初始化项目，由ModelHub XC社区提供模型

Model: utter-project/EuroMoE-2.6B-A0.6B-2512
Source: Original Platform

.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

README.md

@@ -0,0 +1,54 @@
+---
+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-2512
+
+This is the model card for EuroLLM-2.6B-A0.6-2512, the pre-trained model for [EuroLLM-2.6B-A0.6-2512-Instruct](https://huggingface.co/utter-project/EuroMoE-2.6B-A0.6B-Instruct-2512).
+
+- **Developed by:** Instituto Superior Técnico - University of Lisbon, Instituto de Telecomunicações, University of Edinburgh, Aveni, Unbabel, University of Paris-Saclay, Artefact Research Center, University of Amsterdam, Naver Labs, Sorbonne Université.
+- **Funded by:** European Union.
+- **Model type:** A 2.6B 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.
+
+## Bias, Risks, and Limitations
+
+This model has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 8,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "num_local_experts": 64,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 500000,
+  "router_aux_loss_coef": 0.01,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 128000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.47.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92f098b2dd866aa8e9c503a91d8bc9503dec7dcb932fd86cf2f74982e0f2a98
+size 5000160568

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4ab44c1cc4f2dc7f365237b0b80b2abd512a7d906d30b8770d4338cc9544ad
+size 223515752

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e4810e827e4ffcd735429d19d585326bb4efb31e921cb870ecefc4c1fa16e3
+size 15783507

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42957aec88804838805b335da1bbcce9d116024a20c6c4b56757648b9e348254
+size 2408875