Please be aware that
<s>
and
</s>
are special tokens used for the beginning of string (BOS) and end of string (EOS), respectively, while [INST] and [/INST] are considered regular strings.
For the "{SYSTEM_PROMPT}" part, We recommend using "あなたは日本語を話す優秀なアシスタントです。回答には必ず日本語で答えてください。また考える過程も出力してください。"
For the "{USER_MESSAGE_1}" part, We recommend using {instruction}\n{input}
The following YAML configuration was used to produce this model:
merge_method:task_arithmeticbase_model:mistralai/Mistral-7B-v0.1models:-model:tokyotech-llm/Swallow-MS-7b-v0.1parameters:weight:-filter:embed_tokensvalue:1.0-value:0dtype:bfloat16tokenizer_source:model:tokyotech-llm/Swallow-MS-7b-v0.1name:Mistral-7B-v0.1-VE-Swallow-MS---merge_method:task_arithmeticbase_model:stabilityai/japanese-stablelm-base-gamma-7bmodels:-model:tokyotech-llm/Swallow-MS-7b-v0.1parameters:weight:-filter:embed_tokensvalue:1.0-value:0dtype:bfloat16tokenizer_source:model:tokyotech-llm/Swallow-MS-7b-v0.1name:japanese-stablelm-base-gamma-7b-VE-Swallow-MS---merge_method:task_arithmeticbase_model:DataPilot/ArrowPro-7B-KillerWhalemodels:-model:tokyotech-llm/Swallow-MS-7b-v0.1parameters:weight:-filter:embed_tokensvalue:1.0-value:0dtype:bfloat16tokenizer_source:model:tokyotech-llm/Swallow-MS-7b-v0.1name:ArrowPro-7B-KillerWhale-VE-Swallow-MS---merge_method:task_arithmeticbase_model:nitky/RP-7b-instructmodels:-model:tokyotech-llm/Swallow-MS-7b-v0.1parameters:weight:-filter:embed_tokensvalue:1.0-value:0dtype:bfloat16tokenizer_source:model:tokyotech-llm/Swallow-MS-7b-v0.1name:RP-7b-instruct-VE-Swallow-MS---merge_method:task_arithmeticbase_model:mistralai/Mistral-7B-Instruct-v0.3models:-model:tokyotech-llm/Swallow-MS-7b-v0.1parameters:weight:-filter:embed_tokensvalue:1.0-value:0dtype:bfloat16tokenizer_source:model:tokyotech-llm/Swallow-MS-7b-v0.1name:Mistral-7B-Instruct-v0.3-VE-Swallow-MS---merge_method:linearmodels:-model:nitky/Oumuamua-7b-baseparameters:weight:1.0-model:tokyotech-llm/Swallow-MS-7b-instruct-v0.1parameters:weight:0.8-model:tokyotech-llm/Swallow-MS-7b-v0.1parameters:weight:-0.8-model:Mistral-7B-Instruct-v0.3-VE-Swallow-MSparameters:weight:0.8-model:Mistral-7B-v0.1-VE-Swallow-MSparameters:weight:-0.8dtype:bfloat16name:Oumuamua-7b-instruct-alpha---merge_method:linearmodels:-model:nitky/Oumuamua-7b-baseparameters:weight:1.0-model:ArrowPro-7B-KillerWhale-VE-Swallow-MS# include Mistral-7B-Instruct-v0.3parameters:weight:0.8-model:japanese-stablelm-base-gamma-7b-VE-Swallow-MSparameters:weight:-0.8dtype:bfloat16name:Oumuamua-7b-instruct-beta---merge_method:linearmodels:-model:nitky/Oumuamua-7b-baseparameters:weight:1.0-model:RP-7b-instruct-VE-Swallow-MSparameters:weight:0.8-model:japanese-stablelm-base-gamma-7b-VE-Swallow-MSparameters:weight:-0.8-model:Mistral-7B-Instruct-v0.3-VE-Swallow-MSparameters:weight:0.8-model:Mistral-7B-v0.1-VE-Swallow-MSparameters:weight:-0.8dtype:bfloat16name:Oumuamua-7b-instruct-gamma---merge_method:model_stockbase_model:nitky/Oumuamua-7b-basemodels:-model:Oumuamua-7b-instruct-alpha-model:Oumuamua-7b-instruct-beta-model:Oumuamua-7b-instruct-gammadtype:bfloat16name:Oumuamua-7b-instruct
Runs of nitky Oumuamua-7b-instruct on huggingface.co
5
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About Oumuamua-7b-instruct huggingface.co Model
Oumuamua-7b-instruct huggingface.co is an AI model on huggingface.co that provides Oumuamua-7b-instruct's model effect (), which can be used instantly with this nitky Oumuamua-7b-instruct model. huggingface.co supports a free trial of the Oumuamua-7b-instruct model, and also provides paid use of the Oumuamua-7b-instruct. Support call Oumuamua-7b-instruct model through api, including Node.js, Python, http.
Oumuamua-7b-instruct huggingface.co is an online trial and call api platform, which integrates Oumuamua-7b-instruct's modeling effects, including api services, and provides a free online trial of Oumuamua-7b-instruct, you can try Oumuamua-7b-instruct online for free by clicking the link below.
nitky Oumuamua-7b-instruct online free url in huggingface.co:
Oumuamua-7b-instruct is an open source model from GitHub that offers a free installation service, and any user can find Oumuamua-7b-instruct on GitHub to install. At the same time, huggingface.co provides the effect of Oumuamua-7b-instruct install, users can directly use Oumuamua-7b-instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Oumuamua-7b-instruct install url in huggingface.co: