Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,25 @@ 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-Theta-Llama-3-70B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q5_K_L.gguf/Hermes-2-Theta-Llama-3-70B-Q5_K_L-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q5_K_L.gguf/Hermes-2-Theta-Llama-3-70B-Q5_K_L-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q6_K.gguf/Hermes-2-Theta-Llama-3-70B-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q6_K.gguf/Hermes-2-Theta-Llama-3-70B-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q8_0.gguf/Hermes-2-Theta-Llama-3-70B-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B-Q8_0.gguf/Hermes-2-Theta-Llama-3-70B-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Theta-Llama-3-70B.imatrix filter=lfs diff=lfs merge=lfs -text

Hermes-2-Theta-Llama-3-70B-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559cd18cea304f6e12e18e72d6e3e505ef0e3e58baef1767e04748f8b0d7d398
+size 16751195680

Hermes-2-Theta-Llama-3-70B-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d6143f3d38c40ef4c4b1cc03d18c9b3de8e883e4dacf613d0cf06a58eeeb27
+size 24119293472

Hermes-2-Theta-Llama-3-70B-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b5d0b7ddfa7c9fef7c834d7d95a9b3be0468782b11f5e057263bb6054f14ae
+size 21142107680

Hermes-2-Theta-Llama-3-70B-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ed7db18d89415b871d4fed08852239a1683d56ade83ec959a1a2c7c6254a30
+size 19097384480

Hermes-2-Theta-Llama-3-70B-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dad13ee3eaab7b2ec76fd15a1d595007fe1b194e55299d68a5bcd7f03c213e
+size 31937033760

Hermes-2-Theta-Llama-3-70B-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025f12e29fc80665b46225295c106b937d77d0a66bdce2b57fdc2b735685045e
+size 27469493792

Hermes-2-Theta-Llama-3-70B-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c0538925c0b89b3202d41dab385f9ae96a5c79e468951fcad8771b3a182cea
+size 37902661152

Hermes-2-Theta-Llama-3-70B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0691eb031e270d4e69a18c9417828aa7af3caecea278d97357dd9b6f010c8dc4
+size 26375108128

Hermes-2-Theta-Llama-3-70B-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c072b0ce9d71f44845663e11e307b832c9b9081bcbae47777399866c54d54f7
+size 29371168288

Hermes-2-Theta-Llama-3-70B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c63e72557d8ad09868ff5e5cbcde3887a76640fc193e06e30bbdaa41b0b9bf
+size 34267493920

Hermes-2-Theta-Llama-3-70B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905af01bf23fc2157518d31510c7f0426edf604600c55004f539330ab9e1e97f
+size 30912050720

Hermes-2-Theta-Llama-3-70B-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5297b19f1b0f77c2e638468aff8775911d2bb455ed85757325e113b9e45cb39
+size 40029943328

Hermes-2-Theta-Llama-3-70B-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561cd31546bc454ddd62cf201a776cf228a5f72f87ccfbcee0fb3d918938647e
+size 45270201888

Hermes-2-Theta-Llama-3-70B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77cd7638029ec34bb75e60b48dba715dc7bbfdccf4ce428d791697a57952909d
+size 42520393248

Hermes-2-Theta-Llama-3-70B-Q5_K_L.gguf/Hermes-2-Theta-Llama-3-70B-Q5_K_L-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1117825cceee3f224402fc1c1dcb471b06837698375f2c0bd9dd02940da7c4f4
+size 39993594304

Hermes-2-Theta-Llama-3-70B-Q5_K_L.gguf/Hermes-2-Theta-Llama-3-70B-Q5_K_L-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e86b0e7c6a295b603935d64e9840292547613f928c52b009d8572b7e6fca4b4
+size 12574696736

Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829d7d36a29bbf7e65331edcc1dede8c41c6b0ebaa1dfc4ca5b4fbb1fc619f78
+size 49949816352

Hermes-2-Theta-Llama-3-70B-Q6_K.gguf/Hermes-2-Theta-Llama-3-70B-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8b0683baa52e83651b81c9adf57fe03a30b3c9ee1f69c3e1e3ff0598d44d35
+size 39862698528

Hermes-2-Theta-Llama-3-70B-Q6_K.gguf/Hermes-2-Theta-Llama-3-70B-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5d00a9a703bca9c383128ea1d31a2a778be2ed524f532eb10188cdcdc33460
+size 18025444544

Hermes-2-Theta-Llama-3-70B-Q8_0.gguf/Hermes-2-Theta-Llama-3-70B-Q8_0-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057c3cda953db520b4a72be0875e0ed4b954935686c03f6ad4ef8f90db70f715
+size 39808935648

