qwp4w3hyb
/

Meta-Llama-3.1-8B-Instruct-iMat-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

qwp4w3hyb commited on Jul 25

Commit

6d0cccb

•

1 Parent(s): 8308026

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 # Quant Infos
 - Requires latest master + [Rope Scaling PR](https://github.com/ggerganov/llama.cpp/pull/8676)
-  - ubergarm explained how to set up your llama.cpp here: https://huggingface.co/qwp4w3hyb/Meta-Llama-3.1-8B-Instruct-iMat-GGUF/discussions/1#66a26b63de4e162dd84c22c5
 - Might not be perfect yet, but seems to mostly work, including 128k context.
 - quants done with an importance matrix for improved quantization loss
 - Quantized ggufs & imatrix from hf bf16, through bf16. `safetensors bf16 -> gguf bf16 -> quant` for *optimal* quant loss.

 # Quant Infos
 - Requires latest master + [Rope Scaling PR](https://github.com/ggerganov/llama.cpp/pull/8676)
+  - [@ubergarm](https://huggingface.co/ubergarm) explained how to set up your llama.cpp [here](https://huggingface.co/qwp4w3hyb/Meta-Llama-3.1-8B-Instruct-iMat-GGUF/discussions/1#66a26b63de4e162dd84c22c5)
 - Might not be perfect yet, but seems to mostly work, including 128k context.
 - quants done with an importance matrix for improved quantization loss
 - Quantized ggufs & imatrix from hf bf16, through bf16. `safetensors bf16 -> gguf bf16 -> quant` for *optimal* quant loss.