andrijdavid commited on
Commit
977b8c5
β€’
1 Parent(s): f1cbc91

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +338 -0
README.md ADDED
@@ -0,0 +1,338 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+
3
+ ---
4
+ language:
5
+ - en
6
+ - ko
7
+ license: other
8
+ tags:
9
+ - facebook
10
+ - meta
11
+ - pytorch
12
+ - llama
13
+ - llama-3
14
+ - llama-3-ko
15
+ - GGUF
16
+ pipeline_tag: text-generation
17
+ license_name: llama3
18
+ license_link: LICENSE
19
+ quantized_by: andrijdavid
20
+ ---
21
+ # Llama-3-Open-Ko-8B-Instruct-preview-GGUF
22
+ - Original model: [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview)
23
+
24
+ <!-- description start -->
25
+ ## Description
26
+
27
+ This repo contains GGUF format model files for [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview).
28
+
29
+ <!-- description end -->
30
+ <!-- README_GGUF.md-about-gguf start -->
31
+ ### About GGUF
32
+ GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
33
+ Here is an incomplete list of clients and libraries that are known to support GGUF:
34
+ * [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.
35
+ * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.
36
+ * [Ollama](https://github.com/jmorganca/ollama) Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​
37
+ * [KoboldCpp](https://github.com/LostRuins/koboldcpp), A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.
38
+ * [GPT4All](https://gpt4all.io), This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.
39
+ * [LM Studio](https://lmstudio.ai/) An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.
40
+ * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.
41
+ * [Faraday.dev](https://faraday.dev/), An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.
42
+ * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.
43
+ * [candle](https://github.com/huggingface/candle), A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.
44
+ * [ctransformers](https://github.com/marella/ctransformers), A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.
45
+ * [localGPT](https://github.com/PromtEngineer/localGPT) An open-source initiative enabling private conversations with documents.
46
+ <!-- README_GGUF.md-about-gguf end -->
47
+
48
+ <!-- compatibility_gguf start -->
49
+ ## Explanation of quantisation methods
50
+ <details>
51
+ <summary>Click to see details</summary>
52
+ The new methods available are:
53
+
54
+ * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
55
+ * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
56
+ * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
57
+ * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
58
+ * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.
59
+ </details>
60
+ <!-- compatibility_gguf end -->
61
+
62
+ <!-- README_GGUF.md-how-to-download start -->
63
+ ## How to download GGUF files
64
+
65
+ **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.
66
+
67
+ The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
68
+
69
+ * LM Studio
70
+ * LoLLMS Web UI
71
+ * Faraday.dev
72
+
73
+ ### In `text-generation-webui`
74
+
75
+ Under Download Model, you can enter the model repo: LiteLLMs/Llama-3-Open-Ko-8B-Instruct-preview-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-00001-of-00009.gguf.
76
+
77
+ Then click Download.
78
+
79
+ ### On the command line, including multiple files at once
80
+
81
+ I recommend using the `huggingface-hub` Python library:
82
+
83
+ ```shell
84
+ pip3 install huggingface-hub
85
+ ```
86
+
87
+ Then you can download any individual model file to the current directory, at high speed, with a command like this:
88
+
89
+ ```shell
90
+ huggingface-cli download LiteLLMs/Llama-3-Open-Ko-8B-Instruct-preview-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False
91
+ ```
92
+
93
+ <details>
94
+ <summary>More advanced huggingface-cli download usage (click to read)</summary>
95
+
96
+ You can also download multiple files at once with a pattern:
97
+
98
+ ```shell
99
+ huggingface-cli download LiteLLMs/Llama-3-Open-Ko-8B-Instruct-preview-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
100
+ ```
101
+
102
+ For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
103
+
104
+ To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
105
+
106
+ ```shell
107
+ pip3 install huggingface_hub[hf_transfer]
108
+ ```
109
+
110
+ And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
111
+
112
+ ```shell
113
+ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download LiteLLMs/Llama-3-Open-Ko-8B-Instruct-preview-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False
114
+ ```
115
+
116
+ Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
117
+ </details>
118
+ <!-- README_GGUF.md-how-to-download end -->
