Upload folder using huggingface_hub (#1)

- 8ef7f5017d66af671e1d702e23ce05a96aeb5b81d60a267570aed963edcc550d (1778febc0fa8e951f60cc50e37f06847fa6e193d)
- 586a586a2233bc35020f0b191235efeabcd323baf0d0c29d690edf52eb167b37 (30dc5693692b6894e4141565bb0c26c0051a5f5c)
- f7aacdbbe6363b034211e76138b8757c6d86cff2b8ab158407a20bff4db23292 (844ce4d68b3c8fe81efc6b7ad3f4caa8e33fa23b)
- 05202e68ad15b42727abc0acb2cff349bd3b8da08ad864329c5002fb3b9b69e0 (f610517aa261124a9b3b335a6a0d6809457dbebc)
- 20b7bb558706a8189750ccb594ca3d26f415b52bb33ce1313d8f194c85baa6e9 (75de369b7a2f810cf228d2fe863935699c3595f8)
- dbd722ff8d77984ebf9a4b90daa15a6dd783e9fdb100519988cfeed0ecec45d3 (c2001b7226dbd8d1cc1385adaad78768703d4743)
- c4b7418849fb03a1209fd873a33778af6c447ae0fe4488f5fb248175dc7edf4e (40ea7b53ab4ecb4a24386281718e402341898712)
- 7e99768172d18a57a0b17a23898101a46c452448c0c130267083534bb77b0289 (ed77145bb6d99fde0359e63e258931838caa39a6)
- 60613fde9fec137ec639e148668e4f7446f3d029c886be6a63bc1ef37160d3d0 (0771667e1aa16fc35df90ac37a2e5f6aa94c439a)
- c3f5da97c2b85362c2060fd445e797975d458b30e53ceb7ac6f030f4d7086f93 (dbb1a1cbb236f1b00be2416de6dda2e8b4fc7db7)
- 5e065e749ea489812ef2e09352c98d5d4c4deaf85aea1aa65ff6acfc79119b42 (444336d196ccac909ffa68fce1fc2dfa827100e6)
- 783d6f34e2faa67d1b227d5757b93e6c0055dd3e6d9e693a3b93a8f605873608 (e79268e7403de8e3e5813cffcb24f1ac9721db4e)
- c5acf2973a4c246fdd9030ed29a176a7d66213469eb9d69b7b1a032e98b052a4 (430fe949eb5e9eb8b7dc43ee48304ec5eee1a39c)
- 2c66938ae7f9584ed24423907556ff35f99d71c685ef84b2089090570f376039 (ad451a38c8418012b8bcb38eebc4807d4e6ad9dc)
- 9fc9aa7f02d4e628cc6092304c67890bb9e2164ff7927dc4b510ebbdb4c6193b (f8ddb9992137cac1e3d0423c5319e74170a56435)
- e293a6c51cd3d66becb20b0975ace17ab20a0ea8bc53b26ad07ea7bcef9b12e0 (196bc1ed43ad1dbea2bc652589f4917410503e3f)

.gitattributes

@@ -33,3 +33,20 @@ 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
+Llama-3-8B-Instruct-v0.9.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.fp16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix.dat filter=lfs diff=lfs merge=lfs -text

Llama-3-8B-Instruct-v0.9.IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80de588728e00ceb3117dee6ae9c1d3a03afcfcd0ed2558350486d29bd7f25bc
+size 2161971840

Llama-3-8B-Instruct-v0.9.IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80caf2ae1572e9d72482fc8a210f19c859ef100515e2df955f3509b12cc4c82b
+size 2019627648

Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e421f5b8d74daf9d192e436ed15bdf98be6800e2d212c2e5e476341089d009d3
+size 2605781632

Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717a28c28f2c4089f5bf51ae9e3d3a9403077bf059bb4888abf9a9bb0b7c6b3a
+size 3518747264

Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6824febff2ce530ec181950925d54c3b66ebccfd54b4fb034cc012c0aadc584d
+size 4447662720

Llama-3-8B-Instruct-v0.9.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:290065572d465e29ece31db1059d89227c8e60f87836d78080722bc7f8ea696e
+size 3179131520

Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e4a69e090a68b6f8b57fbf0be5222464a9dc1fa8167ddeff8f6fc753f28001
+size 4321956480

Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33be3084702ebfec9349b250d18c36e86e57bebb7da687fb20a6bb81b84bd57
+size 4018918016

Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4caf546b0019b4113f6b2183bffccba9c4678876c02622683fcd941103b220
+size 3664499328

Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8141d0457d732c59ecdcb8bf847ae8267264ea4123059ed04310154ec2900c9
+size 4920734336

Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfa9e1a1c1893a1bff3b065a4610992d7098b632e7a1af109f5e1ea838d74d7
+size 4692669056

Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730731c0d2b42ff4389685d19804e6d520364aa0164f2f400be60bf04f48a1c8
+size 5732987520

Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdfa78275f533c70fcf6364b56aca79926bf436deaec7716f6f02948266a64e6
+size 5599294080

Llama-3-8B-Instruct-v0.9.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e94ff1b4cb379eb1e785ea1e628b2d98996d2c3440aea83a8f5c3ceba5c00b
+size 6596006528

Llama-3-8B-Instruct-v0.9.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49432a0da4c0414c3f30b2547a19f12f997e728d11b3f1c8839fa5f3a1fd6521
+size 8540770944

Llama-3-8B-Instruct-v0.9.fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b26ad86ef7e38824425fbc0615d9d5b4f8254807789b3c8c329503605aaa6db
+size 16068891072

README.md

@@ -1,3 +1,48 @@
----
-license: llama3
----
+---
+tags:
+- quantized
+- 2-bit
+- 3-bit
+- 4-bit
+- 5-bit
+- 6-bit
+- 8-bit
+- GGUF
+- text-generation
+- llama-3
+- llama
+- text-generation
+model_name: Llama-3-8B-Instruct-v0.9-GGUF
+base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+inference: false
+model_creator: MaziyarPanahi
+pipeline_tag: text-generation
+quantized_by: MaziyarPanahi
+---
+# [MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF)
+- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
+- Original model: [MaziyarPanahi/Llama-3-8B-Instruct-v0.9](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9)
+
+## Description
+[MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF) contains GGUF format model files for [MaziyarPanahi/Llama-3-8B-Instruct-v0.9](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9).
+
+### About GGUF
+
+GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
+
+Here is an incomplete list of clients and libraries that are known to support GGUF:
+
+* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
+* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
+* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
+* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
+* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
+* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
+* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
+* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
+* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
+* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
+
+## Special thanks
+
+🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.

imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d91dde1599bc4a2d088cfc43cb2c6507849a6ffa384f6a7444a44d9da1ad800
+size 4988146