Transformers
GGUF
yi
TheBloke commited on
Commit
d1146f3
1 Parent(s): 55468d5

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -10
README.md CHANGED
@@ -7,7 +7,7 @@ license_name: yi-license
7
  model_creator: 01-ai
8
  model_name: Yi 34B
9
  model_type: yi
10
- prompt_template: '{prompt}
11
 
12
  '
13
  quantized_by: TheBloke
@@ -70,13 +70,13 @@ Here is an incomplete list of clients and libraries that are known to support GG
70
  <!-- repositories-available end -->
71
 
72
  <!-- prompt-template start -->
73
- ## Prompt template: None
74
 
75
  ```
76
  Human: {prompt} Assistant:
77
 
78
  ```
79
- Prompt template mentioned in the Yi github repo.
80
  <!-- prompt-template end -->
81
 
82
 
@@ -192,7 +192,7 @@ Windows Command Line users: You can set the environment variable by running `set
192
  Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
193
 
194
  ```shell
195
- ./main -ngl 32 -m yi-34b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
196
  ```
197
 
198
  Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
@@ -295,13 +295,19 @@ And thank you again to a16z for their generous grant.
295
 
296
  The **Yi** series models are large language models trained from scratch by
297
  developers at [01.AI](https://01.ai/). The first public release contains two
298
- bilingual(English/Chinese) base models with the parameter sizes of 6B and 34B.
299
- Both of them are trained with 4K sequence length and can be extended to 32K
300
- during inference time.
 
 
 
301
 
302
  ## News
303
 
304
- - 🎯 **2023/11/02**: The base model of `Yi-6B` and `Yi-34B`.
 
 
 
305
 
306
 
307
  ## Model Performance
@@ -318,8 +324,9 @@ during inference time.
318
  | Aquila-34B | 67.8 | 71.4 | 63.1 | - | - | - | - | - |
319
  | Falcon-180B | 70.4 | 58.0 | 57.8 | 59.0 | 54.0 | 77.3 | 68.8 | 34.0 |
320
  | Yi-6B | 63.2 | 75.5 | 72.0 | 72.2 | 42.8 | 72.3 | 68.7 | 19.8 |
321
- | **Yi-34B** | **76.3** | **83.7** | **81.4** | **82.8** | **54.3** | **80.1** | **76.4** | 37.1 |
322
-
 
323
 
324
  While benchmarking open-source models, we have observed a disparity between the
325
  results generated by our pipeline and those reported in public sources (e.g.
 
7
  model_creator: 01-ai
8
  model_name: Yi 34B
9
  model_type: yi
10
+ prompt_template: 'Human: {prompt} Assistant:
11
 
12
  '
13
  quantized_by: TheBloke
 
70
  <!-- repositories-available end -->
71
 
72
  <!-- prompt-template start -->
73
+ ## Prompt template: Yi
74
 
75
  ```
76
  Human: {prompt} Assistant:
77
 
78
  ```
79
+
80
  <!-- prompt-template end -->
81
 
82
 
 
192
  Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
193
 
194
  ```shell
195
+ ./main -ngl 32 -m yi-34b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Human: {prompt} Assistant:"
196
  ```
197
 
198
  Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
 
295
 
296
  The **Yi** series models are large language models trained from scratch by
297
  developers at [01.AI](https://01.ai/). The first public release contains two
298
+ bilingual(English/Chinese) base models with the parameter sizes of 6B([`Yi-6B`](https://huggingface.co/01-ai/Yi-6B))
299
+ and 34B([`Yi-34B`](https://huggingface.co/01-ai/Yi-34B)). Both of them are trained
300
+ with 4K sequence length and can be extended to 32K during inference time.
301
+ The [`Yi-6B-200K`](https://huggingface.co/01-ai/Yi-6B-200K)
302
+ and [`Yi-34B-200K`](https://huggingface.co/01-ai/Yi-34B-200K) are base model with
303
+ 200K context length.
304
 
305
  ## News
306
 
307
+ - 🎯 **2023/11/06**: The base model of [`Yi-6B-200K`](https://huggingface.co/01-ai/Yi-6B-200K)
308
+ and [`Yi-34B-200K`](https://huggingface.co/01-ai/Yi-34B-200K) with 200K context length.
309
+ - 🎯 **2023/11/02**: The base model of [`Yi-6B`](https://huggingface.co/01-ai/Yi-6B) and
310
+ [`Yi-34B`](https://huggingface.co/01-ai/Yi-34B).
311
 
312
 
313
  ## Model Performance
 
324
  | Aquila-34B | 67.8 | 71.4 | 63.1 | - | - | - | - | - |
325
  | Falcon-180B | 70.4 | 58.0 | 57.8 | 59.0 | 54.0 | 77.3 | 68.8 | 34.0 |
326
  | Yi-6B | 63.2 | 75.5 | 72.0 | 72.2 | 42.8 | 72.3 | 68.7 | 19.8 |
327
+ | Yi-6B-200K | 64.0 | 75.3 | 73.5 | 73.9 | 42.0 | 72.0 | 69.1 | 19.0 |
328
+ | **Yi-34B** | **76.3** | **83.7** | 81.4 | 82.8 | **54.3** | **80.1** | 76.4 | 37.1 |
329
+ | Yi-34B-200K | 76.1 | 83.6 | **81.9** | **83.4** | 52.7 | 79.7 | **76.6** | 36.3 |
330
 
331
  While benchmarking open-source models, we have observed a disparity between the
332
  results generated by our pipeline and those reported in public sources (e.g.