Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF
Llama.cpp imatrix quantization of failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
Original Model: failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3058
IMatrix dataset: here
Files
IMatrix
Status: ✅ Available
Link: here
Common Quants
| Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
|---|---|---|---|---|---|
| Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q8_0/* | Q8_0 | 74.98GB | ✅ Available | ⚪ Static | ✂ Yes |
| Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q6_K/* | Q6_K | 57.89GB | ✅ Available | ⚪ Static | ✂ Yes |
| Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q4_K.gguf | Q4_K | 42.52GB | ✅ Available | 🟢 IMatrix | 📦 No |
| Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q3_K.gguf | Q3_K | 34.27GB | ✅ Available | 🟢 IMatrix | 📦 No |
| Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q2_K.gguf | Q2_K | 26.38GB | ✅ Available | 🟢 IMatrix | 📦 No |
All Quants
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/Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF --include "Meta-Llama-3-70B-Instruct-abliterated-v3.5.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/Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF --include "Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's
Inference
Simple chat template
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
{user_prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{assistant_response}<|eot_id|><|start_header_id|>user<|end_header_id|>
{next_user_prompt}<|eot_id|>
Chat template with system prompt
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{user_prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{assistant_response}<|eot_id|><|start_header_id|>user<|end_header_id|>
{next_user_prompt}<|eot_id|>
Llama.cpp
llama.cpp/main -m Meta-Llama-3-70B-Instruct-abliterated-v3.5.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:
Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q8_0) - Run
gguf-split --merge Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q8_0/Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q8_0-00001-of-XXXXX.gguf Meta-Llama-3-70B-Instruct-abliterated-v3.5.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!
- Downloads last month
- 2,228