apepkuss79's picture
Update README.md
19c7cc6 verified
metadata
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
inference: false
library_name: transformers
license: apache-2.0
model_creator: TinyLlama
model_name: Tinyllama 1.1B Chat v1.0
model_type: tinyllama
pipeline_tag: text-generation
quantized_by: Second State Inc.

TinyLlama-1.1B-Chat-v1.0-GGUF

Original Model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Run with LlamaEdge

  • LlamaEdge version: v0.12.3 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: 2048

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:TinyLlama-1.1B-Chat-v1.0-Q5_K_M.gguf \
      llama-api-server.wasm \
      --prompt-template zephyr \
      --ctx-size 2048 \
      --model-name TinyLlama-1.1B-Chat
    
  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:TinyLlama-1.1B-Chat-v1.0-Q5_K_M.gguf \
      llama-chat.wasm \
      --prompt-template zephyr \
      --ctx-size 2048
    

Quantized GGUF Models

Name Quant method Bits Size Use case
TinyLlama-1.1B-Chat-v1.0-Q2_K.gguf Q2_K 2 482 MB smallest, significant quality loss - not recommended for most purposes
TinyLlama-1.1B-Chat-v1.0-Q3_K_L.gguf Q3_K_L 3 592 MB small, substantial quality loss
TinyLlama-1.1B-Chat-v1.0-Q3_K_M.gguf Q3_K_M 3 550 MB very small, high quality loss
TinyLlama-1.1B-Chat-v1.0-Q3_K_S.gguf Q3_K_S 3 499 MB very small, high quality loss
TinyLlama-1.1B-Chat-v1.0-Q4_0.gguf Q4_0 4 637 MB legacy; small, very high quality loss - prefer using Q3_K_M
TinyLlama-1.1B-Chat-v1.0-Q4_K_M.gguf Q4_K_M 4 668 MB medium, balanced quality - recommended
TinyLlama-1.1B-Chat-v1.0-Q4_K_S.gguf Q4_K_S 4 643 MB small, greater quality loss
TinyLlama-1.1B-Chat-v1.0-Q5_0.gguf Q5_0 5 766 MB legacy; medium, balanced quality - prefer using Q4_K_M
TinyLlama-1.1B-Chat-v1.0-Q5_K_M.gguf Q5_K_M 5 782 MB large, very low quality loss - recommended
TinyLlama-1.1B-Chat-v1.0-Q5_K_S.gguf Q5_K_S 5 766 MB large, low quality loss - recommended
TinyLlama-1.1B-Chat-v1.0-Q6_K.gguf Q6_K 6 903 MB very large, extremely low quality loss
TinyLlama-1.1B-Chat-v1.0-Q8_0.gguf Q8_0 8 1.17 GB very large, extremely low quality loss - not recommended