Downloads · 30 days
164
1% of all-time downloads
acsr-v2-yi34b_GGUF
zgce/acsr-v2-yi34b_GGUF
acsr-v2-yi34b_GGUF is a machine learning model from zgce. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
- base model: Yi-34B-Chat - LoRA: Yi-34b-alpaca-cot-lora 支持Alpaca格式对话，效果很差不推荐使用Alpaca指令格式 - LoRA: Yi-34B-Spicyboros-3.1-LoRA 非官方对话数据集 - LoRA: limarpv3-yi-llama-34b-lora 扮演类长回复
All-time downloads
15.5K
Public
Repo size
131 GB
Likes
12
Public
Repo makeup
Click a slice to open those files.
.gguf131 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Nov 26, 2023
- Updated
- Dec 1, 2023
- SHA
- 56607eb0
Model card
From the Hugging Face model README
acsr-y34b-gguf
- base model: Yi-34B-Chat
- LoRA: Yi-34b-alpaca-cot-lora 支持Alpaca格式对话，效果很差不推荐使用Alpaca指令格式
- LoRA: Yi-34B-Spicyboros-3.1-LoRA 非官方对话数据集
- LoRA: limarpv3-yi-llama-34b-lora 扮演类长回复
- Instruction template: ChatML
- Origin max token size: 4096
- 在使用text-generation-webui作后台，SillyTavern做前端时，webui上MaxToken调到8K时SillyTavern的MaxToken要调整到18K，WebUI才不会提前截断
- 上下文长度8K Alpha调到2.5左右时，聊天到6K 以上Token还是不可避免的出现重复的回复和回复质量下降
- 在SillyTavern上要得到Roleplay样式的长回复需做如下调整
- 使用ChatML作为指令格式
- 勾选
用换行符换行序列 - 最后输出序列调整为
### Response (2 paragraphs, engaging, natural, authentic, descriptive, creative): - 自定义停止符调整为
["<|im_end|>用户", "\n### Input"] - 系统提示调整为
Avoid repetition, don't loop. Develop the plot slowly, always stay in character. Describe all actions in full, elaborate, explicit, graphic, and vivid detail. Mention all relevant sensory perceptions.
- License
- mit
- Created
- Nov 26, 2023
- Updated
- Dec 1, 2023