初始化项目,由ModelHub XC社区提供模型

Model: tiiuae/Falcon-H1-1.5B-Deep-Instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-11-03 20:00:14 +08:00
commit 77b4f6ae33
10 changed files with 334580 additions and 0 deletions

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

143
README.md Normal file
View File

@@ -0,0 +1,143 @@
---
library_name: transformers
tags:
- falcon-h1
license: other
license_name: falcon-llm-license
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
base_model: tiiuae/Falcon-H1-1.5B-Deep-Base
inference: true
---
<img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/falcon_mamba/falcon-h1-logo.png" alt="drawing" width="800"/>
# Table of Contents
0. [TL;DR](#TL;DR)
1. [Model Details](#model-details)
2. [Training Details](#training-details)
3. [Usage](#usage)
4. [Evaluation](#evaluation)
5. [Citation](#citation)
# TL;DR
# Model Details
## Model Description
- **Developed by:** [https://www.tii.ae](https://www.tii.ae)
- **Model type:** Causal decoder-only
- **Architecture:** Hybrid Transformers + Mamba architecture
- **Language(s) (NLP):** English, Multilingual
- **License:** Falcon-LLM License
# Training details
For more details about the training protocol of this model, please refer to the [Falcon-H1 technical blogpost](https://falcon-lm.github.io/blog/falcon-h1/) and [Technical Report](https://arxiv.org/abs/2507.22448).
# Usage
Currently to use this model you can either rely on Hugging Face `transformers`, `vLLM` or `llama.cpp` library.
## Inference
Make sure to install the latest version of `transformers` or `vllm`, eventually install these packages from source:
```bash
pip install git+https://github.com/huggingface/transformers.git
```
For vLLM, make sure to install `vllm>=0.9.0`:
```bash
pip install "vllm>=0.9.0"
```
### 🤗 transformers
Refer to the snippet below to run H1 models using 🤗 transformers:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "tiiuae/Falcon-H1-1B-Base"
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
# Perform text generation
```
### vLLM
For vLLM, simply start a server by executing the command below:
```
# pip install vllm>=0.9.0
vllm serve tiiuae/Falcon-H1-1B-Instruct --tensor-parallel-size 2 --data-parallel-size 1
```
### `llama.cpp`
You can find all GGUF files compatible with `llama.cpp` under [our official collection](https://huggingface.co/collections/tiiuae/falcon-h1-6819f2795bc406da60fab8df)
# Evaluation
Falcon-H1 series perform very well on a variety of tasks, including reasoning tasks.
| Tasks | Falcon-H1-1.5B-deep | Qwen3-1.7B | Qwen2.5-1.5B | Gemma3-1B | Llama3.2-1B | Falcon3-1B |
| --- | --- | --- | --- | --- | --- | --- |
| **General** | | | | | |
| BBH | **54.43** | 35.18 | 42.41 | 35.86 | 33.21 | 34.47 |
| ARC-C | **43.86** | 34.81 | 40.53 | 34.13 | 34.64 | 43.09 |
| TruthfulQA | **50.48** | 49.39 | 47.05 | 42.17 | 42.08 | 42.31 |
