From 4ce2bbdbca0464a3acbc7ce7db3a8fbf82eb9d26 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 13 May 2026 10:08:34 +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: Joaoffg/ELM Source: Original Platform --- .gitattributes | 35 +++++++++++++++++++++++++++++++++ README.md | 43 +++++++++++++++++++++++++++++++++++++++++ config.json | 29 +++++++++++++++++++++++++++ generation_config.json | 6 ++++++ model.safetensors | 3 +++ special_tokens_map.json | 23 ++++++++++++++++++++++ tokenizer.model | 3 +++ tokenizer_config.json | 42 ++++++++++++++++++++++++++++++++++++++++ 8 files changed, 184 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.model create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2d03ab4 --- /dev/null +++ b/README.md @@ -0,0 +1,43 @@ +--- +license: llama2 +language: +- en +- nl +tags: +- academic +- university +--- +# Model Card for the Erasmian Language Model + +ELM is a community driven large language model tailored to the research and education needs of Erasmus University (EUR, Netherlands) students and staff. + +The model draws inspiration from ChatGPT and Llama in terms of architecture, but it aims to be privacy sensitive, environmentally conscious, and from and for the Erasmus community. Here are a few key points of ELM: + +We hope that the ELM experience becomes a template for community driven, decentralized and purpuseful AI development and application. + +## Model Details + +### Model Description + +The underlying language model is trained and fine-tuned on academic outputs from Erasmus University, such as scientific papers or student theses; +Training and fine-tuning the model is a joint effort of students and staff, transparent for all parties involved; +The prompt-response examples used to fine tune the model come from students and staff, not crowdsourcing services; +Defining what is the "better" model output also comes from the perspective of research and education. +The true richness of ELM lies in the way its training data is generated. What is the "state-of-the-art" model may change quickly, but quality data will maintain its relevance and ensure that ELM and its future iterations serve the needs of the community that nurtured it. + + + +- **Developed by:** João Gonçalves, Nick Jelicic +- **Funded by [optional]:** Convergence AI and Digitalization, Erasmus Trustfonds +- **Model type:** Llama-2 Instruct +- **Language(s) (NLP):** English, Dutch +- **License:** Llama2 + +### Model Sources + + + +- **Repository:** https://github.com/Joaoffg/ELM +- **Paper:** https://arxiv.org/abs/2408.06931 +- **Demo:** https://huggingface.co/spaces/Joaoffg/Joaoffg-ELM + diff --git a/config.json b/config.json new file mode 100644 index 0000000..22c19f8 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "/data/storage_elm_medium/CHAT_ELM_7M_RLHF_Merged", + "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": 5120, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 32, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-12, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.40.2", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..589fbca --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.40.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..30ff76c --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98d729a26e589f9c2ce43cfaf1c53e8f7b78e0b6b85f784bddb20136308e9f1 +size 3611582888 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6475c8c --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3801a11a627988531d236ce6dc33cf32c7970a232d1a18bc2aa4f6468fefcd54 +size 7170399 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..f22402f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +}