File size: 24,170 Bytes
a68f5dc
 
 
8d824d4
fb970e8
8d824d4
fb970e8
8d824d4
fb970e8
a68f5dc
fb970e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8d824d4
 
 
fb970e8
 
 
 
 
 
 
8d824d4
fb970e8
8d824d4
 
 
 
 
 
fb970e8
e822f1d
fb970e8
e822f1d
cf2561e
 
fb970e8
8d824d4
 
 
 
 
 
e822f1d
 
 
fb970e8
8d824d4
 
 
 
 
 
 
 
fb970e8
e822f1d
fb970e8
8d824d4
fb970e8
8d824d4
 
 
 
 
 
 
 
 
fb970e8
e822f1d
fb970e8
e822f1d
 
8d824d4
fb970e8
 
 
 
 
 
8d824d4
fb970e8
e822f1d
8d824d4
fb970e8
 
 
 
 
 
8d824d4
 
e822f1d
8d824d4
 
 
 
 
 
 
 
 
e822f1d
8d824d4
fb970e8
 
 
 
 
 
 
 
 
8d824d4
 
e822f1d
8d824d4
 
 
 
 
 
 
 
 
 
e822f1d
8d824d4
fb970e8
 
 
 
 
 
 
 
 
 
 
8d824d4
 
 
e822f1d
 
8d824d4
fb970e8
 
 
 
 
 
8d824d4
 
e822f1d
8d824d4
 
 
 
 
 
 
104df2b
8d824d4
e822f1d
 
8d824d4
 
 
 
 
 
 
 
 
e822f1d
 
8d824d4
 
 
 
 
 
 
 
 
e822f1d
 
8d824d4
 
 
 
 
 
 
e822f1d
 
8d824d4
 
 
 
 
e822f1d
8d824d4
 
 
 
 
e822f1d
fb970e8
 
 
 
 
 
 
 
 
 
 
8d824d4
 
fb970e8
 
 
 
8d824d4
 
fb970e8
e822f1d
fb970e8
 
 
 
 
8d824d4
fb970e8
e822f1d
fb970e8
 
8d824d4
 
 
fb970e8
 
8d824d4
 
fb970e8
 
e822f1d
fb970e8
e822f1d
fb970e8
 
8d824d4
 
 
 
e822f1d
 
 
 
 
 
 
 
 
 
 
8d824d4
 
fb970e8
 
e822f1d
fb970e8
 
8d824d4
fb970e8
8d824d4
fb970e8
 
 
 
e822f1d
fb970e8
e822f1d
fb970e8
8d824d4
 
 
 
 
 
 
 
fb970e8
e822f1d
fb970e8
8d824d4
 
 
fb970e8
 
e822f1d
fb970e8
e822f1d
 
 
 
fb970e8
e822f1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
---
license: other
license_name: orion
license_link: https://huggingface.co/OrionStarAI/Orion-14B-Chat/blob/main/ModelsCommunityLicenseAgreement
widget:
  - text: "Hi!"
    output:
      text: "Hello! How can I help you today?"
pipeline_tag: text-generation
---

<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
![](./assets/imgs/orion_start.PNG)

<div align="center">
<h1>
  Orion-14B
</h1>
</div>

<div align="center">


<h4 align="center">
    <p>
        <b>🌐English</b> |
        <a href="https://huggingface.co/OrionStarAI/Orion-14B-Chat/blob/main/README_cn.md">🇨🇳中文</a><br><br>
        🤗 <a href="https://huggingface.co/OrionStarAI" target="_blank">HuggingFace Mainpage</a> | 🤖 <a href="https://modelscope.cn/organization/OrionStarAI" target="_blank">ModelScope Mainpage</a><br>🎬 <a href="https://huggingface.co/spaces/OrionStarAI/Orion-14B-App-Demo" target="_blank">HuggingFace Demo</a> | 🎫 <a href="https://modelscope.cn/studios/OrionStarAI/Orion-14B-App-Demo/summary" target="_blank">ModelScope Demo</a>
    <p>
</h4>

</div>



# Table of Contents

- [📖 Model Introduction](#model-introduction)
- [🔗 Model Download](#model-download)
- [🔖 Model Benchmark](#model-benchmark)
- [📊 Model Inference](#model-inference)
- [🥇 Company Introduction](#company-introduction)
- [📜 Declarations & License](#declarations-license)

