metadata

license: other
pipeline_tag: text-generation
base_model: internlm/internlm2_5-7b-chat
model_creator: InternLM
model_name: internlm2_5-7b-chat
quantized_by: Second State Inc.

internlm2_5-7b-chat-GGUF

Original Model

internlm/internlm2_5-7b-chat

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: 32000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:internlm2_5-7b-chat-Q5_K_M.gguf \
  llama-api-server.wasm \
  --prompt-template chatml \
  --ctx-size 32000 \
  --model-name internlm2_5-7b-chat

Run as LlamaEdge command app

wasmedge --dir .:. \
  --nn-preload default:GGML:AUTO:internlm2_5-7b-chat-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template chatml \
  --ctx-size 32000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
internlm2_5-7b-chat-Q2_K.gguf	Q2_K	2	3.01 GB	smallest, significant quality loss - not recommended for most purposes
internlm2_5-7b-chat-Q3_K_L.gguf	Q3_K_L	3	4.13 GB	small, substantial quality loss
internlm2_5-7b-chat-Q3_K_M.gguf	Q3_K_M	3	3.83 GB	very small, high quality loss
internlm2_5-7b-chat-Q3_K_S.gguf	Q3_K_S	3	3.48 GB	very small, high quality loss
internlm2_5-7b-chat-Q4_0.gguf	Q4_0	4	4.45 GB	legacy; small, very high quality loss - prefer using Q3_K_M
internlm2_5-7b-chat-Q4_K_M.gguf	Q4_K_M	4	4.71 GB	medium, balanced quality - recommended
internlm2_5-7b-chat-Q4_K_S.gguf	Q4_K_S	4	4.48 GB	small, greater quality loss
internlm2_5-7b-chat-Q5_0.gguf	Q5_0	5	5.37 GB	legacy; medium, balanced quality - prefer using Q4_K_M
internlm2_5-7b-chat-Q5_K_M.gguf	Q5_K_M	5	5.51 GB	large, very low quality loss - recommended
internlm2_5-7b-chat-Q5_K_S.gguf	Q5_K_S	5	5.37 GB	large, low quality loss - recommended
internlm2_5-7b-chat-Q6_K.gguf	Q6_K	6	6.35 GB	very large, extremely low quality loss
internlm2_5-7b-chat-Q8_0.gguf	Q8_0	8	8.22 GB	very large, extremely low quality loss - not recommended
internlm2_5-7b-chat-f16.gguf	f16	16	15.5 GB

Quantized with llama.cpp b3361