Yi-34B-Chat-GGUF
Original Model
Run with LlamaEdge
LlamaEdge version: v0.2.15 and above
Prompt template
Prompt type:
chatmlPrompt string
<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistantReverse prompt:
<|im_end|>Run as LlamaEdge service
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-6B-Chat-Q5_K_M.gguf llama-api-server.wasm -p chatml -r '<|im_end|>'
- Run as LlamaEdge command app
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-6B-Chat-Q5_K_M.gguf llama-chat.wasm -p chatml -r '<|im_end|>'
Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| Yi-6B-Chat-Q2_K.gguf | Q2_K | 2 | 2.34 GB | smallest, significant quality loss - not recommended for most purposes |
| Yi-6B-Chat-Q3KL.gguf | Q3KL | 3 | 3.24 GB | small, substantial quality loss |
| Yi-6B-Chat-Q3KM.gguf | Q3KM | 3 | 2.99 GB | very small, high quality loss |
| Yi-6B-Chat-Q3KS.gguf | Q3KS | 3 | 2.71 GB | very small, high quality loss |
| Yi-6B-Chat-Q4_0.gguf | Q4_0 | 4 | 3.48 GB | legacy; small, very high quality loss - prefer using Q3KM |
| Yi-6B-Chat-Q4KM.gguf | Q4KM | 4 | 3.67 GB | medium, balanced quality - recommended |
| Yi-6B-Chat-Q4KS.gguf | Q4KS | 4 | 3.50 GB | small, greater quality loss |
| Yi-6B-Chat-Q5_0.gguf | Q5_0 | 5 | 4.20 GB | legacy; medium, balanced quality - prefer using Q4KM |
| Yi-6B-Chat-Q5KM.gguf | Q5KM | 5 | 4.30 GB | large, very low quality loss - recommended |
| Yi-6B-Chat-Q5KS.gguf | Q5KS | 5 | 4.20 GB | large, low quality loss - recommended |
| Yi-6B-Chat-Q6_K.gguf | Q6_K | 6 | 4.97 GB | very large, extremely low quality loss |
| Yi-6B-Chat-Q8_0.gguf | Q8_0 | 8 | 6.44 GB | very large, extremely low quality loss - not recommended |
评论