初始化项目，由ModelHub XC社区提供模型

Model: AIDC-AI/Marco-LLM-ES
Source: Original Platform

.gitattributes

@@ -0,0 +1,39 @@
+*.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
+model-00000-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,66 @@
+---
+language:
+- es
+pipeline_tag: text-generation
+tags:
+- pretrained
+license: apache-2.0
+---
+
+# Marco-LLM-ES-7B
+
+## Introduction
+
+Marco-LLM-ES is a series of enhanced language models specifically fine-tuned for common languages used in Spain, including Catalan, Basque, Galician, and Spanish. This repository contains the 7B Marco-LLM-ES base language model.
+
+Compared with the state-of-the-art open-source language models, Marco-LLM-ES has undergone extensive continued pretraining on a dataset containing approximately 50 billion tokens, enhancing its capabilities in the targeted languages while maintaining competitiveness in general benchmarks.
+
+For more details, please refer to our [Hugging Face page](https://huggingface.co/AIDC-AI/Marco-LLM-ES).
+
+## Model Details
+
+Marco-LLM-ES series includes models of varying sizes, from 7B to 72B parameters, including both base and instruction-tuned (Instruct) models. The models are based on the Transformer architecture with SwiGLU activation, attention QKV bias, and group query attention. Additionally, the models employ an improved tokenizer adaptive to multiple languages.
+
+## Usage
+
+It is not advised to use the base language models for direct text generation tasks. Instead, it is recommended to apply post-training methods such as Supervised Fine-tuning (SFT), Reinforcement Learning with Human Feedback (RLHF), or continued pretraining to adapt the models for specific use cases.
+
+### Performance
+
+The evaluation of Marco-LLM-ES models focuses on performance in natural language understanding, general question answering, coding, mathematics, scientific knowledge, reasoning, multilingual capability, and their enhanced performance in the targeted languages: Catalan, Basque, Galician, and Spanish.
+
+The datasets used for evaluation include:
+
+**Spanish-specific Tasks**: Evaluations in Catalan, Basque, Galician, and Spanish at LaLeaderboard (5-shot)
+
+
+#### Marco-LLM-ES-7B performance
+
+|  Datasets         |   Marco-LLM-ES-7B  |
+| :---------------- | :-----------------: |
+| Spanish           | **44.49**           |
+| Catalan           | **39.45**           |
+| Basque            | **28.66**           |
+| Galician          | **24.04**           |
+| Average           | **34.16**           |
+
+## Citation
+
+If you find our work helpful, please give us a citation.
+```
+@article{unique_identifier,
+
+title={Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement},
+
+journal={arXiv},
+
+volume={},
+
+number={2412.04003},
+
+year={2024},
+
+url={https://arxiv.org/abs/2412.04003}
+
+}
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

configuration.json

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

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": false,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.37.0"
+}

model-00000-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77bee75a8c93efaa5a0a202997573412f61f2ef6d8139d2faf52ab7df2d46ef
+size 3875705088

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ebe54df7334c1ecc46757e52374c2168f6e0294d16e17e5da51249f1758ac70
+size 4444566848

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a919d27f9962974172847ab360be9f9ae3d5d94f4b5f2e80b627d8632a32cc2
+size 4224367056

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344f94a8fbc5d32a71d5ac94a2021db506d2dc8c3a503cd5cea74291dfec9c8f
+size 2686632840

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+    "metadata": {
+    "total_size": 15231233024
+    },
+    "weight_map": {
+        "model.layers.19.self_attn.o_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00000-of-00004.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.norm.weight": "model-00001-of-00004.safetensors",
+        "lm_head.weight": "model-00002-of-00004.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00000-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors"
+    }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}