59>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64": {
"content": "<extra_id_60>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65": {
"content": "<extra_id_61>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"66": {
"content": "<extra_id_62>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"67": {
"content": "<extra_id_63>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"68": {
"content": "<extra_id_64>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"69": {
"content": "<extra_id_65>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"70": {
"content": "<extra_id_66>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"71": {
"content": "<extra_id_67>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"72": {
"content": "<extra_id_68>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73": {
"content": "<extra_id_69>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"74": {
"content": "<extra_id_70>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75": {
"content": "<extra_id_71>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"76": {
"content": "<extra_id_72>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"77": {
"content": "<extra_id_73>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"78": {
"content": "<extra_id_74>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"79": {
"content": "<extra_id_75>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"80": {
"content": "<extra_id_76>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"81": {
"content": "<extra_id_77>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"82": {
"content": "<extra_id_78>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"83": {
"content": "<extra_id_79>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"84": {
"content": "<extra_id_80>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"85": {
"content": "<extra_id_81>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"86": {
"content": "<extra_id_82>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"87": {
"content": "<extra_id_83>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"88": {
"content": "<extra_id_84>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"89": {
"content": "<extra_id_85>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"90": {
"content": "<extra_id_86>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"91": {
"content": "<extra_id_87>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92": {
"content": "<extra_id_88>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"93": {
"content": "<extra_id_89>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"94": {
"content": "<extra_id_90>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"95": {
"content": "<extra_id_91>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"96": {
"content": "<extra_id_92>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"97": {
"content": "<extra_id_93>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"98": {
"content": "<extra_id_94>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"99": {
"content": "<extra_id_95>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "<extra_id_96>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "<extra_id_97>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "<extra_id_98>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "<extra_id_99>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}