119
+ <!-- README_GGUF.md-how-to-run start -->
120
+ ## Example `llama.cpp` command
121
+
122
+ Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
123
+
124
+ ```shell
125
+ ./main -ngl 35 -m Q4_0/Q4_0-00001-of-00009.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>"
126
+ ```
127
+
128
+ Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
129
+
130
+ Change `-c 8192` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
131
+
132
+ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
133
+
134
+ For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
135
+
136
+ ## How to run in `text-generation-webui`
137
+
138
+ Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
139
+
140
+ ## How to run from Python code
141
+
142
+ You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
143
+
144
+ ### How to load this model in Python code, using llama-cpp-python
145
+
146
+ For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
147
+
148
+ #### First install the package
149
+
150
+ Run one of the following commands, according to your system:
151
+
152
+ ```shell
153
+ # Base ctransformers with no GPU acceleration
154
+ pip install llama-cpp-python
155
+ # With NVidia CUDA acceleration
156
+ CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
157
+ # Or with OpenBLAS acceleration
158
+ CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
159
+ # Or with CLBLast acceleration
160
+ CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
161
+ # Or with AMD ROCm GPU acceleration (Linux only)
162
+ CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
163
+ # Or with Metal GPU acceleration for macOS systems only
164
+ CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
165
+ # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
166
+ $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
167
+ pip install llama-cpp-python
168
+ ```
169
+
170
+ #### Simple llama-cpp-python example code
171
+
172
+ ```python
173
+ from llama_cpp import Llama
174
+ # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
175
+ llm = Llama(
176
+ model_path="./Q4_0/Q4_0-00001-of-00009.gguf", # Download the model file first
177
+ n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
178
+ n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
179
+ n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
180
+ )
181
+ # Simple inference example
182
+ output = llm(
183
+ "<PROMPT>", # Prompt
184
+ max_tokens=512, # Generate up to 512 tokens
185
+ stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
186
+ echo=True # Whether to echo the prompt
187
+ )
188
+ # Chat Completion API
189
+ llm = Llama(model_path="./Q4_0/Q4_0-00001-of-00009.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
190
+ llm.create_chat_completion(
191
+ messages = [
192
+ {"role": "system", "content": "You are a story writing assistant."},
193
+ {
194
+ "role": "user",
195
+ "content": "Write a story about llamas."
196
+ }
197
+ ]
198
+ )
199
+ ```
200
+
201
+ ## How to use with LangChain
202
+
203
+ Here are guides on using llama-cpp-python and ctransformers with LangChain:
204
+
205
+ * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
206
+ * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
207
+
208
+ <!-- README_GGUF.md-how-to-run end -->
209
+
210
+ <!-- footer end -->
211
+
212
+ <!-- original-model-card start -->
213
+ # Original model card: Llama-3-Open-Ko-8B-Instruct-preview
214
+
215
+
216
+ ## Llama-3-Open-Ko-8B-Instruct-preview
217
+
218
+ > Update @ 2024.05.01: Pre-Release [Llama-3-KoEn-8B](https://huggingface.co/beomi/Llama-3-KoEn-8B-preview) model & [Llama-3-KoEn-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-KoEn-8B-Instruct-preview)
219
+
220
+ > Update @ 2024.04.24: Release [Llama-3-Open-Ko-8B model](https://huggingface.co/beomi/Llama-3-Open-Ko-8B) & [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview)
221
+
222
+ ## Model Details
223
+
224
+ **Llama-3-Open-Ko-8B-Instruct-preview**
225
+
226
+ Llama-3-Open-Ko-8B model is continued pretrained language model based on Llama-3-8B.
227
+
228
+ This model is trained fully with publicily available resource, with 60GB+ of deduplicated texts.
229
+
230
+ With the new Llama-3 tokenizer, the pretraining conducted with 17.7B+ tokens, which slightly more than Korean tokenizer(Llama-2-Ko tokenizer).
231
+
232
+ The train was done on TPUv5e-256, with the warm support from TRC program by Google.
233
+
234
+ With applying the idea from [Chat Vector paper](https://arxiv.org/abs/2310.04799), I released Instruction model named [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview).
235
+
236
+ Since it is NOT finetuned with any Korean instruction set(indeed `preview`), but it would be great starting point for creating new Chat/Instruct models.
