Upload README.md with huggingface_hub

README.md

@@ -1,14 +1,11 @@
 ---
-base_model: rombodawg/Rombos-LLM-V2.5-Qwen-32b
-library_name: transformers
-license: apache-2.0
-pipeline_tag: text-generation
 quantized_by: bartowski
+pipeline_tag: text-generation
 ---
 
-## Llamacpp imatrix Quantizations of Rombos-LLM-V2.5-Qwen-32b
+## Llamacpp imatrix Quantizations of Replete-LLM-V2.5-Qwen-32b
 
-Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3825">b3825</a> for quantization.
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3972">b3972</a> for quantization.
 
 Original model: https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-32b
 
@@ -31,6 +28,7 @@ Run them in [LM Studio](https://lmstudio.ai/)
 | Filename | Quant type | File Size | Split | Description |
 | -------- | ---------- | --------- | ----- | ----------- |
 | [Replete-LLM-V2.5-Qwen-32b-f16.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/tree/main/Replete-LLM-V2.5-Qwen-32b-f16) | f16 | 65.54GB | true | Full F16 weights. |
+| [Replete-LLM-V2.5-Qwen-32b-f16.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/tree/main/Replete-LLM-V2.5-Qwen-32b-f16) | f16 | 65.54GB | true | Full F16 weights. |
 | [Replete-LLM-V2.5-Qwen-32b-Q8_0.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-Q8_0.gguf) | Q8_0 | 34.82GB | false | Extremely high quality, generally unneeded but max available quant. |
 | [Replete-LLM-V2.5-Qwen-32b-Q6_K_L.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-Q6_K_L.gguf) | Q6_K_L | 27.26GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
 | [Replete-LLM-V2.5-Qwen-32b-Q6_K.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-Q6_K.gguf) | Q6_K | 26.89GB | false | Very high quality, near perfect, *recommended*. |
@@ -41,6 +39,7 @@ Run them in [LM Studio](https://lmstudio.ai/)
 | [Replete-LLM-V2.5-Qwen-32b-Q4_K_M.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-Q4_K_M.gguf) | Q4_K_M | 19.85GB | false | Good quality, default size for must use cases, *recommended*. |
 | [Replete-LLM-V2.5-Qwen-32b-Q4_K_S.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-Q4_K_S.gguf) | Q4_K_S | 18.78GB | false | Slightly lower quality with more space savings, *recommended*. |
 | [Replete-LLM-V2.5-Qwen-32b-Q4_0.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-Q4_0.gguf) | Q4_0 | 18.71GB | false | Legacy format, generally not worth using over similarly sized formats |
+| [Replete-LLM-V2.5-Qwen-32b-IQ4_NL.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-IQ4_NL.gguf) | IQ4_NL | 18.68GB | false | Similar to IQ4_XS, but slightly larger. |
 | [Replete-LLM-V2.5-Qwen-32b-Q3_K_XL.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-Q3_K_XL.gguf) | Q3_K_XL | 17.93GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
 | [Replete-LLM-V2.5-Qwen-32b-IQ4_XS.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-IQ4_XS.gguf) | IQ4_XS | 17.69GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
 | [Replete-LLM-V2.5-Qwen-32b-Q3_K_L.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-32b-Q3_K_L.gguf) | Q3_K_L | 17.25GB | false | Lower quality but usable, good for low RAM availability. |