初始化项目，由ModelHub XC社区提供模型

Model: teddylee777/Llama-3-Open-Ko-8B-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,45 @@
+*.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
+Llama-3-Open-Ko-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Open-Ko-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Open-Ko-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Open-Ko-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Open-Ko-8B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Open-Ko-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Open-Ko-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Open-Ko-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Open-Ko-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-Open-Ko-8B-FP16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997bb28ff1bfb69be3b613ea7513a92b69bff73793e73278b4ad45527b9e61c3
+size 16068890432

Llama-3-Open-Ko-8B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16cee5d03821faab0336e64d98466291d5833d3aa3c2bacd0ee89c80c667ad7
+size 4661211360

Llama-3-Open-Ko-8B-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175345fdad8a8dccc8803b70d80c80c41345e437837715b6ee4b516c93ce3340
+size 5130252512

Llama-3-Open-Ko-8B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7948cb641cd4788d8f9422e7bcfd43872e669c1eaf025ec448874d24153d5cc9
+size 4920733920

Llama-3-Open-Ko-8B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2390fa8644f8faa6f560b943a1f1cfdf7efceb167eb03e8a04b6927b8148d28
+size 4692668640

Llama-3-Open-Ko-8B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0e462753d711bc3cdd80ff24f27b95d6f249e4170687776e639a8442c75ef5
+size 5599293664

Llama-3-Open-Ko-8B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8d628db5c6bf1afdf9faa82c538805899b9794056063cd50984b2896b11f14
+size 5732987104

Llama-3-Open-Ko-8B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc5d4cd2aa871ebcef86c8d00f6dbcb615d7fbb7c9f64461dd78160b45987e1
+size 5599293664

Llama-3-Open-Ko-8B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce061de7ea05ffe5e5d98ae0f3278a10fd3219670aff71c636c7751af1f45cf
+size 6596006112

Llama-3-Open-Ko-8B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074cf30c3b2d9432de158d61630e8098ea97c7c18163795583b78adf67944835
+size 8540770528

README.md

@@ -0,0 +1,149 @@
+---
+language:
+- en
+- ko
+pipeline_tag: text-generation
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
+- llama-3-ko
+license: llama3
+license_name: llama3
+license_link: https://llama.meta.com/llama3/license
+---
+
+- Original model is [beomi/Llama-3-Open-Ko-8B](https://huggingface.co/beomi/Llama-3-Open-Ko-8B)
+- quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp)
+
+
+## Ollama
+
+Modelfile
+
+```
+FROM Llama-3-Open-Ko-8B-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>
+```
+
+
+> Update @ 2024.04.24: Release Llama-3-Open-Ko-8B model & [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview)
+
+## Model Details
+
+**Llama-3-Open-Ko-8B**
+
+The Llama-3-Open-Ko-8B model is a continued pretrained language model based on the Llama-3-8B framework. This model is trained with over 60GB of deduplicated texts sourced from publicly available resources. With the new Llama-3 tokenizer, the model has been pretrained with more than 17.7B tokens, which is slightly more than that processed by the Korean tokenizer of Llama-2. Training was conducted on a TPUv5e-256, supported by Google's TRC program.
+
+**Llama-3-Open-Ko-8B-Instruct-preview**
+
+The Instruction model, named Llama-3-Open-Ko-8B-Instruct-preview, incorporates concepts from the [Chat Vector paper](https://arxiv.org/abs/2310.04799). This model is a preview and has not been fine-tuned with any Korean instruction set, making it a strong starting point for developing new chat and instruct models.
+
+**Meta Llama-3**
+
+Developed and released by Meta, the Meta Llama 3 family of large language models (LLMs) are optimized for dialogue use cases and excel across common industry benchmarks, emphasizing helpfulness and safety. 
+
+**Model Developers**: Junbum Lee (Beomi)
+
+**Variations**: Llama-3-Open-Ko is available in one configuration — 8B.
+
+**Input/Output**: Models accept text input and generate text and code.
+
+**Model Architecture**: Llama 3 utilizes an optimized transformer architecture.
+
+<table>
+  <tr>
+   <td>
+   </td>
+   <td><strong>Training Data</strong>
+   </td>
+   <td><strong>Params</strong>
+   </td>
+   <td><strong>Context length</strong>
+   </td>
+   <td><strong>GQA</strong>
+   </td>
+   <td><strong>Token count</strong>
+   </td>
+   <td><strong>Knowledge cutoff</strong>
+   </td>
+  </tr>
+  <tr>
+   <td rowspan="2" >Llama-3-Open-Ko
+   </td>
+   <td rowspan="2" >Same as Open-Solar-Ko Dataset
+   </td>
+   <td>8B
+   </td>
+   <td>8k
+   </td>
+   <td>Yes
+   </td>
+   <td rowspan="2" >17.7B+
+   </td>
+   <td>Jun, 2023
+   </td>
+  </tr>
+</table>
+
+*Dataset list available [here](https://huggingface.co/beomi/OPEN-SOLAR-KO-10.7B/tree/main/corpus)
+
+## Intended Use
+
+**Commercial and Research Applications**: Llama 3 is designed for use in English, tailored for assistant-like chat in its instruction-tuned models, while the pretrained models are versatile across various natural language generation tasks.
+
+**Out-of-scope**: Any use violating applicable laws, regulations, or the Acceptable Use Policy and Llama 3 Community License is prohibited.
+
+### Responsibility & Safety
+
+Meta's commitment to Responsible AI includes steps to limit misuse and harm while supporting the open source community. Developers are encouraged to implement safety best practices and use resources like [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) to tailor safety needs specifically to their use cases.
+
+#### Responsible Release
+
+Following a rigorous process against misuse, we ensure all safety and ethical guidelines are adhered to, as detailed in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
+
+## Ethical Considerations and Limitations
+
+Llama 3 is built on the principles of openness, inclusivity, and helpfulness, designed to be accessible and valuable across diverse backgrounds and use cases. Developers should undertake thorough safety testing and tuning for specific applications before deployment.
+
+
+## Citation instructions
+
+**Llama-3-Open-Ko**
+
+```
+@article{llama3openko,
+  title={Llama-3-Open-Ko},
+  author={L, Junbum},
+  year={2024},
+  url={https://huggingface.co/beomi/Llama-3-Open-Ko-8B}
+}
+```
+
+**Original Llama-3**
+
+```
+@article{llama3modelcard,
+  title={Llama 3 Model Card},
+  author={AI@Meta},
+  year={2024},
+  url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.35.2"
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "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:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7
+size 9085698