metadata

base_model: Alibaba-NLP/gte-Qwen2-7B-instruct
license: apache-2.0
model_creator: Alibaba-NLP
model_name: gte-Qwen2-7B-instruct
quantized_by: Second State Inc.

gte-Qwen2-7B-instruct-GGUF

Original Model

Alibaba-NLP/gte-Qwen2-7B-instruct

Run with LlamaEdge

LlamaEdge version: v0.16.8
Prompt template
- Prompt type: embedding
Context size: 128000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:gte-Qwen2-7B-instruct-Q5_K_M.gguf \
  llama-api-server.wasm \
  --model-name gte-Qwen2-7B-instruct \
  --prompt-template embedding \
  --ctx-size 128000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
gte-Qwen2-7B-instruct-Q2_K.gguf	Q2_K	2	3.01 GB	smallest, significant quality loss - not recommended for most purposes
gte-Qwen2-7B-instruct-Q3_K_L.gguf	Q3_K_L	3	4.09 GB	small, substantial quality loss
gte-Qwen2-7B-instruct-Q3_K_M.gguf	Q3_K_M	3	3.81 GB	very small, high quality loss
gte-Qwen2-7B-instruct-Q3_K_S.gguf	Q3_K_S	3	3.49 GB	very small, high quality loss
gte-Qwen2-7B-instruct-Q4_0.gguf	Q4_0	4	4.43 GB	legacy; small, very high quality loss - prefer using Q3_K_M
gte-Qwen2-7B-instruct-Q4_K_M.gguf	Q4_K_M	4	4.68 GB	medium, balanced quality - recommended
gte-Qwen2-7B-instruct-Q4_K_S.gguf	Q4_K_S	4	4.46 GB	small, greater quality loss
gte-Qwen2-7B-instruct-Q5_0.gguf	Q5_0	5	5.31 GB	legacy; medium, balanced quality - prefer using Q4_K_M
gte-Qwen2-7B-instruct-Q5_K_M.gguf	Q5_K_M	5	5.44 GB	large, very low quality loss - recommended
gte-Qwen2-7B-instruct-Q5_K_S.gguf	Q5_K_S	5	5.31 GB	large, low quality loss - recommended
gte-Qwen2-7B-instruct-Q6_K.gguf	Q6_K	6	6.25 GB	very large, extremely low quality loss
gte-Qwen2-7B-instruct-Q8_0.gguf	Q8_0	8	8.10 GB	very large, extremely low quality loss - not recommended
gte-Qwen2-7B-instruct-f16.gguf	f16	16	15.2 GB

Quantized with llama.cpp b4754