metadata
base_model: openchat/openchat-3.5-0106
inference: false
library_name: transformers
license: apache-2.0
model_creator: OpenChat
model_name: Openchat 3.5 0106
model_type: mistral
pipeline_tag: text-generation
quantized_by: Second State Inc.
tags:
- openchat
OpenChat-3.5-0106-GGUF
Original Model
Run with LlamaEdge
LlamaEdge version: v0.2.4
Prompt template
Prompt type:
openchatPrompt string
GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
Run as LlamaEdge service
wasmedge --dir .:. --nn-preload default:GGML:AUTO:openchat-3.5-0106-Q5_K_M.gguf llama-api-server.wasm -p openchat -r '<|end_of_turn|>'Run as LlamaEdge command app
wasmedge --dir .:. --nn-preload default:GGML:AUTO:openchat-3.5-0106-Q5_K_M.gguf llama-chat.wasm -p openchat -r '<|end_of_turn|>'
Quantized GGUF Models
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|---|---|---|---|---|---|
| openchat-3.5-0106.Q2_K.gguf | Q2_K | 2 | 3.08 GB | 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| openchat-3.5-0106.Q3_K_L.gguf | Q3_K_L | 3 | 3.82 GB | 6.32 GB | small, substantial quality loss |
| openchat-3.5-0106.Q3_K_M.gguf | Q3_K_M | 3 | 3.52 GB | 6.02 GB | very small, high quality loss |
| openchat-3.5-0106.Q3_K_S.gguf | Q3_K_S | 3 | 3.16 GB | 5.66 GB | very small, high quality loss |
| openchat-3.5-0106.Q4_0.gguf | Q4_0 | 4 | 4.11 GB | 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| openchat-3.5-0106.Q4_K_M.gguf | Q4_K_M | 4 | 4.37 GB | 6.87 GB | medium, balanced quality - recommended |
| openchat-3.5-0106.Q4_K_S.gguf | Q4_K_S | 4 | 4.14 GB | 6.64 GB | small, greater quality loss |
| openchat-3.5-0106.Q5_0.gguf | Q5_0 | 5 | 5.00 GB | 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| openchat-3.5-0106.Q5_K_M.gguf | Q5_K_M | 5 | 5.13 GB | 7.63 GB | large, very low quality loss - recommended |
| openchat-3.5-0106.Q5_K_S.gguf | Q5_K_S | 5 | 5.00 GB | 7.50 GB | large, low quality loss - recommended |
Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.