commit 4ff21b5731c06a791c67795c5ba7a2d88c33c4c4 Author: ModelHub XC Date: Sun Aug 2 13:29:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: utter-project/EuroLLM-9B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40c5359 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow 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 + +*.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 + +*.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 + +tokenizer.model filter=lfs diff=lfs merge=lfs -text +pytorch_model.bin filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd3eb95 --- /dev/null +++ b/README.md @@ -0,0 +1,126 @@ +--- +license: apache-2.0 +language: +- en +- de +- es +- fr +- it +- pt +- pl +- nl +- tr +- sv +- cs +- el +- hu +- ro +- fi +- uk +- sl +- sk +- da +- lt +- lv +- et +- bg +- 'no' +- ca +- hr +- ga +- mt +- gl +- zh +- ru +- ko +- ja +- ar +- hi +library_name: transformers +--- + +# Model Card for EuroLLM-9B + + +This is the model card for EuroLLM-9B. You can also check the instruction tuned version: [EuroLLM-9B-Instruct](https://huggingface.co/utter-project/EuroLLM-9B-Instruct). + +- **Developed by:** Unbabel, Instituto Superior Técnico, Instituto de Telecomunicações, University of Edinburgh, Aveni, University of Paris-Saclay, University of Amsterdam, Naver Labs, Sorbonne Université. +- **Funded by:** European Union. +- **Model type:** A 9B parameter multilingual transfomer LLM. +- **Language(s) (NLP):** Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Irish, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish, Arabic, Catalan, Chinese, Galician, Hindi, Japanese, Korean, Norwegian, Russian, Turkish, and Ukrainian. +- **License:** Apache License 2.0. + +## Model Details + +The EuroLLM project has the goal of creating a suite of LLMs capable of understanding and generating text in all European Union languages as well as some additional relevant languages. +EuroLLM-9B is a 9B parameter model trained on 4 trillion tokens divided across the considered languages and several data sources: Web data, parallel data (en-xx and xx-en), and high-quality datasets. +EuroLLM-9B-Instruct was further instruction tuned on EuroBlocks, an instruction tuning dataset with focus on general instruction-following and machine translation. + + +### Model Description + +EuroLLM uses a standard, dense Transformer architecture: +- We use grouped query attention (GQA) with 8 key-value heads, since it has been shown to increase speed at inference time while maintaining downstream performance. +- We perform pre-layer normalization, since it improves the training stability, and use the RMSNorm, which is faster. +- We use the SwiGLU activation function, since it has been shown to lead to good results on downstream tasks. +- We use rotary positional embeddings (RoPE) in every layer, since these have been shown to lead to good performances while allowing the extension of the context length. + +For pre-training, we use 400 Nvidia H100 GPUs of the Marenostrum 5 supercomputer, training the model with a constant batch size of 2,800 sequences, which corresponds to approximately 12 million tokens, using the Adam optimizer, and BF16 precision. +Here is a summary of the model hyper-parameters: +| | | +|--------------------------------------|----------------------| +| Sequence Length | 4,096 | +| Number of Layers | 42 | +| Embedding Size | 4,096 | +| FFN Hidden Size | 12,288 | +| Number of Heads | 32 | +| Number of KV Heads (GQA) | 8 | +| Activation Function | SwiGLU | +| Position Encodings | RoPE (\Theta=10,000) | +| Layer Norm | RMSNorm | +| Tied Embeddings | No | +| Embedding Parameters | 0.524B | +| LM Head Parameters | 0.524B | +| Non-embedding Parameters | 8.105B | +| Total Parameters | 9.154B | + +## Run the model + + from transformers import AutoModelForCausalLM, AutoTokenizer + + model_id = "utter-project/EuroLLM-9B" + tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id) + + text = "English: My name is EuroLLM. Portuguese:" + + inputs = tokenizer(text, return_tensors="pt") + outputs = model.generate(**inputs, max_new_tokens=20) + print(tokenizer.decode(outputs[0], skip_special_tokens=True)) + + +## Results + +### EU Languages + + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/63f33ecc0be81bdc5d903466/ob_1sLM8c7dxuwpv6AAHA.png) +**Table 1:** Comparison of open-weight LLMs on multilingual benchmarks. The borda count corresponds to the average ranking of the models (see ([Colombo et al., 2022](https://arxiv.org/abs/2202.03799))). For Arc-challenge, Hellaswag, and MMLU we are using Okapi datasets ([Lai et al., 2023](https://aclanthology.org/2023.emnlp-demo.28/)) which include 11 languages. For MMLU-Pro and MUSR we translate the English version with Tower ([Alves et al., 2024](https://arxiv.org/abs/2402.17733)) to 6 EU languages. +\* As there are no public versions of the pre-trained models, we evaluated them using the post-trained versions. + +The results in Table 1 highlight EuroLLM-9B's superior performance on multilingual tasks compared to other European-developed models (as shown by the Borda count of 1.0), as well as its strong competitiveness with non-European models, achieving results comparable to Gemma-2-9B and outperforming the rest on most benchmarks. + +### English + + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/63f33ecc0be81bdc5d903466/EfilsW_p-JA13mV2ilPkm.png) + +**Table 2:** Comparison of open-weight LLMs on English general benchmarks. +\* As there are no public versions of the pre-trained models, we evaluated them using the post-trained versions. + +The results in Table 2 demonstrate EuroLLM's strong performance on English tasks, surpassing most European-developed models and matching the performance of Mistral-7B (obtaining the same Borda count). + + +## Bias, Risks, and Limitations + +EuroLLM-9B has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements). diff --git a/config.json b/config.json new file mode 100644 index 0000000..357ea58 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 42, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.1", + "use_cache": true, + "vocab_size": 128000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8a0505d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.40.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..4d5d32b --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5517592f3f7ee60778497e6f1f60080ebc6b2fa2e545cbee58264ca7a897f1ae +size 18304683744 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..a0870fd --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cb50bebf1425550c6d4659a4ba33f2eaf101a3dc02fb35774e7b9c3cb618ac +size 18304766238 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..5bae06b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a25fe2b15ebf63338f3a9bda8655ea6ffbb7eafe719fdd891f42a0e468aae982 +size 8175769 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..062965b --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42957aec88804838805b335da1bbcce9d116024a20c6c4b56757648b9e348254 +size 2408875 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..8055981 --- /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": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "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": false +}