# 1. Model Introduction

- Orion-14B-Chat is fine-tuned from Orion-14B-Base using a high-quality corpus of approximately 850,000 entries (only sft), and it also supports Chinese, English, Japanese, and Korean. It performs exceptionally well on the MT-Bench and AlignBench evaluation sets, significantly surpassing other models of the same parameter scale in multiple metrics. For details, please refer to [tech report](https://github.com/OrionStarAI/Orion/blob/master/doc/Orion14B_v3.pdf).

- The 850,000 fine-tuning corpus comprises two parts: approximately 220,000 manually curated high-quality datasets and 630,000 entries selected and semantically deduplicated from open-source data through model filtering. Among these, the Japanese and Korean data, totaling 70,000 entries, have only undergone basic cleaning and deduplication.

- The Orion-14B series models exhibit the following features:
  - Among models with 20B-parameter scale level, Orion-14B-Base model shows outstanding performance in comprehensive evaluations.
  - Strong multilingual capabilities, significantly outperforming in Japanese and Korean testsets.
  - The fine-tuned models demonstrate strong adaptability, excelling in human-annotated blind tests.
  - The long-chat version supports extremely long texts, extending up to 200K tokens.
  - The quantized versions reduce model size by 70%, improve inference speed by 30%, with performance loss less than 1%.
 <div align="center">
  <img src="./assets/imgs/model_cap_en.png" alt="model_cap_en" width="50%" />
</div>

- Orion-14B series models including:
  - **Orion-14B-Base:**  A multilingual large language foundational model with 14 billion parameters, pretrained on a diverse dataset of 2.5 trillion tokens.
  - **Orion-14B-Chat:**  A chat-model fine-tuned on a high-quality corpus aims to provide an excellence interactive experience for users in the large model community.
  - **Orion-14B-LongChat:**  This model is optimized for long context lengths more than 200k tokens and demonstrates performance comparable to proprietary models on long context evaluation sets.
  - **Orion-14B-Chat-RAG:**  A chat-model fine-tuned on a custom retrieval augmented generation dataset, achieving superior performance in retrieval augmented generation tasks.
  - **Orion-14B-Chat-Plugin:**  A chat-model specifically tailored for plugin and function calling tasks, ideal for agent-related scenarios where the LLM acts as a plugin and function call system.
  - **Orion-14B-Base-Int4:**  A quantized base model utilizing 4-bit integer weights. It significantly reduces the model size by 70% and increases the inference speed by 30% while incurring a minimal performance loss of only 1%.
  - **Orion-14B-Chat-Int4:**  A quantized chat model utilizing 4-bit integer weights.

# 2. Model Download

Model release and download links are provided in the table below:

| Model Name              | HuggingFace Download Links                                                        | ModelScope Download Links                                                                       |
|-------------------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
| ⚾Orion-14B-Base        | [Orion-14B-Base](https://huggingface.co/OrionStarAI/Orion-14B-Base)               | [Orion-14B-Base](https://modelscope.cn/models/OrionStarAI/Orion-14B-Base/summary)               |
| 😛Orion-14B-Chat        | [Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat)               | [Orion-14B-Chat](https://modelscope.cn/models/OrionStarAI/Orion-14B-Chat/summary)               |
| 📃Orion-14B-LongChat    | [Orion-14B-LongChat](https://huggingface.co/OrionStarAI/Orion-14B-LongChat)       | [Orion-14B-LongChat](https://modelscope.cn/models/OrionStarAI/Orion-14B-LongChat/summary)       |
| 🔎Orion-14B-Chat-RAG    | [Orion-14B-Chat-RAG](https://huggingface.co/OrionStarAI/Orion-14B-Chat-RAG)       | [Orion-14B-Chat-RAG](https://modelscope.cn/models/OrionStarAI/Orion-14B-Chat-RAG/summary)       |
| 🔌Orion-14B-Chat-Plugin | [Orion-14B-Chat-Plugin](https://huggingface.co/OrionStarAI/Orion-14B-Chat-Plugin) | [Orion-14B-Chat-Plugin](https://modelscope.cn/models/OrionStarAI/Orion-14B-Chat-Plugin/summary) |
| 💼Orion-14B-Base-Int4   | [Orion-14B-Base-Int4](https://huggingface.co/OrionStarAI/Orion-14B-Base-Int4)     | [Orion-14B-Base-Int4](https://modelscope.cn/models/OrionStarAI/Orion-14B-Base-Int4/summary)     |
| 📦Orion-14B-Chat-Int4   | [Orion-14B-Chat-Int4](https://huggingface.co/OrionStarAI/Orion-14B-Chat-Int4)     | [Orion-14B-Chat-Int4](https://modelscope.cn/models/OrionStarAI/Orion-14B-Chat-Int4/summary)     |