237
+
238
+ **Sample usage**
239
+
240
+ ```python
241
+ from transformers import AutoTokenizer, AutoModelForCausalLM
242
+ import torch
243
+
244
+ model_id = "beomi/Llama-3-Open-Ko-8B-Instruct-preview"
245
+
246
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
247
+ model = AutoModelForCausalLM.from_pretrained(
248
+ model_id,
249
+ torch_dtype="auto",
250
+ device_map="auto",
251
+ )
252
+
253
+ messages = [
254
+ {"role": "system", "content": "μΉœμ ˆν•œ μ±—λ΄‡μœΌλ‘œμ„œ μƒλŒ€λ°©μ˜ μš”μ²­μ— μ΅œλŒ€ν•œ μžμ„Έν•˜κ³  μΉœμ ˆν•˜κ²Œ λ‹΅ν•˜μž. λͺ¨λ“  λŒ€λ‹΅μ€ ν•œκ΅­μ–΄(Korean)으둜 λŒ€λ‹΅ν•΄μ€˜."},
255
+ {"role": "user", "content": "ν”Όλ³΄λ‚˜μΉ˜ μˆ˜μ—΄μ΄ 뭐야? 그리고 ν”Όλ³΄λ‚˜μΉ˜ μˆ˜μ—΄μ— λŒ€ν•΄ 파이썬 μ½”λ“œλ₯Ό 짜쀘볼래?"},
256
+ ]
257
+
258
+ input_ids = tokenizer.apply_chat_template(
259
+ messages,
260
+ add_generation_prompt=True,
261
+ return_tensors="pt"
262
+ ).to(model.device)
263
+
264
+ terminators = [
265
+ tokenizer.eos_token_id,
266
+ tokenizer.convert_tokens_to_ids("<|eot_id|>")
267
+ ]
268
+
269
+ outputs = model.generate(
270
+ input_ids,
271
+ max_new_tokens=512,
272
+ eos_token_id=terminators,
273
+ do_sample=True,
274
+ temperature=1,
275
+ top_p=0.9,
276
+ )
277
+ response = outputs[0][input_ids.shape[-1]:]
278
+ print(tokenizer.decode(response, skip_special_tokens=True))
279
+ ```
280
+
281
+ **Sample Output**
282
+
283
+ μ—¬λŸ¬λΆ„κ»˜μ„œλŠ” λ¬Όλ‘  μ•„μ‹œλŠ”μ§€λΌλ„ μ„€λͺ…을 λ“œλ¦¬κ² μŠ΅λ‹ˆλ‹€! ν”Όλ³΄λ‚˜μΉ˜(Piconacci) μˆ˜μ—΄μ€ λ‹€μŒκ³Ό 같은 μˆ˜μ—΄μ„ λ§ν•©λ‹ˆλ‹€: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144, 233,.... μ΄λ ‡κ²Œ κ³„μ†λ˜κ³  μžˆμŠ΅λ‹ˆλ‹€. 이 μˆ˜μ—΄μ€ μΌλ°˜μ μœΌλ‘œλŠ” μˆ˜ν•™μ—μ„œ λ¬΄ν•œνžˆ μ§€μ†λ©λ‹ˆλ‹€. 각 μˆ˜λŠ” 이전 수의 두 λ°°κ°€ λ˜λŠ” μˆ˜μ—΄μž…λ‹ˆλ‹€.
284
+
285
+ 이 μˆ˜μ—΄μ„ 파이썬(Python)으둜 κ΅¬ν˜„ν•˜κ³ μž ν•˜μ‹ λ‹€λ©΄ λ‹€μŒκ³Ό 같은 μ½”λ“œλ₯Ό μž‘μ„±ν•  수 μžˆμŠ΅λ‹ˆλ‹€.
286
+ ```python
287
+ def fibonacci(n):
288
+ if n == 0:
289
+ return 0
290
+ elif n == 1:
291
+ return 1
292
+ else:
293
+ return fibonacci(n-1) + fibonacci(n-2)
294
+ ```
295
+ 이 μ½”λ“œμ—μ„œλŠ” `n`이 μž…λ ₯받은 수λ₯Ό λ‚˜νƒ€λ‚΄λŠ” λ³€μˆ˜λ‘œ, ν”Όλ³΄λ‚˜μΉ˜ μˆ˜μ—΄μ„ κ΅¬ν˜„ν•©λ‹ˆλ‹€. 이 μ½”λ“œλ₯Ό μ‹€ν–‰μ‹œν‚€λ©΄ μž…λ ₯받은 μˆ˜μ— 따라 ν”Όλ³΄λ‚˜μΉ˜ μˆ˜μ—΄μ˜ ν•΄λ‹Ή 항을 λ°˜ν™˜ν•©λ‹ˆλ‹€. 예λ₯Ό λ“€μ–΄, `fibonacci(10)` ν•˜λ©΄ 55λ₯Ό λ°˜ν™˜ν•©λ‹ˆλ‹€.
