From 8440dd0febc31c795e627727e1f8fb99da87f0fc Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 13 Apr 2026 11:24:28 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: gplsi/Aitana-2B-S-base-IP-1.0 Source: Original Platform --- .gitattributes | 36 +++++++++ README.md | 157 ++++++++++++++++++++++++++++++++++++++++ config.json | 30 ++++++++ generation_config.json | 6 ++ model.safetensors | 3 + special_tokens_map.json | 23 ++++++ tokenizer.json | 3 + tokenizer.model | 3 + tokenizer_config.json | 16 ++++ 9 files changed, 277 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..92fe572 --- /dev/null +++ b/README.md @@ -0,0 +1,157 @@ +--- +library_name: transformers +pipeline_tag: text-generation +tags: + - llama + - causal-lm + - text-generation + - transformers +--- + +# Aitana-2B-S-base-IP-1.0 + +## Table of Contents + +- Model description +- Intended uses and limitations +- How to use +- Training +- Technical specifications +- Additional information + +## Model description + +Aitana-2B-S-base-IP-1.0 is a generative language model with a decoder-only architecture. +This repository contains the base checkpoint, intended for causal language modeling and +for further adaptation or task-specific fine-tuning. + +Based on the files shipped in this repository, the checkpoint uses the Llama +architecture and the Transformers ecosystem. The local configuration indicates: + +- architecture: `LlamaForCausalLM` +- hidden size: `2048` +- layers: `24` +- attention heads: `16` +- vocabulary size: `256000` +- context length: `8192` +- tensor dtype in config: `bfloat16` + +## Intended uses and limitations + +Aitana-2B-S-base-IP-1.0 is a base model that can be used for causal language +modeling and text generation. As with other base checkpoints, it is generally more +useful as a starting point for instruction-tuning, domain adaptation, or downstream +fine-tuning than as a final end-user assistant model. + +Because this repository currently only exposes the model artifacts and not the full +training report, claims about domain coverage, language balance, safety behavior, and + benchmark performance should be added only once they are confirmed by the model +authors. + +## How to use + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "gplsi/Aitana-2B-S-base-IP-1.0" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto", +) + +prompt = "Escriu un breu resum sobre la importància de la llengua." +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) + +outputs = model.generate( + **inputs, + max_new_tokens=128, + do_sample=True, + top_p=0.9, + temperature=0.7, + eos_token_id=tokenizer.eos_token_id, + pad_token_id=tokenizer.pad_token_id, +) + +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +## Training + +### Base model + +TO-DO: document the original parent checkpoint or initialization source for +Aitana-2B-S-base-IP-1.0. + +### Training data + +TO-DO: document the training corpora, language distribution, preprocessing steps, +deduplication policy, anonymization steps, and data filtering criteria. + +### Training hyperparameters + +TO-DO: document the effective batch size, learning rate schedule, optimizer setup, +number of epochs or tokens seen, sequence length used during training, and hardware. + +## Technical specifications + +### Model architecture and objective + +- architecture: decoder-only causal language model +- implementation class: `LlamaForCausalLM` +- hidden size: `2048` +- intermediate size: `5440` +- layers: `24` +- attention heads: `16` +- key/value heads: `16` +- maximum position embeddings: `8192` +- vocabulary size: `256000` +- BOS token id: `1` +- EOS token id: `2` +- PAD token id: `3` + +### Tokenizer + +The tokenizer files in this repository define: + +- BOS token: `` +- EOS token: `` +- PAD token: `` +- UNK token: `` + +### Hardware and software + +The repository is packaged for the Hugging Face `transformers` library. +Specific training hardware and training software details should be documented by the +model authors if they are intended to be part of the public model card. + +## Additional information + +### Author + +TO-DO: confirm the author list and institutional attribution to be displayed in the +public model card. + +### Contact + +TO-DO: add a contact email or project contact point. + +### License + +TO-DO: confirm the license for this checkpoint and add it both here and in +`config.json` if desired. + +### Funding + +TO-DO: add funding information if this checkpoint is part of a funded project. + +### Disclaimer + +This repository contains a base language model checkpoint. Base models can reflect +biases present in their training data and may generate inaccurate, misleading, or +unsafe content. Anyone deploying this model, or systems built on top of it, is +responsible for evaluating those risks and ensuring compliance with applicable legal, +ethical, and operational requirements. diff --git a/config.json b/config.json new file mode 100644 index 0000000..60de044 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5440, + "max_position_embeddings": 8192, + "mlp_bias": false, + "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, + "transformers_version": "4.57.1", + "use_cache": true, + "vocab_size": 256000, + "pad_token_id": 3 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..cad7045 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.57.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..303e961 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbebcfd6c3dfe0365ab2bc2d9b57e4e3c47b57ddcb303132d6dd177f94dcfd39 +size 4507005744 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..3a5e64f --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a84e9f07a00c042e289e0d3e5d0ea113e86d40ea86ecfeae60db162fc11d88b +size 37007413 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..bf57480 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab94ddf46d14f0279254858d53770c5319c5129d47291ee2bada530271cb1292 +size 4813276 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0945306 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,16 @@ +{ + "add_prefix_space": true, + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "is_local": true, + "local_files_only": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}