# 3. Model Benchmarks

## 3.1. Base Model Orion-14B-Base Benchmarks
### 3.1.1. LLM evaluation results on examination and professional knowledge
| Model              | C-Eval   | CMMLU    | MMLU     | AGIEval  | Gaokao   | BBH      |
|--------------------|----------|----------|----------|----------|----------|----------|
| LLaMA2-13B         |   41.4   |   38.4   |   55.0   |   30.9   |   18.2   |   45.6   |
| Skywork-13B        |   59.1   |   61.4   |   62.7   |   43.6   |   56.1   |   48.3   |
| Baichuan2-13B      |   59.0   |   61.3   |   59.5   |   37.4   |   45.6   |   49.0   |
| QWEN-14B           |   71.7   |   70.2   |   67.9   |   51.9   | **62.5** |   53.7   |
| InternLM-20B       |   58.8   |   59.0   |   62.1   |   44.6   |   45.5   |   52.5   |
| **Orion-14B-Base** | **72.9** | **70.6** | **69.9** | **54.7** |   62.1   | **56.5** |

### 3.1.2. LLM evaluation results on language understanding and common knowledge
| Model             |RACE-middle|RACE-high |HellaSwag | PIQA     | Lambada  | WSC      |
|--------------------|----------|----------|----------|----------|----------|----------|
| LLaMA 2-13B        |   63.0   |   58.9   |   77.5   |   79.8   |   76.5   |   66.3   |
| Skywork-13B        |   87.6   |   84.1   |   73.7   |   78.3   |   71.8   |   66.3   |
| Baichuan 2-13B     |   68.9   |   67.2   |   70.8   |   78.1   |   74.1   |   66.3   |
| QWEN-14B           |   93.0   |   90.3   | **80.2** |   79.8   |   71.4   |   66.3   |
| InternLM-20B       |   86.4   |   83.3   |   78.1   | **80.3** |   71.8   |   68.3   |
| **Orion-14B-Base** | **93.3** | **91.3** |   78.5   |   79.5   | **78.9** | **70.2** |

### 3.1.3. LLM evaluation results of OpenCompass testsets
| Model | Average  | Examination | Language | Knowledge | Understanding | Reasoning |
|------------------|----------|----------|----------|----------|----------|----------|
| LLaMA 2-13B      |   47.3   |   45.2   |   47.0   |   58.3   |   50.9   |   43.6   |
| Skywork-13B      |   53.6   |   61.1   |   51.3   |   52.7   |   64.5   |   45.2   |
| Baichuan 2-13B   |   49.4   |   51.8   |   47.5   |   48.9   |   58.1   |   44.2   |
| QWEN-14B         |   62.4   |   71.3   |   52.67  |   56.1   |   68.8   |   60.1   |
| InternLM-20B     |   59.4   |   62.5   |   55.0   | **60.1** |   67.3   |   54.9   |
|**Orion-14B-Base**| **64.4** | **71.4** | **55.0** |   60.0   | **71.9** | **61.6** |

