metadata

base_model: bespokelabs/Bespoke-Stratos-32B
license: apache-2.0
model_creator: bespokelabs
model_name: Bespoke-Stratos-32B
quantized_by: Second State Inc.
library_name: transformers
language:
  - en

Bespoke-Stratos-32B-GGUF

Original Model

bespokelabs/Bespoke-Stratos-32B

Run with LlamaEdge

LlamaEdge version: v0.16.1

Prompt template

Prompt type: chatml

Prompt string

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Context size: 128000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Bespoke-Stratos-32B-Q5_K_M.gguf \
  llama-api-server.wasm \
  --model-name Bespoke-Stratos-32B \
  --prompt-template chatml \
  --ctx-size 128000

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Bespoke-Stratos-32B-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template chatml \
  --ctx-size 128000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Bespoke-Stratos-32B-Q2_K.gguf	Q2_K	2	12.3 GB	smallest, significant quality loss - not recommended for most purposes
Bespoke-Stratos-32B-Q3_K_L.gguf	Q3_K_L	3	17.2 GB	small, substantial quality loss
Bespoke-Stratos-32B-Q3_K_M.gguf	Q3_K_M	3	15.9 GB	very small, high quality loss
Bespoke-Stratos-32B-Q3_K_S.gguf	Q3_K_S	3	14.4 GB	very small, high quality loss
Bespoke-Stratos-32B-Q4_0.gguf	Q4_0	4	18.6 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Bespoke-Stratos-32B-Q4_K_M.gguf	Q4_K_M	4	19.9 GB	medium, balanced quality - recommended
Bespoke-Stratos-32B-Q4_K_S.gguf	Q4_K_S	4	18.8 GB	small, greater quality loss
Bespoke-Stratos-32B-Q5_0.gguf	Q5_0	5	22.6 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Bespoke-Stratos-32B-Q5_K_M.gguf	Q5_K_M	5	23.3 GB	large, very low quality loss - recommended
Bespoke-Stratos-32B-Q5_K_S.gguf	Q5_K_S	5	22.6 GB	large, low quality loss - recommended
Bespoke-Stratos-32B-Q6_K.gguf	Q6_K	6	26.9 GB	very large, extremely low quality loss
Bespoke-Stratos-32B-Q8_0.gguf	Q8_0	8	34.8 GB	very large, extremely low quality loss - not recommended
Bespoke-Stratos-32B-f16-00001-of-00003.gguf	f16	16	29.8 GB
Bespoke-Stratos-32B-f16-00002-of-00003.gguf	f16	16	29.8 GB
Bespoke-Stratos-32B-f16-00003-of-00003.gguf	f16	16	5.87 GB

Quantized with llama.cpp b4529