Upload README.md with huggingface_hub

README.md

@@ -1,8 +1,6 @@
 ---
-base_model: 01-ai/Yi-Coder-1.5B-Chat
-license: apache-2.0
-pipeline_tag: text-generation
 quantized_by: bartowski
+pipeline_tag: text-generation
 ---
 
 ## Llamacpp imatrix Quantizations of Yi-Coder-1.5B-Chat
@@ -28,7 +26,7 @@ Run them in [LM Studio](https://lmstudio.ai/)
 
 ## What's new:
 
-Fixing tokenizer
+Fix tokenizer
 
 ## Download a file (not the whole branch) from below:
 
@@ -45,13 +43,19 @@ Fixing tokenizer
 | [Yi-Coder-1.5B-Chat-Q4_K_M.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_K_M.gguf) | Q4_K_M | 0.96GB | false | Good quality, default size for must use cases, *recommended*. |
 | [Yi-Coder-1.5B-Chat-Q3_K_XL.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q3_K_XL.gguf) | Q3_K_XL | 0.94GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
 | [Yi-Coder-1.5B-Chat-Q4_K_S.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_K_S.gguf) | Q4_K_S | 0.90GB | false | Slightly lower quality with more space savings, *recommended*. |
-| [Yi-Coder-1.5B-Chat-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_0_4_4.gguf) | Q4_0_4_4 | 0.87GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
 | [Yi-Coder-1.5B-Chat-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_0_8_8.gguf) | Q4_0_8_8 | 0.87GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
 | [Yi-Coder-1.5B-Chat-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_0_4_8.gguf) | Q4_0_4_8 | 0.87GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
+| [Yi-Coder-1.5B-Chat-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_0_4_4.gguf) | Q4_0_4_4 | 0.87GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
 | [Yi-Coder-1.5B-Chat-Q4_0.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_0.gguf) | Q4_0 | 0.87GB | false | Legacy format, generally not worth using over similarly sized formats |
 | [Yi-Coder-1.5B-Chat-IQ4_XS.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-IQ4_XS.gguf) | IQ4_XS | 0.83GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
 | [Yi-Coder-1.5B-Chat-Q3_K_L.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q3_K_L.gguf) | Q3_K_L | 0.83GB | false | Lower quality but usable, good for low RAM availability. |
+| [Yi-Coder-1.5B-Chat-Q3_K_M.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q3_K_M.gguf) | Q3_K_M | 0.79GB | false | Low quality. |
+| [Yi-Coder-1.5B-Chat-Q2_K_L.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q2_K_L.gguf) | Q2_K_L | 0.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
 | [Yi-Coder-1.5B-Chat-IQ3_M.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-IQ3_M.gguf) | IQ3_M | 0.75GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Yi-Coder-1.5B-Chat-Q3_K_S.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q3_K_S.gguf) | Q3_K_S | 0.72GB | false | Low quality, not recommended. |
+| [Yi-Coder-1.5B-Chat-IQ3_XS.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-IQ3_XS.gguf) | IQ3_XS | 0.69GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Yi-Coder-1.5B-Chat-Q2_K.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q2_K.gguf) | Q2_K | 0.63GB | false | Very low quality but surprisingly usable. |
+| [Yi-Coder-1.5B-Chat-IQ2_M.gguf](https://huggingface.co/bartowski/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-IQ2_M.gguf) | IQ2_M | 0.62GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
 
 ## Embed/output weights