### 3.1.4. Comparison of LLM performances on Japanese testsets
| Model             |**Average**|  JCQA    |  JNLI    |  MARC    |  JSQD    |  JQK     |  XLS     |  XWN     |  MGSM    |
|--------------------|----------|----------|----------|----------|----------|----------|----------|----------|----------|
| PLaMo-13B          |   52.3   |   56.7   |   42.8   |   95.8   |   70.6   |   71.0   |   8.70   |   70.5   |   2.40   |
| WebLab-10B         |   50.7   |   66.6   |   53.7   |   82.1   |   62.9   |   56.2   |   10.0   |   72.0   |   2.40   |
| ELYZA-jp-7B        |   48.8   |   71.7   |   25.3   |   86.6   |   70.8   |   64.1   |   2.50   |   62.1   |   7.20   |
| StableLM-jp-7B     |   51.1   |   33.4   |   43.3   | **96.7** |   70.6   |   78.1   |   10.7   |   72.8   |   2.80   |
| LLaMA 2-13B        |   46.3   |   75.0   |   47.6   |   38.8   |   76.1   |   67.7   |   18.1   |   63.2   |   10.4   |
| Baichuan 2-13B     |   57.1   |   73.7   |   31.3   |   91.6   |   80.5   |   63.3   |   18.6   |   72.2   |   25.2   |
| QWEN-14B           |   65.8   |   85.9   |   60.7   |   97.0   |   83.3   |   71.8   |   18.8   |   70.6   |   38.0   |
| Yi-34B             |   67.1   |   83.8   |   61.2   |   95.2   | **86.1** |   78.5   | **27.2** |   69.2   |   35.2   |
| **Orion-14B-Base** | **69.1** | **88.2** | **75.8** |   94.1   |   75.7   | **85.1** |   17.3   | **78.8** | **38.0** |

### 3.1.5. Comparison of LLM performances on Korean testsets. n = 0 and n = 5 stand for n-shot prompts used in the evaluation
|Model      | **Average**<br>n=0&nbsp;&nbsp;n=5 | HellaSwag<br>n=0&nbsp;&nbsp;n=5 | COPA<br> n=0&nbsp;&nbsp;n=5 | BooIQ<br>n=0&nbsp;&nbsp;n=5 | SentiNeg<br>n=0&nbsp;&nbsp;n=5|
|------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| KoGPT            |  53.0   &nbsp;&nbsp;   70.1  |  55.9   &nbsp;&nbsp;   58.3  |  73.5   &nbsp;&nbsp;   72.9  |  45.1   &nbsp;&nbsp;   59.8  |  37.5   &nbsp;&nbsp;   89.4  |
| Polyglot-ko-13B  |  69.6   &nbsp;&nbsp;   73.7  |**59.5** &nbsp;&nbsp; **63.1**|**79.4** &nbsp;&nbsp; **81.1**|  48.2   &nbsp;&nbsp;   60.4  |  91.2   &nbsp;&nbsp;   90.2  |
| LLaMA 2-13B      |  46.7   &nbsp;&nbsp;   63.7  |  41.3   &nbsp;&nbsp;   44.0  |  59.3   &nbsp;&nbsp;   63.8  |  34.9   &nbsp;&nbsp;   73.8  |  51.5   &nbsp;&nbsp;   73.4  |
| Baichuan 2-13B   |  52.1   &nbsp;&nbsp;   58.7  |  39.2   &nbsp;&nbsp;   39.6  |  60.6   &nbsp;&nbsp;   60.6  |  58.4   &nbsp;&nbsp;   61.5  |  50.3   &nbsp;&nbsp;   72.9  |
| QWEN-14B         |  53.8   &nbsp;&nbsp;   73.7  |  45.3   &nbsp;&nbsp;   46.8  |  64.9   &nbsp;&nbsp;   68.9  |  33.4   &nbsp;&nbsp;   83.5  |  71.5   &nbsp;&nbsp;   95.7  |
| Yi-34B           |  54.2   &nbsp;&nbsp;   72.1  |  44.6   &nbsp;&nbsp;   44.7  |  58.0   &nbsp;&nbsp;   60.6  |  65.9   &nbsp;&nbsp;   90.2  |  48.3   &nbsp;&nbsp;   92.9  |
|**Orion-14B-Chat**|**74.5** &nbsp;&nbsp; **79.6**|  47.0   &nbsp;&nbsp;   49.6  |  77.7   &nbsp;&nbsp;   79.4  |**81.6** &nbsp;&nbsp; **90.7**|**92.4** &nbsp;&nbsp; **98.7**|

