legraphista's picture
update: tags
8a83d77 verified
metadata
base_model: internlm/internlm2-math-plus-1_8b
inference: false
language:
  - en
  - zh
library_name: gguf
license: other
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - math
  - quantized
  - GGUF
  - imatrix
  - quantization
  - imat
  - imatrix
  - static

internlm2-math-plus-1_8b-IMat-GGUF

Llama.cpp imatrix quantization of internlm/internlm2-math-plus-1_8b

Original Model: internlm/internlm2-math-plus-1_8b
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3008
IMatrix dataset: here


Files

IMatrix

Status: βœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
internlm2-math-plus-1_8b.Q8_0.gguf Q8_0 2.01GB βœ… Available βšͺ Static πŸ“¦ No
internlm2-math-plus-1_8b.Q6_K.gguf Q6_K 1.55GB βœ… Available βšͺ Static πŸ“¦ No
internlm2-math-plus-1_8b.Q4_K.gguf Q4_K 1.17GB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.Q3_K.gguf Q3_K 964.41MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.Q2_K.gguf Q2_K 771.89MB βœ… Available 🟒 IMatrix πŸ“¦ No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
internlm2-math-plus-1_8b.FP16.gguf F16 3.78GB βœ… Available βšͺ Static πŸ“¦ No
internlm2-math-plus-1_8b.BF16.gguf BF16 3.78GB βœ… Available βšͺ Static πŸ“¦ No
internlm2-math-plus-1_8b.Q5_K.gguf Q5_K 1.36GB βœ… Available βšͺ Static πŸ“¦ No
internlm2-math-plus-1_8b.Q5_K_S.gguf Q5_K_S 1.33GB βœ… Available βšͺ Static πŸ“¦ No
internlm2-math-plus-1_8b.Q4_K_S.gguf Q4_K_S 1.12GB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.Q3_K_L.gguf Q3_K_L 1.03GB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.Q3_K_S.gguf Q3_K_S 888.26MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.Q2_K_S.gguf Q2_K_S 727.45MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ4_NL.gguf IQ4_NL 1.11GB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ4_XS.gguf IQ4_XS 1.06GB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ3_M.gguf IQ3_M 915.00MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ3_S.gguf IQ3_S 888.26MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ3_XS.gguf IQ3_XS 852.87MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ3_XXS.gguf IQ3_XXS 787.59MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ2_M.gguf IQ2_M 719.96MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ2_S.gguf IQ2_S 679.06MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ2_XS.gguf IQ2_XS 635.43MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ2_XXS.gguf IQ2_XXS 591.39MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ1_M.gguf IQ1_M 540.28MB βœ… Available 🟒 IMatrix πŸ“¦ No
internlm2-math-plus-1_8b.IQ1_S.gguf IQ1_S 509.60MB βœ… Available 🟒 IMatrix πŸ“¦ No

Downloading using huggingface-cli

If you do not have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Download the specific file you want:

huggingface-cli download legraphista/internlm2-math-plus-1_8b-IMat-GGUF --include "internlm2-math-plus-1_8b.Q8_0.gguf" --local-dir ./

If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/internlm2-math-plus-1_8b-IMat-GGUF --include "internlm2-math-plus-1_8b.Q8_0/*" --local-dir internlm2-math-plus-1_8b.Q8_0
# see FAQ for merging GGUF's

Inference

Simple chat template

<s><|im_start|>user
Can you provide ways to eat combinations of bananas and dragonfruits?<|im_end|>
<|im_start|>assistant
Sure! Here are some ways to eat bananas and dragonfruits together:
 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey.
 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey.<|im_end|>
<|im_start|>user
What about solving an 2x + 3 = 7 equation?<|im_end|>

Chat template with system prompt

<s><|im_start|>system
You are a helpful AI.<|im_end|>
<|im_start|>user
Can you provide ways to eat combinations of bananas and dragonfruits?<|im_end|>
<|im_start|>assistant
Sure! Here are some ways to eat bananas and dragonfruits together:
 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey.
 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey.<|im_end|>
<|im_start|>user
What about solving an 2x + 3 = 7 equation?<|im_end|>

Llama.cpp

llama.cpp/main -m internlm2-math-plus-1_8b.Q8_0.gguf --color -i -p "prompt here (according to the chat template)"

FAQ

Why is the IMatrix not applied everywhere?

According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).

How do I merge a split GGUF?

  1. Make sure you have gguf-split available
  2. Locate your GGUF chunks folder (ex: internlm2-math-plus-1_8b.Q8_0)
  3. Run gguf-split --merge internlm2-math-plus-1_8b.Q8_0/internlm2-math-plus-1_8b.Q8_0-00001-of-XXXXX.gguf internlm2-math-plus-1_8b.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!