| HellaSwag | **65.54** | 49.27 | 62.23 | 42.24 | 55.3 | 58.53 |
| MMLU | **66.11** | 57.04 | 59.76 | 40.87 | 45.93 | 46.1 |
| **Math** | | | | | |
| GSM8k | **82.34** | 69.83 | 57.47 | 42.38 | 44.28 | 44.05 |
| MATH-500 | **77.8** | 73.0 | 48.4 | 45.4 | 13.2 | 19.8 |
| AMC-23 | **56.56** | 46.09 | 24.06 | 19.22 | 7.19 | 6.87 |
| AIME-24 | **14.37** | 12.5 | 2.29 | 0.42 | 1.46 | 0.41 |
| AIME-25 | **11.04** | 8.12 | 1.25 | 1.25 | 0.0 | 0.21 |
| **Science** | | | | | |
| GPQA | **33.22** | 27.68 | 26.26 | 28.19 | 26.59 | 26.76 |
| GPQA_Diamond | **40.57** | 33.33 | 25.59 | 21.55 | 25.08 | 31.31 |
| MMLU-Pro | **41.89** | 23.54 | 28.35 | 14.46 | 16.2 | 18.49 |
| MMLU-stem | **67.3** | 54.3 | 54.04 | 35.39 | 39.16 | 39.64 |
| **Code** | | | | | |
| HumanEval | **73.78** | 67.68 | 56.1 | 40.85 | 34.15 | 22.56 |
| HumanEval+ | **68.9** | 60.96 | 50.61 | 37.2 | 29.88 | 20.73 |
| MBPP | **68.25** | 58.73 | 64.81 | 57.67 | 33.6 | 20.63 |
| MBPP+ | **56.61** | 49.74 | 56.08 | 50.0 | 29.37 | 17.2 |
| LiveCodeBench | **23.87** | 14.87 | 12.52 | 5.09 | 2.35 | 0.78 |
| CRUXEval | **52.32** | 18.88 | 34.76 | 12.7 | 0.06 | 15.58 |
| **Instruction Following** | | | | | |
| IFEval | **83.5** | 70.77 | 45.33 | 61.48 | 55.34 | 54.26 |
| Alpaca-Eval | **27.12** | 21.89 | 9.54 | 17.87 | 9.38 | 6.98 |
| MTBench | **8.53** | 7.61 | 7.1 | 7.03 | 6.37 | 6.03 |
| LiveBench | 36.83 | **40.73** | 21.65 | 18.79 | 14.97 | 14.1 |
You can check more in detail on our [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1/), detailed benchmarks.
# Useful links
- View [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1/).
- View [our technical report](https://arxiv.org/abs/2507.22448).
- Feel free to join [our discord server](https://discord.gg/trwMYP9PYm) if you have any questions or to interact with our researchers and developers.
# Citation
If the Falcon-H1 family of models were helpful to your work, feel free to give us a cite.
```
@article{falconh1,
title={Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance},
author={Jingwei Zuo and Maksim Velikanov and Ilyas Chahed and Younes Belkada and Dhia Eddine Rhayem and Guillaume Kunsch and Hakim Hacid and Hamza Yous and Brahim Farhat and Ibrahim Khadraoui and Mugariya Farooq and Giulia Campesan and Ruxandra Cojocaru and Yasser Djilali and Shi Hu and Iheb Chaabane and Puneesh Khanna and Mohamed El Amine Seddik and Ngoc Dung Huynh and Phuc Le Khac and Leen AlQadi and Billel Mokeddem and Mohamed Chami and Abdalgader Abubaker and Mikhail Lubinets and Kacper Piskorski and Slim Frikha},
journal = {arXiv preprint arXiv:2507.22448},
year={2025}
}
```

17
chat_template.jinja Normal file
View File

@@ -0,0 +1,17 @@
{{bos_token}}
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "You are a function calling AI model. You are provided with function signature within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.\n<tools>\n" }}