Hermes-2-Theta-Llama-3-70B-Q8_0.gguf/Hermes-2-Theta-Llama-3-70B-Q8_0-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe090102f7f3b880e14f0b86e62fb6a07efd4de0fced5b3b16cfb2087565ed6
+size 35166113792

Hermes-2-Theta-Llama-3-70B.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dad2529e810901674a280a8703982a6a132b47d81f7cc807463284b2c7c0255
+size 24922299

README.md

@@ -0,0 +1,101 @@
+---
+license: llama3
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- distillation
+- synthetic data
+- function calling
+- structured outputs
+- json mode
+quantized_by: bartowski
+---
+
+## Llamacpp imatrix Quantizations of Hermes-2-Theta-Llama-3-70B
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3166">b3166</a> for quantization.
+
+Original model: https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-70B
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
+
+## Prompt format
+
+```
+<|begin_of_text|><|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Hermes-2-Theta-Llama-3-70B-Q8_0.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/tree/main/Hermes-2-Theta-Llama-3-70B-Q8_0.gguf) | Q8_0 | 74.97GB | Extremely high quality, generally unneeded but max available quant. |
+| [Hermes-2-Theta-Llama-3-70B-Q6_K.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/tree/main/Hermes-2-Theta-Llama-3-70B-Q6_K.gguf) | Q6_K | 57.88GB | Very high quality, near perfect, *recommended*. |
+| [Hermes-2-Theta-Llama-3-70B-Q5_K_L.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/tree/main/Hermes-2-Theta-Llama-3-70B-Q5_K_L.gguf) | Q5_K_L | 52.56GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
+| [Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf) | Q5_K_M | 49.94GB | High quality, *recommended*. |
+| [Hermes-2-Theta-Llama-3-70B-Q4_K_L.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-Q4_K_L.gguf) | Q4_K_L | 45.27GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
+| [Hermes-2-Theta-Llama-3-70B-Q4_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-Q4_K_M.gguf) | Q4_K_M | 42.52GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
+| [Hermes-2-Theta-Llama-3-70B-IQ4_XS.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-IQ4_XS.gguf) | IQ4_XS | 37.90GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Hermes-2-Theta-Llama-3-70B-Q3_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-Q3_K_M.gguf) | Q3_K_M | 34.26GB | Even lower quality. |
+| [Hermes-2-Theta-Llama-3-70B-IQ3_M.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-IQ3_M.gguf) | IQ3_M | 31.93GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Hermes-2-Theta-Llama-3-70B-Q3_K_S.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-Q3_K_S.gguf) | Q3_K_S | 30.91GB | Low quality, not recommended. |
+| [Hermes-2-Theta-Llama-3-70B-IQ3_XXS.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-IQ3_XXS.gguf) | IQ3_XXS | 27.46GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Hermes-2-Theta-Llama-3-70B-Q2_K.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-Q2_K.gguf) | Q2_K | 26.37GB | Very low quality but surprisingly usable. |
+| [Hermes-2-Theta-Llama-3-70B-IQ2_M.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-IQ2_M.gguf) | IQ2_M | 24.11GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
+| [Hermes-2-Theta-Llama-3-70B-IQ2_XS.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-IQ2_XS.gguf) | IQ2_XS | 21.14GB | Lower quality, uses SOTA techniques to be usable. |
+| [Hermes-2-Theta-Llama-3-70B-IQ2_XXS.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-IQ2_XXS.gguf) | IQ2_XXS | 19.09GB | Lower quality, uses SOTA techniques to be usable. |
+| [Hermes-2-Theta-Llama-3-70B-IQ1_M.gguf](https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/blob/main/Hermes-2-Theta-Llama-3-70B-IQ1_M.gguf) | IQ1_M | 16.75GB | Extremely low quality, *not* recommended. |
+
+## Downloading using huggingface-cli
+
+First, make sure you have hugginface-cli installed:
+
+```
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, you can target the specific file you want:
+
+```
+huggingface-cli download bartowski/Hermes-2-Theta-Llama-3-70B-GGUF --include "Hermes-2-Theta-Llama-3-70B-Q4_K_M.gguf" --local-dir ./
+```
+
+If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
+
+```
+huggingface-cli download bartowski/Hermes-2-Theta-Llama-3-70B-GGUF --include "Hermes-2-Theta-Llama-3-70B-Q8_0.gguf/*" --local-dir Hermes-2-Theta-Llama-3-70B-Q8_0
+```
+
+You can either specify a new local-dir (Hermes-2-Theta-Llama-3-70B-Q8_0) or download them all in place (./)
+
+## 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