Llamacpp quants

.gitattributes

@@ -33,3 +33,26 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B.imatrix filter=lfs diff=lfs merge=lfs -text

Hermes-2-Pro-Llama-3-8B-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571e40780d87f8fc5f13d788f7c84aabb7ea22903cae08aba28a7ca055ed2219
+size 2162105952

Hermes-2-Pro-Llama-3-8B-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c19a8afcf69dd00207164b00422519955a21c2000a2b25223e5daa70a63047d
+size 2019761760

Hermes-2-Pro-Llama-3-8B-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342d35feab74b2e3472decfe88685d1fb8870b34ed203aae520a6d6742bf0f33
+size 2948428384

Hermes-2-Pro-Llama-3-8B-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0121d6e2694ec210a4bb26164175ff38c45070082a222137b59fa9255934fffc
+size 2758636128

Hermes-2-Pro-Llama-3-8B-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4a5a6a1346f1b04c167e1c0125d53dc8a302eeaefa434f775da9688f73d32a
+size 2605915744

Hermes-2-Pro-Llama-3-8B-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f0d9890c0c149bc8d89063325329fc037ae56efdb5bf1c9245bcc43ffd5841
+size 2399346272

Hermes-2-Pro-Llama-3-8B-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d428634d65de79f9730f3ad52ebef423f4bca1ff0b2ee0f7a3915e8875c733
+size 3784988256

Hermes-2-Pro-Llama-3-8B-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f926c28913d6260c7c25992620d93dabbb7d3709ac0d94551942e5e628ee8efe
+size 3682489952

Hermes-2-Pro-Llama-3-8B-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14017c4359870743e4f1c0b68b283f6ec132244fc7930e1e42d2f3699cd6c731
+size 3518912096

Hermes-2-Pro-Llama-3-8B-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85d7dd841c0a679b672b0ba0a45915a4a03f9f223bb8b6234d562f58afe0fdc
+size 3275059808

Hermes-2-Pro-Llama-3-8B-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7888494b8c2fcdc05960dda6f2957d9ba22870d3566321de668e99048153fc2
+size 4678171232

Hermes-2-Pro-Llama-3-8B-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b33105f10b0b291044f56353a5fd99a106ece55a46e63ccccc78e6c67cff136
+size 4447840864

Hermes-2-Pro-Llama-3-8B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95222f4335c477850a53321cfb40243ccf473e7f041774ecbda40a55b09b384f
+size 3179283040

Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2821c4c8a70c49ee6caf40b9952d3f8d247e30796f1eda520d2d4d89294dc96
+size 4322121312

Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8617a800f820006d3f15b2d5dd253e692af618db1243a122f6fadc1d3374ee9d
+size 4019082848

Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fdaae7c9f003a3af5793616c808a7dc2ae3126ae925d1b0abf46fb43609ff6
+size 3664664160

Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad49fe16b0246e01d13c48efde720ef371829fbc80160c89090ea487eee64d0
+size 4920916576

Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6153ddb5a03efb7eb8500f18de57be11e7736378ef9911c9ca2c147da311cb2
+size 4692851296

Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac46649e5c107e5afcf8a734fbbda50695cb0d2cd1daec8eba6b6df1e5655530
+size 5733186144

Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210121772762938998d241d54ed1ac8b8ba90241ab2a3f3f81fdcfc1f740bcd5
+size 5599492704

Hermes-2-Pro-Llama-3-8B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee31bb0538bbdec64b2c579b81d17d353e3fc8c1d2bdd60f5401493c9e3435a
+size 6596222560

Hermes-2-Pro-Llama-3-8B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d82bd2f02c4be5cb2598a3d960fe51acf91f6d54f8290f0aa8dbe359f9df87
+size 8541050464

Hermes-2-Pro-Llama-3-8B.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6356b40e963b557cb537ca3db4a1f3caaea8b1313c9097f13a7825dca2829f36
+size 4988166

README.md

@@ -0,0 +1,105 @@
+---
+base_model: NousResearch/Meta-Llama-3-8B
+tags:
+- Llama-3
+- instruct
+- finetune
+- chatml
+- DPO
+- RLHF
+- gpt4
+- synthetic data
+- distillation
+- function calling
+- json mode
+- axolotl
+model-index:
+- name: Hermes-2-Pro-Llama-3-8B
+  results: []
+license: apache-2.0
+language:
+- en
+datasets:
+- teknium/OpenHermes-2.5
+widget:
+- example_title: Hermes 2 Pro
+  messages:
+  - role: system
+    content: You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.
+  - role: user
+    content: Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+
+## Llamacpp imatrix Quantizations of Hermes-2-Pro-Llama-3-8B
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2777">b2777</a> for quantization.
+
+Original model: https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B
+
+All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
+
+## Prompt format
+
+
+```
+<|im_start|>system
+You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
+<|im_start|>user
+Hello, who are you?<|im_end|>
+<|im_start|>assistant
+```
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Hermes-2-Pro-Llama-3-8B-Q8_0.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
+| [Hermes-2-Pro-Llama-3-8B-Q6_K.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
+| [Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
+| [Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
+| [Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
+| [Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
+| [Hermes-2-Pro-Llama-3-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
+| [Hermes-2-Pro-Llama-3-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
+| [Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
+| [Hermes-2-Pro-Llama-3-8B-IQ3_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Hermes-2-Pro-Llama-3-8B-IQ3_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
+| [Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
+| [Hermes-2-Pro-Llama-3-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Hermes-2-Pro-Llama-3-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Hermes-2-Pro-Llama-3-8B-Q2_K.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
+| [Hermes-2-Pro-Llama-3-8B-IQ2_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
+| [Hermes-2-Pro-Llama-3-8B-IQ2_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
+| [Hermes-2-Pro-Llama-3-8B-IQ2_XS.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
+| [Hermes-2-Pro-Llama-3-8B-IQ2_XXS.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
+| [Hermes-2-Pro-Llama-3-8B-IQ1_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
+| [Hermes-2-Pro-Llama-3-8B-IQ1_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
+
+## Which file should I choose?
+
+A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
+
+The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
+
+If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
+
+If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
+
+Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+
+If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
+
+If you want to get more into the weeds, you can check out this extremely useful feature chart:
+
+[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
+
+But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
+
+These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+
+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