{%- for tool in tools %}[{{- tool | tojson }}]{%- endfor %}
{{- "\n</tools>\nFor each function call, return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:\n<tool_call>\n{'arguments': <args-dict>, 'name': <function-name>}\n</tool_call>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}{% for message in messages %}{%- if message.role != 'system' %}{{'<|im_start|>' + message['role'] + '
' + message['content'] + '<|im_end|>' + '
'}}{%- endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}

64
config.json Normal file
View File

@@ -0,0 +1,64 @@
{
"architectures": [
"FalconH1ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attention_in_multiplier": 1.0,
"attention_out_multiplier": 0.5,
"attn_layer_indices": null,
"bos_token_id": 1,
"embedding_multiplier": 5.656854249492381,
"eos_token_id": 11,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1280,
"initializer_range": 0.02,
"intermediate_size": 3072,
"key_multiplier": 0.17677669529663687,
"lm_head_multiplier": 0.03125,
"mamba_chunk_size": 128,
"mamba_conv_bias": true,
"mamba_d_conv": 4,
"mamba_d_head": 64,
"mamba_d_ssm": 1536,
"mamba_d_state": 256,
"mamba_expand": 2,
"mamba_n_groups": 1,
"mamba_n_heads": 24,
"mamba_norm_before_gate": false,
"mamba_proj_bias": false,
"mamba_rms_norm": true,
"mamba_use_mlp": true,
"max_position_embeddings": 131072,
"mlp_bias": false,
"mlp_expansion_factor": 8,
"mlp_multipliers": [
0.7071067811865476,
0.3125
],
"model_type": "falcon_h1",
"num_attention_heads": 6,
"num_hidden_layers": 66,
"num_key_value_heads": 2,
"num_logits_to_keep": 1,
"pad_token_id": 0,
"projectors_bias": false,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 100000000000.0,
"ssm_in_multiplier": 1.0,
"ssm_multipliers": [
0.3535533905932738,
0.25,
0.1767766952966369,
0.5,
0.3535533905932738
],
"ssm_out_multiplier": 0.23570226039551587,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.0.dev0",
"use_cache": true,
"vocab_size": 65537
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": [11, 228],
"pad_token_id": 0,
"transformers_version": "4.52.0.dev0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9257702f6e7c44b86ace9a74dfc213482e63d15d16f6df7415f3e89813252354
size 3109875616

356
special_tokens_map.json Normal file
View File

@@ -0,0 +1,356 @@
{
"additional_special_tokens": [
"<|pad|>",
">>ABSTRACT<<",
">>INTRODUCTION<<",
">>SUMMARY<<",
">>COMMENT<<",
">>ANSWER<<",
">>QUESTION<<",
">>DOMAIN<<",
">>PREFIX<<",
">>SUFFIX<<",
">>MIDDLE<<",
"<|finetune_right_pad_id|>",
"<|start_header_id|>",
"<|end_header_id|>",
"<|eom_id|>",
"<|eot_id|>",
"<|begin_of_text|>",
">>TITLE<<",
"<tool_response>",
"</tool_response>",
"<tool_call>",
"</tool_call>",
"<schema>",
"</schema>",
"<scratch_pad>",
"</scratch_pad>",
"<thinking>",
