utkmst
/

chimera-beta-test2-lora-merged-Q4_K_M-GGUF

instruction-tuned

Model card Files Files and versions

utkmst commited on Mar 8

Commit

fa43cba

·

verified ·

1 Parent(s): acbad5e

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ language:
 - en
 tags:
 - llama-cpp
-- gguf
 - llama-3.1
 - instruction-tuned
 license: llama3.1
@@ -24,7 +24,7 @@ This is a quantized GGUF version of my fine-tuned model [`utkmst/chimera-beta-te
 ## Architecture
 - **Base Model**: meta-llama/Llama-3.1-8B-Instruct
-- **Size**: 8B parameters
 - **Type**: Decoder-only transformer
 - **Quantization**: Q4_K_M GGUF format (4-bit quantization with K-means clustering)

 - en
 tags:
 - llama-cpp
+- ggufa
 - llama-3.1
 - instruction-tuned
 license: llama3.1
 ## Architecture
 - **Base Model**: meta-llama/Llama-3.1-8B-Instruct
+- **Size**: 8.03B parameters
 - **Type**: Decoder-only transformer
 - **Quantization**: Q4_K_M GGUF format (4-bit quantization with K-means clustering)