初始化项目，由ModelHub XC社区提供模型

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

.gitattributes

@@ -0,0 +1,52 @@
+*.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
+ 
+*.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.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,118 @@
+---
+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
+base_model:
+- utter-project/EuroMoE-2.6B-A0.6B-Preview
+---
+
+# Model Card for EuroMoE-2.6B-A0.6B-Instruct-Preview
+
+⚠️ PREVIEW RELEASE: This is a preview version of EuroMoE-2.6B-A0.6B-Instruct-Preview. The model is still under development and may have limitations in performance and stability. Use with caution in production environments.
+
+This is the model card for EuroMoE-2.6B-A0.6B-Instruct-Preview. You can also check the pre-trained version: [EuroMoE-2.6B-A0.6B-Preview](https://huggingface.co/utter-project/EuroMoE-2.6B-A0.6B-Preview).
+
+- **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 2.6B parameter multilingual transformer MoE with 0.6B active parameters.
+- **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.
+EuroMoE-2.6B-A0.6B is a 22B parameter model trained on 8 trillion tokens divided across the considered languages and several data sources: Web data, parallel data (en-xx and xx-en), and high-quality datasets.
+EuroMoE-2.6B-A0.6B-Instruct was further instruction tuned on EuroBlocks, an instruction tuning dataset with focus on general instruction-following and machine translation.
+
+
+### Model Description
+
+EuroMoE uses a standard MoE Transformer architecture:
+- We use grouped query attention (GQA) with 2 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 512 Nvidia A100 GPUs of the Leonardo supercomputer, training the model with a constant batch size of 4096 sequences, which corresponds to approximately 17 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                     |         24           |
+| Embedding Size                       |           1,024      |
+| Total/Active experts                  |      64/8      |
+| Expert Hidden Size                   |            512      |
+| Number of Heads                      |        8            |
+| Number of KV Heads (GQA)             |         2            |
+| Activation Function                  | SwiGLU               |
+| Position Encodings                   | RoPE (\Theta=500,000) |
+| Layer Norm                           | RMSNorm              |
+| Tied Embeddings                      | Yes                  |
+| Embedding Parameters                 | 0.13B               |
+| LM Head Parameters                   | 0.13B               |
+| Active Non-embedding Parameters             | 0.34B               |
+| Total Non-embedding Parameters             | 2.35B               |
+| Active Parameters                   | 0.6B               |
+| Total Parameters                     | 2.61B               |
+
+## Run the model
+    
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+    
+    model_id = "utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview"
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id)
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are EuroLLM --- an AI assistant specialized in European languages that provides safe, educational and helpful answers.",
+        },
+        {
+            "role": "user", "content": "What is the capital of Portugal? How would you describe it?"
+        },
+        ]
+
+    inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+    outputs = model.generate(inputs, max_new_tokens=1024)
+    print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+
+## Bias, Risks, and Limitations
+
+EuroMoE-2.6B-A0.6B-Instruct-Preview 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 +1,32 @@
+{
+  "_name_or_path": "/mnt/cephfs-nvme/nunomg/axolotl/sft_ckpts/eurollm/EuroBlocks-500M-2.5B-MoE-200525-chatml-after-anneal",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 4,
+  "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": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 128000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dffaff23a9e5e58a8dd19745cbdcf22095f4e7f28d6183d08b009221ab22dc5e
+size 5000160568

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f23d9076af7abad027cd092a9a19c140dd6fd9cfb0315c1612f7c400b171f03
+size 223515752

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_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