初始化项目，由ModelHub XC社区提供模型

Model: tiiuae/Falcon-H1-1.5B-Base Source: Original Platform
2026-11-03 20:16:13 +08:00
commit 108d67a019
9 changed files with 334539 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,152 @@
+---
+library_name: transformers
+language:
+- ar
+- cs
+- de
+- en
+- es
+- fr
+- hi
+- it
+- ja
+- ko
+- nl
+- pl
+- pt
+- ro
+- ru
+- sv
+- ur
+- zh
+tags:
+- falcon-h1
+license: other
+license_name: falcon-llm-license
+license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
+---
+
+<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 our `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 | Qwen3-1.7B | Qwen2.5-1.5B | Gemma3-1B | Llama3.2-1B | Falcon3-1B |
+| --- | --- | --- | --- | --- | --- | --- |
+| **General**  | | | | | |
+| BBH | **46.57** | 43.05 | 40.55 | 30.26 | 30.72 | 35.24 |
+| MMLU | 61.81 | **62.46** | 61.13 | 26.33 | 32.39 | 45.14 |
+| ARC-C | 53.24 | **55.72** | 54.27 | 39.33 | 39.42 | 47.87 |
+| HellaSwag | 66.76 | 67.09 | **67.86** | 62.94 | 65.73 | 62.3 |
+| Winogrande | 65.59 | **66.3** | 64.56 | 62.59 | 62.75 | 61.17 |
+| **Math**  | | | | | |
+| GSM8k | 52.01 | **70.74** | 63.0 | 2.2 | 7.05 | 34.95 |
+| MATH lvl5 | **20.39** | 16.39 | 8.84 | 1.21 | 0.98 | 3.4 |
+| **Science**  | | | | | |
+| GPQA | 29.11 | **29.45** | 28.36 | 24.66 | 23.57 | 27.85 |
+| MMLU-Pro | **35.53** | 33.81 | 28.72 | 11.31 | 11.8 | 16.11 |
+| MMLU-stem | **63.37** | 61.53 | 54.93 | 27.59 | 30.19 | 40.06 |
+| **Code**  | | | | | |
+| HumanEval | 50.0 | **67.68** | 35.37 | 6.71 | 18.9 | 10.37 |
+| HumanEval+ | 42.68 | **60.98** | 29.27 | 5.49 | 16.46 | 9.15 |
+| MBPP | 65.08 | **67.72** | 60.05 | 12.7 | 35.98 | 12.43 |
+| MBPP+ | 55.03 | **58.99** | 49.47 | 9.52 | 29.89 | 9.52 |
+
+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}
+}
+```
--- a/config.json
+++ b/config.json
@@ -0,0 +1,64 @@
+{
+  "architectures": [
+    "FalconH1ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_in_multiplier": 1.0,
+  "attention_out_multiplier": 0.234375,
+  "attn_layer_indices": null,
+  "bos_token_id": 1,
+  "embedding_multiplier": 5.656854249492381,
+  "eos_token_id": 11,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "key_multiplier": 0.06905339660024876,
+  "lm_head_multiplier": 0.01953125,
+  "mamba_chunk_size": 128,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_head": 64,
+  "mamba_d_ssm": 3072,
+  "mamba_d_state": 256,
+  "mamba_expand": 2,
+  "mamba_n_groups": 1,
+  "mamba_n_heads": 48,
+  "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": [
+    0.4419417382415922,
+    0.13020833333333331
+  ],
+  "model_type": "falcon_h1",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 24,
+  "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": 0.625,
+  "ssm_multipliers": [
+    0.3535533905932738,
+    0.25,
+    0.1767766952966369,
+    0.5,
+    0.3535533905932738
+  ],
+  "ssm_out_multiplier": 0.11785113019775793,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65536
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "pad_token_id": 0,
+  "transformers_version": "4.52.0.dev0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acd2ef3e946e88a6e8cb14d38942f2ffbf6f52a5bc37312c1e0cc64574f1aeb
+size 3109764840
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,342 @@
+{
+  "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>",
+    ">>UNUSED_119<<",
+    ">>UNUSED_120<<",
+    ">>UNUSED_215<<",
+    ">>UNUSED_216<<",
+    ">>UNUSED_217<<",
+    ">>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<<"
+  ],
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`