second-state/Yi-1.5-9B-Chat-16K-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
master
Yi-1.5-9B-Chat-16K-GGUF/README.md
ai-modelscope 670dcf5c6b Update README.md with license information (#1) 
- Update README.md with license information (22f8e64fa95921df1603b2482a486dc4292ddc4f)

Co-authored-by: Chen_01AI <Chen-01AI@users.noreply.huggingface.co>
2024-10-28 15:40:35 +08:00

4.3 KiB
Raw Permalink Blame History

base_model, inference, model_creator, model_name, model_type, pipeline_tag, quantized_by, license
base_model inference model_creator model_name model_type pipeline_tag quantized_by license
01-ai/Yi-1.5-9B-Chat-16K false 01-ai Yi-1.5-9B-Chat-16 yi text-generation Second State Inc. apache-2.0

Yi-1.5-9B-Chat-16K-GGUF

Original Model

01-ai/Yi-1.5-9B-Chat-16K

Run with LlamaEdge

  • LlamaEdge version: coming soon

  • 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: 16384

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-9B-Chat-16K-Q5_K_M.gguf \
  llama-api-server.wasm \
  --prompt-template chatml \
  --reverse-prompt "<|im_end|>" \
  --ctx-size 16384 \
  --model-name Yi-1.5-9B-Chat-16K

  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-9B-Chat-16K-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template chatml \
  --reverse-prompt "<|im_end|>" \
  --ctx-size 16384

Quantized GGUF Models

Name Quant method Bits Size Use case
Yi-1.5-9B-Chat-16K-Q2_K.gguf Q2_K 2 3.35 GB smallest, significant quality loss - not recommended for most purposes
Yi-1.5-9B-Chat-16K-Q3_K_L.gguf Q3_K_L 3 4.69 GB small, substantial quality loss
Yi-1.5-9B-Chat-16K-Q3_K_M.gguf Q3_K_M 3 4.32 GB very small, high quality loss
Yi-1.5-9B-Chat-16K-Q3_K_S.gguf Q3_K_S 3 3.9 GB very small, high quality loss
Yi-1.5-9B-Chat-16K-Q4_0.gguf Q4_0 4 5.04 GB legacy; small, very high quality loss - prefer using Q3_K_M
Yi-1.5-9B-Chat-16K-Q4_K_M.gguf Q4_K_M 4 5.33 GB medium, balanced quality - recommended
Yi-1.5-9B-Chat-16K-Q4_K_S.gguf Q4_K_S 4 5.07 GB small, greater quality loss
Yi-1.5-9B-Chat-16K-Q5_0.gguf Q5_0 5 6.11 GB legacy; medium, balanced quality - prefer using Q4_K_M
Yi-1.5-9B-Chat-16K-Q5_K_M.gguf Q5_K_M 5 6.26 GB large, very low quality loss - recommended
Yi-1.5-9B-Chat-16K-Q5_K_S.gguf Q5_K_S 5 6.11 GB large, low quality loss - recommended
Yi-1.5-9B-Chat-16K-Q6_K.gguf Q6_K 6 7.25 GB very large, extremely low quality loss
Yi-1.5-9B-Chat-16K-Q8_0.gguf Q8_0 8 9.38 GB very large, extremely low quality loss - not recommended
Yi-1.5-9B-Chat-16K-f16.gguf f16 16 17.7 GB

Quantized with llama.cpp b3135