Edit model card

AutoCoder-IMat-GGUF

Llama.cpp imatrix quantization of Bin12345/AutoCoder

Original Model: Bin12345/AutoCoder
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3010
IMatrix dataset: here


Files

IMatrix

Status: βœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
AutoCoder.Q8_0.gguf Q8_0 35.43GB βœ… Available βšͺ Static πŸ“¦ No
AutoCoder.Q6_K.gguf Q6_K 27.36GB βœ… Available βšͺ Static πŸ“¦ No
AutoCoder.Q4_K.gguf Q4_K 19.94GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.Q3_K.gguf Q3_K 16.09GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.Q2_K.gguf Q2_K 12.36GB βœ… Available 🟒 IMatrix πŸ“¦ No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
AutoCoder.BF16/* BF16 66.69GB βœ… Available βšͺ Static βœ‚ Yes
AutoCoder.FP16/* F16 66.69GB βœ… Available βšͺ Static βœ‚ Yes
AutoCoder.Q5_K.gguf Q5_K 23.54GB βœ… Available βšͺ Static πŸ“¦ No
AutoCoder.Q5_K_S.gguf Q5_K_S 22.96GB βœ… Available βšͺ Static πŸ“¦ No
AutoCoder.Q4_K_S.gguf Q4_K_S 18.94GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.Q3_K_L.gguf Q3_K_L 17.56GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.Q3_K_S.gguf Q3_K_S 14.42GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.Q2_K_S.gguf Q2_K_S 11.39GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ4_NL.gguf IQ4_NL 18.88GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ4_XS.gguf IQ4_XS 17.86GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ3_M.gguf IQ3_M 15.03GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ3_S.gguf IQ3_S 14.48GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ3_XS.gguf IQ3_XS 13.71GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ3_XXS.gguf IQ3_XXS 12.85GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ2_M.gguf IQ2_M 11.36GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ2_S.gguf IQ2_S 10.48GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ2_XS.gguf IQ2_XS 9.91GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ2_XXS.gguf IQ2_XXS 8.92GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ1_M.gguf IQ1_M 7.82GB βœ… Available 🟒 IMatrix πŸ“¦ No
AutoCoder.IQ1_S.gguf IQ1_S 7.16GB 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/AutoCoder-IMat-GGUF --include "AutoCoder.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/AutoCoder-IMat-GGUF --include "AutoCoder.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Simple chat template

Human: Can you provide ways to eat combinations of bananas and dragonfruits?
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.<|EOT|>
Human: What about solving an 2x + 3 = 7 equation?
Assistant: 

Chat template with system prompt

You are a helpful AI.
Human: Can you provide ways to eat combinations of bananas and dragonfruits?
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.<|EOT|>
Human: What about solving an 2x + 3 = 7 equation?
Assistant: 

Llama.cpp

llama.cpp/main -m AutoCoder.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: AutoCoder.Q8_0)
  3. Run gguf-split --merge AutoCoder.Q8_0/AutoCoder.Q8_0-00001-of-XXXXX.gguf AutoCoder.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!

Downloads last month
1,999
GGUF
Model size
33.3B params
Architecture
llama

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Quantized from

Collection including legraphista/AutoCoder-IMat-GGUF