### 3.1.6. Multilingual evaluation
| Model              | Train Lang | Japanese | Korean   | Chinese  |  English |
|--------------------|------------|----------|----------|----------|----------|
| PLaMo-13B          |  En,Jp     |   52.3   |   *      |   *      |   *      |
| Weblab-10B         |  En,Jp     |   50.7   |   *      |   *      |   *      |
| ELYZA-jp-7B        |  En,Jp     |   48.8   |   *      |   *      |   *      |
| StableLM-jp-7B     |  En,Jp     |   51.1   |   *      |   *      |   *      |
| KoGPT-6B           |  En,Ko     |   *      |   70.1   |   *      |   *      |
| Polyglot-ko-13B    |  En,Ko     |   *      |   70.7   |   *      |   *      |
| Baichuan2-13B      |  Multi     |   57.1   |   58.7   |   50.8   |   57.1   |
| Qwen-14B           |  Multi     |   65.8   |   73.7   |   64.5   |   65.4   |
| Llama2-13B         |  Multi     |   46.3   |   63.7   |   41.4   |   55.3   |
| Yi-34B             |  Multi     |   67.1   |   72.2   |   58.7   | **68.8** |
| **Orion-14B-Chat** |  Multi     | **69.1** | **79.5** | **67.9** |   67.3   |


## 3.2. Chat Model Orion-14B-Chat Benchmarks
### 3.2.1. Chat model subjective evaluation of MTBench
| Model        | First-Turn | Second-Turn | **Average** |
|----------------------|----------|----------|----------|
| Baichuan2-13B-Chat   |   7.05   |   6.47   |   6.76   |
| Qwen-14B-Chat        |   7.30   |   6.62   |   6.96   |
| Llama2-13B-Chat      |   7.10   |   6.20   |   6.65   |
| InternLM-20B-Chat    |   7.03   |   5.93   |   6.48   |
| **Orion-14B-Chat**   | **7.68** | **7.07** | **7.37** |
\* use vllm for inference

### 3.2.2. Chat model subjective evaluation of AlignBench
| Model              | Math.  |  Logi. | Basic. | Chi.   | Comp.  | Writ.  | Role.  | Prof.  |**Avg.**|
|--------------------|--------|--------|--------|--------|--------|--------|--------|--------|--------|
| Baichuan2-13B-Chat |  3.76  |  4.07  |  6.22  |  6.05  |  7.11  |  6.97  |  6.75  |  6.43  |  5.25  |
| Qwen-14B-Chat      |**4.91**|**4.71**|**6.90**|  6.36  |  6.74  |  6.64  |  6.59  |  6.56  |**5.72**|
| Llama2-13B-Chat    |  3.05  |  3.79  |  5.43  |  4.40  |  6.76  |  6.63  |  6.99  |  5.65  |  4.70  |
| InternLM-20B-Chat  |  3.39  |  3.92  |  5.96  |  5.50  |**7.18**|  6.19  |  6.49  |  6.22  |  4.96  |
| **Orion-14B-Chat** |  4.00  |  4.24  |  6.18  |**6.57**|  7.16  |**7.36**|**7.16**|**6.99**|  5.51  |
\* use vllm for inference

## 3.3. LongChat Model Orion-14B-LongChat Benchmarks
### 3.3.1. LongChat evaluation of LongBench
| Model           | NarrativeQA|MultiFieldQA-en|MultiFieldQA-zh| DuReader  | QMSum     | VCSUM     | TREC      | TriviaQA  | LSHT      |RepoBench-P|
|--------------------------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|
| GPT-3.5-Turbo-16k        | **23.60** | **52.30** | **61.20** |   28.70   |   23.40   | **16.00** |   68.00   | **91.40** |   29.20   |   53.60   |
| LongChat-v1.5-7B-32k     |   16.90   |   41.40   |   29.10   |   19.50   |   22.70   |    9.90   |   63.50   |   82.30   |   23.20   |   55.30   |
| Vicuna-v1.5-7B-16k       |   19.40   |   38.50   |   43.00   |   19.30   |   22.80   |   15.10   |   71.50   |   86.20   |   28.80   |   43.50   |
| Yi-6B-200K               |   14.11   |   36.74   |   22.68   |   14.01   |   20.44   |    8.08   |   72.00   |   86.61   |   38.00   | **63.29** |
| Orion-14B-LongChat       |   19.47   |   48.11   |   55.84   | **37.02** | **24.87** |   15.44   | **77.00** |   89.12   | **45.50** |   54.31   |


