metadata
base_model: openchat/openchat-3.6-8b-20240522
inference: false
library_name: gguf
license: llama3
pipeline_tag: text-generation
quantized_by: legraphista
tags:
- quantized
- GGUF
- imatrix
- quantization
- imat
- imatrix
- static
openchat-3.6-8b-20240522-IMat-GGUF
Llama.cpp imatrix quantization of openchat/openchat-3.6-8b-20240522
Original Model: openchat/openchat-3.6-8b-20240522
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3006
IMatrix dataset: here
Files
IMatrix
Status: ✅ Available
Link: here
Common Quants
| Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
|---|---|---|---|---|---|
| openchat-3.6-8b-20240522.Q8_0.gguf | Q8_0 | 8.54GB | ✅ Available | ⚪ Static | 📦 No |
| openchat-3.6-8b-20240522.Q6_K.gguf | Q6_K | 6.60GB | ✅ Available | ⚪ Static | 📦 No |
| openchat-3.6-8b-20240522.Q4_K | Q4_K | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.Q3_K | Q3_K | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.Q2_K | Q2_K | - | ⏳ Processing | 🟢 IMatrix | - |
All Quants
| Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
|---|---|---|---|---|---|
| openchat-3.6-8b-20240522.FP16.gguf | F16 | 16.07GB | ✅ Available | ⚪ Static | 📦 No |
| openchat-3.6-8b-20240522.BF16.gguf | BF16 | 16.07GB | ✅ Available | ⚪ Static | 📦 No |
| openchat-3.6-8b-20240522.Q5_K.gguf | Q5_K | 5.73GB | ✅ Available | ⚪ Static | 📦 No |
| openchat-3.6-8b-20240522.Q5_K_S.gguf | Q5_K_S | 5.60GB | ✅ Available | ⚪ Static | 📦 No |
| openchat-3.6-8b-20240522.Q4_K_S | Q4_K_S | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.Q3_K_L | Q3_K_L | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.Q3_K_S | Q3_K_S | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.Q2_K_S | Q2_K_S | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ4_NL | IQ4_NL | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ4_XS | IQ4_XS | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ3_M | IQ3_M | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ3_S | IQ3_S | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ3_XS | IQ3_XS | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ3_XXS | IQ3_XXS | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ2_M | IQ2_M | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ2_S | IQ2_S | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ2_XS | IQ2_XS | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ2_XXS | IQ2_XXS | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ1_M | IQ1_M | - | ⏳ Processing | 🟢 IMatrix | - |
| openchat-3.6-8b-20240522.IQ1_S | IQ1_S | - | ⏳ Processing | 🟢 IMatrix | - |
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/openchat-3.6-8b-20240522-IMat-GGUF --include "openchat-3.6-8b-20240522.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/openchat-3.6-8b-20240522-IMat-GGUF --include "openchat-3.6-8b-20240522.Q8_0/*" --local-dir openchat-3.6-8b-20240522.Q8_0
# see FAQ for merging GGUF's
Inference
Simple chat template
<|begin_of_text|><|start_header_id|>GPT4 Correct User<|end_header_id|>
Can you provide ways to eat combinations of bananas and dragonfruits?<|eot_id|><|start_header_id|>GPT4 Correct Assistant<|end_header_id|>
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_id|><|start_header_id|>GPT4 Correct User<|end_header_id|>
What about solving an 2x + 3 = 7 equation?<|eot_id|>
Chat template with system prompt
<|begin_of_text|><|start_header_id|>System<|end_header_id|>
You are a helpful AI.<|eot_id|><|start_header_id|>GPT4 Correct User<|end_header_id|>
Can you provide ways to eat combinations of bananas and dragonfruits?<|eot_id|><|start_header_id|>GPT4 Correct Assistant<|end_header_id|>
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_id|><|start_header_id|>GPT4 Correct User<|end_header_id|>
What about solving an 2x + 3 = 7 equation?<|eot_id|>
Llama.cpp
llama.cpp/main -m openchat-3.6-8b-20240522.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?
- Make sure you have
gguf-splitavailable- To get hold of
gguf-split, navigate to https://github.com/ggerganov/llama.cpp/releases - Download the appropriate zip for your system from the latest release
- Unzip the archive and you should be able to find
gguf-split
- To get hold of
- Locate your GGUF chunks folder (ex:
openchat-3.6-8b-20240522.Q8_0) - Run
gguf-split --merge openchat-3.6-8b-20240522.Q8_0/openchat-3.6-8b-20240522.Q8_0-00001-of-XXXXX.gguf openchat-3.6-8b-20240522.Q8_0.gguf- Make sure to point
gguf-splitto the first chunk of the split.
- Make sure to point
Got a suggestion? Ping me @legraphista!