296
+
297
+ 이 μ½”λ“œλŠ” μž¬κ·€μ  ν•¨μˆ˜μ΄κΈ° λ•Œλ¬Έμ— λ©”λͺ¨λ¦¬ μ‚¬μš©μ΄ 쀄어듀 수 μžˆμŠ΅λ‹ˆλ‹€. κ·ΈλŸ¬λ‚˜ μž¬κ·€μ  ν•¨μˆ˜λŠ” λ©”λͺ¨λ¦¬ μ‚¬μš©λŸ‰μ΄ λ§Žμ•„μ§ˆ 수 μžˆμŠ΅λ‹ˆλ‹€. 이λ₯Ό 쀄이기 μœ„ν•΄ μ΄ν„°λ ˆμ΄ν‹°λΈŒ ν•¨μˆ˜λ‘œ κ΅¬ν˜„ν•  μˆ˜λ„ μžˆμŠ΅λ‹ˆλ‹€.
298
+ ```python
299
+ a, b = 0, 1
300
+ for i in range(n):
301
+ a, b = b, a + b
302
+ ```
303
+ 이 μ½”λ“œμ—μ„œλŠ” μ΄ν„°λ ˆμ΄ν‹°λΈŒ ν•¨μˆ˜λ‘œ ν”Όλ³΄λ‚˜μΉ˜ μˆ˜μ—΄μ„ κ΅¬ν˜„ν•©λ‹ˆλ‹€. 이 μ½”λ“œλ₯Ό μ‹€ν–‰μ‹œν‚€λ©΄ μž…λ ₯받은 μˆ˜μ— 따라 ν”Όλ³΄λ‚˜μΉ˜ μˆ˜μ—΄μ˜ ν•΄λ‹Ή 항을 λ°˜ν™˜ν•©λ‹ˆλ‹€. 이 μ½”λ“œλŠ” λ©”λͺ¨λ¦¬ μ‚¬μš©λŸ‰μ„ μ€„μž…λ‹ˆλ‹€. λ‹€λ§Œ, 이 μ½”οΏ½οΏ½λŠ” 더 λ³΅μž‘ν•©λ‹ˆλ‹€. 이 μ½”λ“œλ₯Ό 더 κ°„λ‹¨ν•˜κ²Œ ν•˜λ €λ©΄ μ΄ν„°λ ˆμ΄ν‹°λΈŒ ν•¨μˆ˜λ₯Ό 더 잘 κ΅¬ν˜„ν•  수 μžˆμŠ΅λ‹ˆλ‹€.
304
+ ```python
305
+ a, b = 0, 1
306
+ while True:
307
+ if n == 1:
308
+ return a
309
+ a, b = b, a + b
310
+ n -= 1
311
+ ```
312
+ 이 μ½”λ“œμ—μ„œλŠ” μž…λ ₯받은 μˆ˜μ— 따라 ν”Όλ³΄λ‚˜μΉ˜ μˆ˜μ—΄μ˜...
313
+
314
+ ### More samples
315
+
316
+ > I used same system prompt, but you could change on your own.
