metadata

base_model: amazon/MistralLite
inference: false
license: apache-2.0
model_creator: Amazon Web Services
model_name: MistralLite 7B
model_type: mistral
quantized_by: Second State Inc.

MistralLite-7B-GGUF

Original Model

amazon/MistralLite

Run with LlamaEdge

LlamaEdge version: v0.2.8 and above
Prompt template
- Prompt type: mistrallite
- Prompt string
```
<|prompter|>{user_message}</s><|assistant|>{assistant_message}</s>
```
- Reverse prompt: </s>
Context size: 4096

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:MistralLite-Q5_K_M.gguf llama-api-server.wasm -p mistrallite -r '</s>'

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:MistralLite-Q5_K_M.gguf llama-chat.wasm -p mistrallite -r '</s>'

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
MistralLite-Q2_K.gguf	Q2_K	2	2.7 GB	smallest, significant quality loss - not recommended for most purposes
MistralLite-Q3_K_L.gguf	Q3_K_L	3	3.82 GB	small, substantial quality loss
MistralLite-Q3_K_M.gguf	Q3_K_M	3	3.52 GB	very small, high quality loss
MistralLite-Q3_K_S.gguf	Q3_K_S	3	3.16 GB	very small, high quality loss
MistralLite-Q4_0.gguf	Q4_0	4	4.11 GB	legacy; small, very high quality loss - prefer using Q3_K_M
MistralLite-Q4_K_M.gguf	Q4_K_M	4	4.37 GB	medium, balanced quality - recommended
MistralLite-Q4_K_S.gguf	Q4_K_S	4	4.14 GB	small, greater quality loss
MistralLite-Q5_0.gguf	Q5_0	5	5.00 GB	legacy; medium, balanced quality - prefer using Q4_K_M
MistralLite-Q5_K_M.gguf	Q5_K_M	5	5.13 GB	large, very low quality loss - recommended
MistralLite-Q5_K_S.gguf	Q5_K_S	5	5.00 GB	large, low quality loss - recommended
MistralLite-Q6_K.gguf	Q6_K	6	5.94 GB	very large, extremely low quality loss
MistralLite-Q8_0.gguf	Q8_0	8	7.70 GB	very large, extremely low quality loss - not recommended