"</thinking>",
"<explanation>",
"</explanation>",
"<file_sep>",
"<repo_name>",
"<|im_end|>",
"<|im_start|>",
">>UNUSED_119<<",
">>UNUSED_120<<",
"<|system|>",
">>UNUSED_218<<",
">>UNUSED_219<<",
">>UNUSED_220<<",
">>UNUSED_221<<",
">>UNUSED_222<<",
">>UNUSED_223<<",
">>UNUSED_224<<",
">>UNUSED_225<<",
">>UNUSED_226<<",
">>UNUSED_227<<",
">>UNUSED_228<<",
">>UNUSED_229<<",
">>UNUSED_230<<",
">>UNUSED_231<<",
">>UNUSED_232<<",
">>UNUSED_233<<",
">>UNUSED_234<<",
">>UNUSED_235<<",
">>UNUSED_236<<",
">>UNUSED_237<<",
">>UNUSED_238<<",
">>UNUSED_239<<",
">>UNUSED_240<<",
">>UNUSED_241<<",
">>UNUSED_242<<",
">>UNUSED_243<<",
">>UNUSED_244<<",
">>UNUSED_245<<",
">>UNUSED_246<<",
">>UNUSED_247<<",
">>UNUSED_248<<",
">>UNUSED_249<<",
">>UNUSED_250<<",
">>UNUSED_251<<",
">>UNUSED_252<<",
">>UNUSED_253<<",
">>UNUSED_254<<",
">>UNUSED_255<<",
">>UNUSED_256<<",
">>UNUSED_257<<",
">>UNUSED_258<<",
">>UNUSED_259<<",
">>UNUSED_260<<",
">>UNUSED_261<<",
">>UNUSED_262<<",
">>UNUSED_263<<",
">>UNUSED_264<<",
">>UNUSED_265<<",
">>UNUSED_266<<",
">>UNUSED_267<<",
">>UNUSED_268<<",
">>UNUSED_269<<",
">>UNUSED_270<<",
">>UNUSED_271<<",
">>UNUSED_272<<",
">>UNUSED_273<<",
">>UNUSED_274<<",
">>UNUSED_275<<",
">>UNUSED_276<<",
">>UNUSED_277<<",
">>UNUSED_278<<",
">>UNUSED_279<<",
">>UNUSED_280<<",
">>UNUSED_281<<",
">>UNUSED_282<<",
">>UNUSED_283<<",
">>UNUSED_284<<",
">>UNUSED_285<<",
">>UNUSED_286<<",
">>UNUSED_287<<",
">>UNUSED_288<<",
">>UNUSED_289<<",
">>UNUSED_290<<",
">>UNUSED_291<<",
">>UNUSED_292<<",
">>UNUSED_293<<",
">>UNUSED_294<<",
">>UNUSED_295<<",
">>UNUSED_296<<",
">>UNUSED_297<<",
">>UNUSED_298<<",
">>UNUSED_299<<",
">>UNUSED_300<<",
">>UNUSED_301<<",
">>UNUSED_302<<",
">>UNUSED_303<<",
">>UNUSED_304<<",
">>UNUSED_305<<",
">>UNUSED_306<<",
">>UNUSED_307<<",
">>UNUSED_308<<",
">>UNUSED_309<<",
">>UNUSED_310<<",
">>UNUSED_311<<",
">>UNUSED_312<<",
">>UNUSED_313<<",
">>UNUSED_314<<",
">>UNUSED_315<<",
">>UNUSED_316<<",
">>UNUSED_317<<",
">>UNUSED_318<<",
">>UNUSED_319<<",
">>UNUSED_320<<",
">>UNUSED_321<<",
">>UNUSED_322<<",
">>UNUSED_323<<",
">>UNUSED_324<<",
">>UNUSED_325<<",
">>UNUSED_326<<",
">>UNUSED_327<<",
">>UNUSED_328<<",
">>UNUSED_329<<",
">>UNUSED_330<<",
">>UNUSED_331<<",
">>UNUSED_332<<",
">>UNUSED_333<<",
">>UNUSED_334<<",
">>UNUSED_335<<",
">>UNUSED_336<<",
">>UNUSED_337<<",
">>UNUSED_338<<",
">>UNUSED_339<<",
">>UNUSED_340<<",
">>UNUSED_341<<",
">>UNUSED_342<<",
">>UNUSED_343<<",
">>UNUSED_344<<",
">>UNUSED_345<<",
">>UNUSED_346<<",
">>UNUSED_347<<",
">>UNUSED_348<<",
">>UNUSED_349<<",
">>UNUSED_350<<",
">>UNUSED_351<<",
">>UNUSED_352<<",
">>UNUSED_353<<",
">>UNUSED_354<<",
">>UNUSED_355<<",
">>UNUSED_356<<",
">>UNUSED_357<<",
">>UNUSED_358<<",
">>UNUSED_359<<",
">>UNUSED_360<<",
">>UNUSED_361<<",
">>UNUSED_362<<",
">>UNUSED_363<<",
">>UNUSED_364<<",
">>UNUSED_365<<",
">>UNUSED_366<<",