317
+
318
+ ```python
319
+ messages = [
320
+ {"role": "system", "content": "μΉœμ ˆν•œ μ±—λ΄‡μœΌλ‘œμ„œ μƒλŒ€λ°©μ˜ μš”μ²­μ— μ΅œλŒ€ν•œ μžμ„Έν•˜κ³  μΉœμ ˆν•˜κ²Œ λ‹΅ν•˜μž. λͺ¨λ“  λŒ€λ‹΅μ€ ν•œκ΅­μ–΄(Korean)으둜 λŒ€λ‹΅ν•΄μ€˜."},
321
+ {"role": "user", "content": "ν•œκ΅­μ˜ μ œν—Œ ν—Œλ²•μ— λŒ€ν•΄μ„œ μžμ„Ένžˆ μ„€λͺ…ν•΄μ£Όμ„Έμš”."},
322
+ ]
323
+
324
+ μ΄μˆœμ‹  μž₯ꡰ은 μ‘°μ„ μ‹œλŒ€μ˜ 무인으둜, λŒ€ν•œλ―Όκ΅­μ˜ κ΅­κ°€μœ κ³΅μžμΈ μš°μ˜μ •κ³΅ μ΄μˆœμ‹  μž₯ꡰ은 1545λ…„ 9μ›” 28일 경상남도 μ˜λ Ήμ—μ„œ νƒœμ–΄λ‚¬μŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ은 ν†΅μ œμ‚¬ μ‹œμ ˆμ˜ μ™œλž€ λ•Œ μ‘°μ„ κ³Ό λͺ…λ‚˜λΌ μ—°ν•©κ΅°μ˜ λŒ€κ·œλͺ¨ κ΅°λŒ€λ₯Ό 일으켜 λŒ€μ²©μ„ μ„±κ³΅μ μœΌλ‘œ μ΄λŒμ–΄ μ •μœ μž¬λž€κ³Ό μž„μ§„μ™œλž€μ„ 승리둜 이끈 μΈλ¬Όμž…λ‹ˆλ‹€. κ·ΈλŠ” 1592λ…„ μ „λΌμ’Œμˆ˜μ˜κ΄€μ°°μ‚¬κ°€ λ˜μ–΄ μ „λΌμ’Œμˆ˜μ˜μ—μ„œ μ™œμ μ„ 물리쳀으며, 1597λ…„μ—λŠ” μˆ˜μ›κ³Ό ν•œμ–‘ 방어을 μ„±κ³΅μ μœΌλ‘œ μΉ˜λ£Œν–ˆμŠ΅λ‹ˆλ‹€. λ˜ν•œ λͺ…λŸ‰λŒ€μ²©μ—μ„œ μ™œμ κ³Ό κ²©μ „ν•˜μ—¬ μ΄μˆœμ‹  μ΄μˆœμ‹  μž₯ꡰ은 λͺ…λŸ‰λŒ€μ²©μ—μ„œ μ‘°μ„  κ΄€κ΅°μ˜ 승리λ₯Ό μ΄λŒμ—ˆμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ은 의리λ₯Ό 지킀기 μœ„ν•΄ μ „λ¦¬ν’ˆμ„ κ³ μˆ˜ν•˜λŠ” 결단을 λ‚΄λ ΈμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ은 1598λ…„ μ‚¬μ²œμ„± μ „νˆ¬μ—μ„œ νŒ¨μ „ν•œ ν›„ μ „μ„Έκ°€ 역전돼 μ „μ„Έκ°€ λΆˆλ¦¬ν•΄μ§€μž, λ‚¨ν•˜ν•˜μ—¬ μ΄μˆœμ‹  μž₯ꡰ은 κ²°κ΅­ 좩무곡 μ΄μˆœμ‹ μ˜ 칭호λ₯Ό λ°›μ•˜μŠ΅λ‹ˆλ‹€. 그의 곡적은 λŒ€ν•œλ―Όκ΅­ μ΄μˆœμ‹  μž₯κ΅° κΈ°λ…κ΄€μœΌλ‘œ λͺ…μ˜ˆλ₯Ό 높이고 μžˆμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯κ΅°λ‹˜μ€ μ„ ν˜„μ˜ 칭호둜 1963λ…„ κ±΄κ΅­ν›ˆμž₯ 졜고 ν›ˆμž₯을 μˆ˜μ—¬λ°›μ•˜μœΌλ©°, λŒ€ν•œλ―Όκ΅­μ˜ ꡭ보 제13호둜 μ§€μ •λμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ은 전섀적인 인물둜 ν•œκ΅­μ˜ μ—­μ‚¬μ—μ„œ 큰 쑱적을 λ‚¨κ²ΌμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ이 μ™œλž€ λ‹Ήμ‹œμ˜ μ „νˆ¬μž₯μ†ŒλŠ” 좩무곡이 신라 μ²œμžμ—κ²Œ λ‚˜λΌλ₯Ό μœ„ν•΄ μ‹Έμš΄ 곳을 μ΄μˆœμ‹  μž₯ꡰ의 λ¬˜κ°€ μžˆμŠ΅λ‹ˆλ‹€. λ‚˜λΌμ˜ κ³ λ‚œμ— 지성 μ΄μˆœμ‹  μž₯κ΅°λ‹˜μ˜ μœ„μ—…κ³Ό 의리λ₯Ό κΈ°λ…ν•˜λŠ” κ³³μž…λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ의 행적은 μ΄μˆœμ‹  μž₯κ΅° 기념관, μ΄μˆœμ‹  곡원 등이 μžˆμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ의 곡적을 κΈ°λ…ν•˜κΈ° μœ„ν•΄ λ‹€μ–‘ν•œ λ¬Έν™”μœ μ‚°κ³Ό 기념물이 μ‘°μ„±λμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ의 정신은 λ‚˜λΌλ₯Ό μœ„ν•΄ μ‹Έμš΄ μœ„λŒ€ν•œ 우리의 μ˜μ›…μž…λ‹ˆλ‹€. 1552λ…„ 12μ›”μ—λŠ” μ΄μˆœμ‹  μž₯ꡰ의 전섀을 μ˜›λ‚  동넀에 λ°°ν–₯, ν˜„μž¬λŠ” 좩무곡 μ΄μˆœμ‹  μž₯κ΅°κ»˜μ„œλŠ” μš°λ¦¬λ‚˜λΌμ˜ 상징적 인물이 λμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ은 μ‘°μ„ μ™•μ‘°μ˜ μ€‘μ‹œλ₯Ό λ°›κ³  μžˆμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ은 μ„ μ‘°μ—κ²Œ λ§Žμ€ λŒ€μ˜λ₯Ό μ΄λ£¨μ—ˆμŠ΅λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ의 곡적을 μ˜€λŠ˜λ‚ μ— μ΄λŒμ–΄ μ£ΌλŠ” μΈλ¬Όμž…λ‹ˆλ‹€. κ·Έλ₯Ό λͺ¨μ‹  것은 μ „κ΅­μ˜ μ‚¬λžŒλ“€μž…λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯κ΅°λ‹˜μ˜ κ³ κ²°ν•œ 정신은 μš°λ¦¬λ‚˜λΌκ°€ μ΄λ£©ν•œ μ„±κ³Όμž…λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ은 λ‚˜λΌλ₯Ό μœ„ν•΄ μ‹Έμš΄ μœ„λŒ€ν•œ μΈλ¬Όμž…λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ은 λŒ€ν•œλ―Όκ΅­μ—μ„œ κ°€μž₯ μœ„λŒ€ν•œ μΈλ¬Όμž…λ‹ˆλ‹€. μ΄μˆœμ‹  μž₯ꡰ의 행적은 μ˜μ›νžˆ κΈ°μ–΅ λ˜κ² μ§€μš”.
325
+ ```
326
+
327
+ ```python
328
+ messages = [
329
+ {"role": "system", "content": "μΉœμ ˆν•œ μ±—λ΄‡μœΌλ‘œμ„œ μƒλŒ€λ°©μ˜ μš”μ²­μ— μ΅œλŒ€ν•œ μžμ„Έν•˜κ³  μΉœμ ˆν•˜κ²Œ λ‹΅ν•˜μž. λͺ¨λ“  λŒ€λ‹΅μ€ ν•œκ΅­μ–΄(Korean)으둜 λŒ€λ‹΅ν•΄μ€˜."},
330
+ {"role": "user", "content": "μ„Έμ’…λŒ€μ™•μ˜ μ§‘ν˜„μ „ λ§₯뢁 던짐 사건에 λŒ€ν•΄μ„œ μ•Œκ³  μžˆμ–΄?"},
331
+ ]
332
+
333
+ μ‚¬κ³Όμ˜ μˆ˜λŸ‰μ„ ν™•μΈν•˜κ² μŠ΅λ‹ˆλ‹€. μ €λŠ” 5개의 사과가 μžˆμœΌμ‹ λ°, κ·Έ 쀑 2개λ₯Ό 이미 λ¨Ήμ—ˆμœΌλ‹ˆ 3개의 사과가 λ‚¨μ•„μžˆμŠ΅λ‹ˆλ‹€! γ…Žγ…Ž. κ³„μ†ν•΄μ„œ 먹을 κ³„νš μ—†μž–μ•„μš”? πŸ˜‰
334
+ ```
335
+
336
+
337
+
338
+ <!-- original-model-card end -->