metadata

base_model: Qwen/Qwen2-Math-72B-Instruct
license: other
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen2-Math-72B-Instruct/blob/main/LICENSE
model_creator: Qwen
model_name: Qwen2-Math-72B-Instruct
quantized_by: Second State Inc.
language:
  - en
pipeline_tag: text-generation
tags:
  - chat

Qwen2-Math-72B-Instruct-GGUF

Original Model

Qwen/Qwen2-Math-72B-Instruct

Run with LlamaEdge

LlamaEdge version: v0.13.2 and above

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: 32000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2-Math-72B-Instruct-Q5_K_M.gguf \
  llama-api-server.wasm \
  --model-name Qwen2-Math-72B-Instruct \
  --prompt-template chatml \
  --ctx-size 32000

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2-Math-72B-Instruct-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template chatml \
  --ctx-size 32000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Qwen2-Math-72B-Instruct-Q2_K.gguf	Q2_K	2	29.8 GB	smallest, significant quality loss - not recommended for most purposes
Qwen2-Math-72B-Instruct-Q3_K_L.gguf	Q3_K_L	3	39.5 GB	small, substantial quality loss
Qwen2-Math-72B-Instruct-Q3_K_M.gguf	Q3_K_M	3	37.7 GB	very small, high quality loss
Qwen2-Math-72B-Instruct-Q3_K_S.gguf	Q3_K_S	3	34.5 GB	very small, high quality loss
Qwen2-Math-72B-Instruct-Q4_0.gguf	Q4_0	4	41.2 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Qwen2-Math-72B-Instruct-Q4_K_M.gguf	Q4_K_M	4	47.4 GB	medium, balanced quality - recommended
Qwen2-Math-72B-Instruct-Q4_K_S.gguf	Q4_K_S	4	43.9 GB	small, greater quality loss
Qwen2-Math-72B-Instruct-Q5_0-00001-of-00002.gguf	Q5_0	5	30.0 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Qwen2-Math-72B-Instruct-Q5_0-00002-of-00002.gguf	Q5_0	5	20.2 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Qwen2-Math-72B-Instruct-Q5_K_M-00001-of-00002.gguf	Q5_K_M	5	29.9 GB	large, very low quality loss - recommended
Qwen2-Math-72B-Instruct-Q5_K_M-00002-of-00002.gguf	Q5_K_M	5	24.6 GB	large, very low quality loss - recommended
Qwen2-Math-72B-Instruct-Q5_K_S-00001-of-00002.gguf	Q5_K_S	5	29.9 GB	large, low quality loss - recommended
Qwen2-Math-72B-Instruct-Q5_K_S-00002-of-00002.gguf	Q5_K_S	5	21.4 GB	large, low quality loss - recommended
Qwen2-Math-72B-Instruct-Q6_K-00001-of-00003.gguf	Q6_K	6	29.8 GB	very large, extremely low quality loss
Qwen2-Math-72B-Instruct-Q6_K-00002-of-00003.gguf	Q6_K	6	29.8 GB	very large, extremely low quality loss
Qwen2-Math-72B-Instruct-Q6_K-00003-of-00003.gguf	Q6_K	6	4.66 GB	very large, extremely low quality loss
Qwen2-Math-72B-Instruct-Q8_0-00001-of-00003.gguf	Q8_0	8	29.8 GB	very large, extremely low quality loss - not recommended
Qwen2-Math-72B-Instruct-Q8_0-00002-of-00003.gguf	Q8_0	8	29.8 GB	very large, extremely low quality loss - not recommended
Qwen2-Math-72B-Instruct-Q8_0-00003-of-00003.gguf	Q8_0	8	17.6 GB	very large, extremely low quality loss - not recommended
Qwen2-Math-72B-Instruct-f16-00001-of-00005.gguf	f16	16	29.8 GB
Qwen2-Math-72B-Instruct-f16-00002-of-00005.gguf	f16	16	29.7 GB
Qwen2-Math-72B-Instruct-f16-00003-of-00005.gguf	f16	16	29.5 GB
Qwen2-Math-72B-Instruct-f16-00004-of-00005.gguf	f16	16	29.8 GB
Qwen2-Math-72B-Instruct-f16-00005-of-00005.gguf	f16	16	26.6 GB

Quantized with llama.cpp b3499