">>UNUSED_367<<",
">>UNUSED_368<<",
">>UNUSED_369<<",
">>UNUSED_370<<",
">>UNUSED_371<<",
">>UNUSED_372<<",
">>UNUSED_373<<",
">>UNUSED_374<<",
">>UNUSED_375<<",
">>UNUSED_376<<",
">>UNUSED_377<<",
">>UNUSED_378<<",
">>UNUSED_379<<",
">>UNUSED_380<<",
">>UNUSED_381<<",
">>UNUSED_382<<",
">>UNUSED_383<<",
">>UNUSED_384<<",
">>UNUSED_385<<",
">>UNUSED_386<<",
">>UNUSED_387<<",
">>UNUSED_388<<",
">>UNUSED_389<<",
">>UNUSED_390<<",
">>UNUSED_391<<",
">>UNUSED_392<<",
">>UNUSED_393<<",
">>UNUSED_394<<",
">>UNUSED_395<<",
">>UNUSED_396<<",
">>UNUSED_397<<",
">>UNUSED_398<<",
">>UNUSED_399<<",
">>UNUSED_400<<",
">>UNUSED_401<<",
">>UNUSED_402<<",
">>UNUSED_403<<",
">>UNUSED_404<<",
">>UNUSED_405<<",
">>UNUSED_406<<",
">>UNUSED_407<<",
">>UNUSED_408<<",
">>UNUSED_409<<",
">>UNUSED_410<<",
">>UNUSED_411<<",
">>UNUSED_412<<",
">>UNUSED_413<<",
">>UNUSED_414<<",
">>UNUSED_415<<",
">>UNUSED_416<<",
">>UNUSED_417<<",
">>UNUSED_418<<",
">>UNUSED_419<<",
">>UNUSED_420<<",
">>UNUSED_421<<",
">>UNUSED_422<<",
">>UNUSED_423<<",
">>UNUSED_424<<",
">>UNUSED_425<<",
">>UNUSED_426<<",
">>UNUSED_427<<",
">>UNUSED_428<<",
">>UNUSED_429<<",
">>UNUSED_430<<",
">>UNUSED_431<<",
">>UNUSED_432<<",
">>UNUSED_433<<",
">>UNUSED_434<<",
">>UNUSED_435<<",
">>UNUSED_436<<",
">>UNUSED_437<<",
">>UNUSED_438<<",
">>UNUSED_439<<",
">>UNUSED_440<<",
">>UNUSED_441<<",
">>UNUSED_442<<",
">>UNUSED_443<<",
">>UNUSED_444<<",
">>UNUSED_445<<",
">>UNUSED_446<<",
">>UNUSED_447<<",
">>UNUSED_448<<",
">>UNUSED_449<<",
">>UNUSED_450<<",
">>UNUSED_451<<",
">>UNUSED_452<<",
">>UNUSED_453<<",
">>UNUSED_454<<",
">>UNUSED_455<<",
">>UNUSED_456<<",
">>UNUSED_457<<",
">>UNUSED_458<<",
">>UNUSED_459<<",
">>UNUSED_460<<",
">>UNUSED_461<<",
">>UNUSED_462<<",
">>UNUSED_463<<",
">>UNUSED_464<<",
">>UNUSED_465<<",
">>UNUSED_466<<",
">>UNUSED_467<<",
">>UNUSED_468<<",
">>UNUSED_469<<",
">>UNUSED_470<<",
">>UNUSED_471<<",
">>UNUSED_472<<",
">>UNUSED_473<<",
">>UNUSED_474<<",
">>UNUSED_475<<",
">>UNUSED_476<<",
">>UNUSED_477<<",
">>UNUSED_478<<",
">>UNUSED_479<<",
">>UNUSED_480<<",
">>UNUSED_481<<",
">>UNUSED_482<<",
">>UNUSED_483<<",
">>UNUSED_484<<",
">>UNUSED_485<<",
">>UNUSED_486<<",
">>UNUSED_487<<",
">>UNUSED_488<<",
">>UNUSED_489<<",
">>UNUSED_490<<",
">>UNUSED_491<<",
">>UNUSED_492<<",
">>UNUSED_493<<",
">>UNUSED_494<<",
">>UNUSED_495<<",
">>UNUSED_496<<",
">>UNUSED_497<<",
">>UNUSED_498<<",
">>UNUSED_499<<",
">>UNUSED_500<<",
">>UNUSED_501<<",
">>UNUSED_502<<",
">>UNUSED_503<<",
">>UNUSED_504<<",
">>UNUSED_505<<",
">>UNUSED_506<<",
">>UNUSED_507<<",
">>UNUSED_508<<",
">>UNUSED_509<<",
">>UNUSED_510<<",
">>UNUSED_511<<"
],
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

329397
tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

4545
tokenizer_config.json Normal file

File diff suppressed because it is too large Load Diff