Upload README.md with huggingface_hub

README.md

@@ -1,38 +1,25 @@
+
 ---
-license: gemma
-library_name: transformers
-pipeline_tag: text-generation
-extra_gated_heading: Access Gemma on Hugging Face
-extra_gated_prompt: >-
-  To access Gemma on Hugging Face, you’re required to review and agree to
-  Google’s usage license. To do this, please ensure you’re logged in to Hugging
-  Face and click below. Requests are processed immediately.
-extra_gated_button_content: Acknowledge license
-tags:
-- conversational
 quantized_by: bartowski
-base_model: google/gemma-2-9b-it
+pipeline_tag: text-generation
 ---
 
 ## Llamacpp imatrix Quantizations of gemma-2-9b-it
 
-Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3278">b3278</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/b3389">b3389</a> for quantization.
 
 Original model: https://huggingface.co/google/gemma-2-9b-it
 
 All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
 
-## What's new
-
-- June 31 2024: Contains latest tokenizer fixes, which addressed a few oddities from the original fix, should be closest to correct performance yet. Also has metadata for SWA and logit softcapping. 
-- July 3 2024: Updated the experimental quants to newer method, Q8 for embed/output, yields higher quality at much lower size than f16 (left Q8_0_L since Q8_0 is already Q8 embed/output)
-
 ## Prompt format
 
 ```
-<start_of_turn>user
+<bos><start_of_turn>user
 {prompt}<end_of_turn>
 <start_of_turn>model
+<end_of_turn>
+<start_of_turn>model
 
 ```
 
@@ -40,31 +27,28 @@ Note that this model does not support a System prompt.
 
 ## Download a file (not the whole branch) from below:
 
-| Filename | Quant type | File Size | Description |
-| -------- | ---------- | --------- | ----------- |
-| [gemma-2-9b-it-Q8_0_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q8_1.gguf) | Q8_0_L | 10.68GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
-| [gemma-2-9b-it-Q8_0.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q8_0.gguf) | Q8_0 | 9.82GB | Extremely high quality, generally unneeded but max available quant. |
-| [gemma-2-9b-it-Q6_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K_L.gguf) | Q6_K_L | 7.81GB | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
-| [gemma-2-9b-it-Q6_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K.gguf) | Q6_K | 7.58GB | Very high quality, near perfect, *recommended*. |
-| [gemma-2-9b-it-Q5_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_L.gguf) | Q5_K_L | 6.87GB | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
-| [gemma-2-9b-it-Q5_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_M.gguf) | Q5_K_M | 6.64GB | High quality, *recommended*. |
-| [gemma-2-9b-it-Q5_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_S.gguf) | Q5_K_S | 6.48GB | High quality, *recommended*. |
-| [gemma-2-9b-it-Q4_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_L.gguf) | Q4_K_L | 5.98GB | Uses Q8_0 for embed and output weights. Good quality, uses about 4.83 bits per weight, *recommended*. |
-| [gemma-2-9b-it-Q4_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_M.gguf) | Q4_K_M | 5.76GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
-| [gemma-2-9b-it-Q4_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_S.gguf) | Q4_K_S | 5.47GB | Slightly lower quality with more space savings, *recommended*. |
-| [gemma-2-9b-it-IQ4_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ4_XS.gguf) | IQ4_XS | 5.18GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
-| [gemma-2-9b-it-Q3_K_XL.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_XL.gguf) | Q3_K_XL | 5.35GB | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
-| [gemma-2-9b-it-Q3_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_L.gguf) | Q3_K_L | 5.13GB | Lower quality but usable, good for low RAM availability. |
-| [gemma-2-9b-it-Q3_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_M.gguf) | Q3_K_M | 4.76GB | Even lower quality. |
-| [gemma-2-9b-it-IQ3_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_M.gguf) | IQ3_M | 4.49GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
-| [gemma-2-9b-it-Q3_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_S.gguf) | Q3_K_S | 4.33GB | Low quality, not recommended. |
-| [gemma-2-9b-it-IQ3_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XS.gguf) | IQ3_XS | 4.14GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
-| [gemma-2-9b-it-IQ3_XXS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XXS.gguf) | IQ3_XXS | 3.79GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
-| [gemma-2-9b-it-Q2_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K_L.gguf) | Q2_K_L | 4.02GB | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
-| [gemma-2-9b-it-Q2_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K.gguf) | Q2_K | 3.80GB | Very low quality but surprisingly usable. |
-| [gemma-2-9b-it-IQ2_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_M.gguf) | IQ2_M | 3.43GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
-| [gemma-2-9b-it-IQ2_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_S.gguf) | IQ2_S | 3.21GB | Very low quality, uses SOTA techniques to be usable. |
-| [gemma-2-9b-it-IQ2_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_XS.gguf) | IQ2_XS | 3.06GB | Very low quality, uses SOTA techniques to be usable. |
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [gemma-2-9b-it-f32.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-f32.gguf) | f32 | 36.97GB | false | Full F32 weights. |
+| [gemma-2-9b-it-Q8_0.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q8_0.gguf) | Q8_0 | 9.83GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [gemma-2-9b-it-Q6_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K_L.gguf) | Q6_K_L | 7.81GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [gemma-2-9b-it-Q6_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K.gguf) | Q6_K | 7.59GB | false | Very high quality, near perfect, *recommended*. |
+| [gemma-2-9b-it-Q5_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_L.gguf) | Q5_K_L | 6.87GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [gemma-2-9b-it-Q5_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_M.gguf) | Q5_K_M | 6.65GB | false | High quality, *recommended*. |
+| [gemma-2-9b-it-Q5_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_S.gguf) | Q5_K_S | 6.48GB | false | High quality, *recommended*. |
+| [gemma-2-9b-it-Q4_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_L.gguf) | Q4_K_L | 5.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [gemma-2-9b-it-Q4_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_M.gguf) | Q4_K_M | 5.76GB | false | Good quality, default size for must use cases, *recommended*. |
+| [gemma-2-9b-it-Q4_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_S.gguf) | Q4_K_S | 5.48GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [gemma-2-9b-it-IQ4_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ4_XS.gguf) | IQ4_XS | 5.18GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [gemma-2-9b-it-Q3_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_L.gguf) | Q3_K_L | 5.13GB | false | Lower quality but usable, good for low RAM availability. |
+| [gemma-2-9b-it-Q3_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_M.gguf) | Q3_K_M | 4.76GB | false | Low quality. |
+| [gemma-2-9b-it-IQ3_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_M.gguf) | IQ3_M | 4.49GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [gemma-2-9b-it-Q3_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_S.gguf) | Q3_K_S | 4.34GB | false | Low quality, not recommended. |
+| [gemma-2-9b-it-IQ3_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XS.gguf) | IQ3_XS | 4.14GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [gemma-2-9b-it-Q2_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K_L.gguf) | Q2_K_L | 4.03GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [gemma-2-9b-it-Q2_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K.gguf) | Q2_K | 3.81GB | false | Very low quality but surprisingly usable. |
+| [gemma-2-9b-it-IQ3_XXS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XXS.gguf) | IQ3_XXS | 3.80GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [gemma-2-9b-it-IQ2_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_M.gguf) | IQ2_M | 3.43GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
 
 ## Credits
 
@@ -119,3 +103,4 @@ These I-quants can also be used on CPU and Apple Metal, but will be slower than
 The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
 
 Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
+