Hugging Face's logo

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

Text Generation
GGUF
English
Chinese
math
quantized
GGUF
imatrix
quantization
imat
static
conversational
Model card Files Community
internlm2-math-plus-1_8b-IMat-GGUF / README.md
legraphista's picture
legraphista
update: tags
8a83d77 verified
preview code
|
raw
history blame contribute delete
10.2 kB
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: ✅ 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 ✅ Available ⚪ Static 📦 No
internlm2-math-plus-1_8b.Q6_K.gguf Q6_K 1.55GB ✅ Available ⚪ Static 📦 No
internlm2-math-plus-1_8b.Q4_K.gguf Q4_K 1.17GB ✅ Available 🟢 IMatrix 📦 No
internlm2-math-plus-1_8b.Q3_K.gguf Q3_K 964.41MB ✅ Available 🟢 IMatrix 📦 No
internlm2-math-plus-1_8b.Q2_K.gguf Q2_K 771.89MB ✅ Available 🟢 IMatrix 📦 No

All Quants

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