初始化项目，由ModelHub XC社区提供模型

Model: teddylee777/EEVE-Korean-Instruct-10.8B-v1.0-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,43 @@
+*.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
+EEVE-Korean-Instruct-10.8B-v1.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+EEVE-Korean-Instruct-10.8B-v1.0-FP32.gguf filter=lfs diff=lfs merge=lfs -text
+EEVE-Korean-Instruct-10.8B-v1.0-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+EEVE-Korean-Instruct-10.8B-v1.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EEVE-Korean-Instruct-10.8B-v1.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EEVE-Korean-Instruct-10.8B-v1.0-FP16.gguf filter=lfs diff=lfs merge=lfs -text

EEVE-Korean-Instruct-10.8B-v1.0-FP16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb6718d4a2bda7a659f9e2040321afdec94c071bee2b69eaf27c41e096f1ab1
+size 21611605696

EEVE-Korean-Instruct-10.8B-v1.0-FP32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666bf5f60578f3605c1feea141ec422c1b0d132d971555738ce508736de2448d
+size 43220659904

EEVE-Korean-Instruct-10.8B-v1.0-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acec8e51b3f915f3b6d97c37188134ecc2012025a21fd60f54e051130a17009f
+size 6123351808

EEVE-Korean-Instruct-10.8B-v1.0-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3be01a0fe21a1637af1bc6dcfaef828569ed8072fdc407850ff11eb9abe3cb
+size 6788148992

EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e6683ad9ad6e4488b99730804a47447af43c6eba11ca36f15880d8b305eaee
+size 6512635648

EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884898856f6d6fc6870079074f18b7be1b9238bcee1d0f1df6701177cdf5b680
+size 6169489152

EEVE-Korean-Instruct-10.8B-v1.0-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d15dacebcedd38a2bd878038944f36538ac9fa8937689d85a11d480332c108
+size 7452946176

EEVE-Korean-Instruct-10.8B-v1.0-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d64121b2c9958b6ec3c7ce80829c7e398ea2981b534b98c8b0bac8ff619552a
+size 7653486336

EEVE-Korean-Instruct-10.8B-v1.0-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cbccb5ca65adb8f57b976719cb076de8cb9eac79516ad07e31825f76c16826
+size 7452946176

EEVE-Korean-Instruct-10.8B-v1.0-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba2b2c672a2cb919ca8e620f6af7bb58d2547c000e2ec20bdc75b88bcc20b6f2
+size 8865640192

EEVE-Korean-Instruct-10.8B-v1.0-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1bba02f3bcd395be5707631c48c90e3c6b14bf7f1f75317a942edca98c6022
+size 11482361600

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+base_model: yanolja/EEVE-Korean-10.8B-v1.0
+model-index:
+- name: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
+  results: []
+---
+
+
+- Original model is [yanolja/EEVE-Korean-Instruct-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0)
+- quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp)
+
+
+## Ollama
+
+Modelfile
+
+```
+FROM EEVE-Korean-Instruct-10.8B-v1.0-Q8_0.gguf
+
+TEMPLATE """{{- if .System }}
+<s>{{ .System }}</s>
+{{- end }}
+<s>Human:
+{{ .Prompt }}</s>
+<s>Assistant:
+"""
+
+SYSTEM """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."""
+
+PARAMETER temperature 0
+PARAMETER num_predict 3000
+PARAMETER num_ctx 4096
+PARAMETER stop <s>
+PARAMETER stop </s>
+```
+
+
+
+### Training Data
+  - Korean-translated version of [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
+  - Korean-translated version of [argilla/ultrafeedback-binarized-preferences-cleaned](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences-cleaned)
+  - No other dataset was used
+
+## Citation
+
+```
+@misc{kim2024efficient,
+      title={Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models}, 
+      author={Seungduk Kim and Seungtaek Choi and Myeongho Jeong},
+      year={2024},
+      eprint={2402.14714},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+```
+@misc{cui2023ultrafeedback,
+      title={UltraFeedback: Boosting Language Models with High-quality Feedback}, 
+      author={Ganqu Cui and Lifan Yuan and Ning Ding and Guanming Yao and Wei Zhu and Yuan Ni and Guotong Xie and Zhiyuan Liu and Maosong Sun},
+      year={2023},
+      eprint={2310.01377},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+```
+@misc{SlimOrcaDedup,
+  title = {SlimOrca Dedup: A Deduplicated Subset of SlimOrca},
+  author = {Wing Lian and Guan Wang and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium" and Nathan Hoos},
+  year = {2023},
+  publisher = {HuggingFace},
+  url = {https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup/}
+}
+```
+```
+@misc{mukherjee2023orca,
+      title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, 
+      author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
+      year={2023},
+      eprint={2306.02707},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "yanolja/EEVE-Korean-Instruct-10.8B-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "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": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 40960
+}

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_config.json

@@ -0,0 +1,53 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|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": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}