metadata
base_model: baichuan-inc/Baichuan2-7B-Chat
inference: false
library_name: transformers
license_name: baichuan2-community-license
license_link: >-
https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat/blob/main/Community%20License%20for%20Baichuan2%20Model.pdf
model_creator: Baichuan Intelligent Technology
model_name: Baichuan2 7B Chat
model_type: baichuan
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:
- en
- zh
Baichuan2-7B-Chat-GGUF
Original Model
baichuan-inc/Baichuan2-7B-Chat
Run with LlamaEdge
LlamaEdge version: v0.2.8 and above
Prompt template
Prompt type:
baichuan-2Prompt string
以下内容为人类用户与与一位智能助手的对话。 用户:你好！ 助手:Reverse prompt:
用户:
Context size:
4096Run as LlamaEdge service
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Baichuan2-7B-Chat-Q5_K_M.gguf llama-api-server.wasm -p baichuan-2 -r '用户:'Run as LlamaEdge command app
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Baichuan2-7B-Chat-Q5_K_M.gguf llama-chat.wasm -p baichuan-2 -r '用户:'
Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| Baichuan2-7B-Chat-Q2_K.gguf | Q2_K | 2 | 3.27 GB | smallest, significant quality loss - not recommended for most purposes |
| Baichuan2-7B-Chat-Q3_K_L.gguf | Q3_K_L | 3 | 4.08 GB | small, substantial quality loss |
| Baichuan2-7B-Chat-Q3_K_M.gguf | Q3_K_M | 3 | 3.78 GB | very small, high quality loss |
| Baichuan2-7B-Chat-Q3_K_S.gguf | Q3_K_S | 3 | 3.43 GB | very small, high quality loss |
| Baichuan2-7B-Chat-Q4_0.gguf | Q4_0 | 4 | 4.36 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Baichuan2-7B-Chat-Q4_K_M.gguf | Q4_K_M | 4 | 4.61 GB | medium, balanced quality - recommended |
| Baichuan2-7B-Chat-Q4_K_S.gguf | Q4_K_S | 4 | 4.39 GB | small, greater quality loss |
| Baichuan2-7B-Chat-Q5_0.gguf | Q5_0 | 5 | 5.23 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Baichuan2-7B-Chat-Q5_K_M.gguf | Q5_K_M | 5 | 5.36 GB | large, very low quality loss - recommended |
| Baichuan2-7B-Chat-Q5_K_S.gguf | Q5_K_S | 5 | 5.23 GB | large, low quality loss - recommended |
| Baichuan2-7B-Chat-Q6_K.gguf | Q6_K | 6 | 6.16 GB | very large, extremely low quality loss |
| Baichuan2-7B-Chat-Q8_0.gguf | Q8_0 | 8 | 7.98 GB | very large, extremely low quality loss - not recommended |