## 3.4. Chat RAG Model Benchmarks
### 3.4.1. LLM evaluation results of self-built RAG testsets
|Model|Effectiveness of Response(Keyword)|*Effectiveness of Response(subjective evaluation)|Quoting Ability|Fallback Ability|*AutoQA|*Data Extraction|
|---------------------|------|------|------|------|------|------|
| Baichuan2-13B-Chat  |  85  |  76  |  1   |  0   |  69  |  51  |
| Qwen-14B-Chat       |  79  |  77  |  75  |  47  |  68  |  72  |
| Qwen-72B-Chat(Int4) |  87  |  89  |  90  |  32  |  67  |  76  |
| GPT-4               |  91  |  94  |  96  |  95  |  75  |  86  |
| Orion-14B-Chat-RAG  |  86  |  87  |  91  |  97  |  73  |  71  |
 \* means manual assessment

## 3.5. Chat Plugin Model Orion-14B-Chat-Plugin Benchmarks
### 3.5.1. LLM evaluation results of self-built plugin testsets
|Model |Intent Recognition with Full Params |Intent Recognition with Missing Params |Non-Plugin Invocation Recognition |
|-----------------------|--------|-----------|--------|
| Baichuan2-13B-Chat    |   25   |   0       |   0    |
| Qwen-14B-Chat         |   55   |   0       |   50   |
| GPT-4                 | **95** |   52.38   |   70   |
| Orion-14B-Chat-Plugin |  92.5  | **60.32** | **90** |

## 3.6. Quantized Model Orion-14B-Base-Int4 Benchmarks
### 3.6.1. Comparison of before and after quantization
|Model |Size(GB)|Inference Speed(tokens/s)|C-Eval|CMMLU|MMLU|RACE|HellaSwag|
|-------------------------|-------|-----|------|------|------|------|------|
| OrionStar-14B-Base      |  28.0 | 135 | 72.8 | 70.6 | 70.0 | 93.3 | 78.5 |
| OrionStar-14B-Base-Int4 |  8.3  | 178 | 71.8 | 69.8 | 69.2 | 93.1 | 78.0 |

# 4. Model Inference

Model weights, source code, and configuration needed for inference are published on Hugging Face, and the download link
is available in the table at the beginning of this document. We demonstrate various inference methods here, and the
program will automatically download the necessary resources from Hugging Face.

## 4.1. Python Code

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig

tokenizer = AutoTokenizer.from_pretrained("OrionStarAI/Orion-14B", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-14B", device_map="auto",
                                             torch_dtype=torch.bfloat16, trust_remote_code=True)

model.generation_config = GenerationConfig.from_pretrained("OrionStarAI/Orion-14B")
messages = [{"role": "user", "content": "Hello, what is your name? "}]
response = model.chat(tokenizer, messages, streaming=False)
print(response)

```

In the above Python code, the model is loaded with `device_map='auto'` to utilize all available GPUs. To specify the
device, you can use something like `export CUDA_VISIBLE_DEVICES=0,1` (using GPUs 0 and 1).

## 4.2. Command Line Tool

```shell
CUDA_VISIBLE_DEVICES=0 python cli_demo.py
```

This command-line tool is designed for chat scenarios, and thus, it does not support calling the base model.

## 4.3. Direct Script Inference

```shell

# base model
CUDA_VISIBLE_DEVICES=0 python demo/text_generation_base.py --model OrionStarAI/Orion-14B --tokenizer OrionStarAI/Orion-14B --prompt hello

# chat model
CUDA_VISIBLE_DEVICES=0 python demo/text_generation.py --model OrionStarAI/Orion-14B-Chat --tokenizer OrionStarAI/Orion-14B-Chat --prompt hi

```

## 4.4 Example Output

### 4.4.1. Casual Chat

`````
User: Hello
Orion-14B: Hello! How can I help you today? If you have any questions or need assistance, feel free to ask.
User: What functions do you have?
Orion-14B: As an AI language model, I have a wide range of functions and capabilities, including but not limited to:
  Answering general knowledge questions: I can provide information on various topics such as history, science, geography, and more.
  Providing definitions and explanations: I can explain complex concepts and provide definitions for words and phrases.
  Assisting with tasks: I can help with simple tasks like setting reminders, converting units of measurement, and even ordering food from restaurants.
  Generating text: I can write short stories, essays, articles, and other types of content based on prompts given to me.
  Translating languages: I can translate text from one language to another.
  Chatting: I can engage in conversation with users and respond to their queries in a conversational manner.
  Summarizing long texts: I can summarize longer texts like articles, books, and research papers.
  Generating random numbers and names: I can generate random numbers within a specified range and also suggest names based on certain criteria.
  Playing games: I can play simple games like Hangman, Trivia, and more.
  Providing recommendations: I can recommend movies, music, books, and other forms of entertainment based on user preferences.
  These are just some of the many functions that I am capable of performing. If you have a specific task in mind, feel free to ask me about it.
User: Tell me a joke.
Orion-14B: Sure, here's a classic one-liner: Why don't scientists trust atoms? Because they make up everything.
`````

### 4.4.2. Japanese & Korean Chat

`````
User:自己を紹介してください
Orion-14B:こんにちは、私の名前はChatMaxで、OrionStarによって開発されたAIアシスタントです。私はユーザーに正確で、客観的で、有用な回答を提供し、彼らが問題を解決し、情報を取得するのを助けることができます。
User:자기소개를 해주세요.
Orion-14B:안녕하세요, 제 이름은 ChatMax입니다. OrionStar에서 개발한 AI 어시스턴트입니다. 저는 사용자들에게 정확하고 객관적이며 유용한 답변을 제공하여 문제를 해결하고 정보를 얻는 데 도움을 줄 수 있습니다.
`````


# 5. Declarations, License

## 5.1. Declarations

We strongly urge all users not to use the Orion-14B model for any activities that may harm national or social security or violate the law.
Additionally, we request users not to use the Orion-14B model for internet services without proper security review and filing.
We hope all users abide by this principle to ensure that technological development takes place in a regulated and legal environment.
We have done our best to ensure the compliance of the data used in the model training process. However, despite our
significant efforts, unforeseen issues may still arise due to the complexity of the model and data. Therefore, if any
problems arise due to the use of the Orion-14B open-source model, including but not limited to data security
issues, public opinion risks, or any risks and issues arising from the model being misled, abused, disseminated, or
improperly utilized, we will not assume any responsibility.

## 5.2. License

Community use of the Orion-14B series models
- For code, please comply with  [Apache License Version 2.0](./LICENSE)<br>
- For model, please comply with [【Orion-14B Series】 Models Community License Agreement](./ModelsCommunityLicenseAgreement)


# 6. Company Introduction

OrionStar is a leading global service robot solutions company, founded in September 2016. OrionStar is dedicated to
using artificial intelligence technology to create the next generation of revolutionary robots, allowing people to break
free from repetitive physical labor and making human work and life more intelligent and enjoyable. Through technology,
OrionStar aims to make society and the world a better place.

OrionStar possesses fully self-developed end-to-end artificial intelligence technologies, such as voice interaction and
visual navigation. It integrates product development capabilities and technological application capabilities. Based on
the Orion robotic arm platform, it has launched products such as OrionStar AI Robot Greeting, AI Robot Greeting Mini,
Lucki, Coffee Master, and established the open platform OrionOS for Orion robots. Following the philosophy of "Born for
Truly Useful Robots", OrionStar empowers more people through AI technology.

**The core strengths of OrionStar lies in possessing end-to-end AI application capabilities,** including big data preprocessing, large model pretraining, fine-tuning, prompt engineering, agent, etc.  With comprehensive end-to-end model training capabilities, including systematic data processing workflows and the parallel model training capability of hundreds of GPUs, it has been successfully applied in various industry scenarios such as government affairs, cloud services, international e-commerce, and fast-moving consumer goods.

Companies with demands for deploying large-scale model applications are welcome to contact us.
**Enquiry Hotline: 400-898-7779**<br>
**E-mail: [email protected]**

<div align="center">
  <img src="./assets/imgs/wechat_group.jpg" alt="wechat" width="40%" />
</div>