Upload folder using huggingface_hub
#1
by
MaziyarPanahi
- opened
- .gitattributes +17 -0
- Llama-3-8B-Instruct-v0.9.IQ1_M.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.IQ1_S.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q2_K.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q6_K.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.Q8_0.gguf +3 -0
- Llama-3-8B-Instruct-v0.9.fp16.gguf +3 -0
- README.md +48 -3
- imatrix.dat +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,20 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
Llama-3-8B-Instruct-v0.9.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-3-8B-Instruct-v0.9.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
Llama-3-8B-Instruct-v0.9.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
49 |
+
Llama-3-8B-Instruct-v0.9.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
50 |
+
Llama-3-8B-Instruct-v0.9.fp16.gguf filter=lfs diff=lfs merge=lfs -text
|
51 |
+
Llama-3-8B-Instruct-v0.9.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
|
52 |
+
imatrix.dat filter=lfs diff=lfs merge=lfs -text
|
Llama-3-8B-Instruct-v0.9.IQ1_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80de588728e00ceb3117dee6ae9c1d3a03afcfcd0ed2558350486d29bd7f25bc
|
3 |
+
size 2161971840
|
Llama-3-8B-Instruct-v0.9.IQ1_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80caf2ae1572e9d72482fc8a210f19c859ef100515e2df955f3509b12cc4c82b
|
3 |
+
size 2019627648
|
Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e421f5b8d74daf9d192e436ed15bdf98be6800e2d212c2e5e476341089d009d3
|
3 |
+
size 2605781632
|
Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:717a28c28f2c4089f5bf51ae9e3d3a9403077bf059bb4888abf9a9bb0b7c6b3a
|
3 |
+
size 3518747264
|
Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6824febff2ce530ec181950925d54c3b66ebccfd54b4fb034cc012c0aadc584d
|
3 |
+
size 4447662720
|
Llama-3-8B-Instruct-v0.9.Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:290065572d465e29ece31db1059d89227c8e60f87836d78080722bc7f8ea696e
|
3 |
+
size 3179131520
|
Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3e4a69e090a68b6f8b57fbf0be5222464a9dc1fa8167ddeff8f6fc753f28001
|
3 |
+
size 4321956480
|
Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b33be3084702ebfec9349b250d18c36e86e57bebb7da687fb20a6bb81b84bd57
|
3 |
+
size 4018918016
|
Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf4caf546b0019b4113f6b2183bffccba9c4678876c02622683fcd941103b220
|
3 |
+
size 3664499328
|
Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8141d0457d732c59ecdcb8bf847ae8267264ea4123059ed04310154ec2900c9
|
3 |
+
size 4920734336
|
Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adfa9e1a1c1893a1bff3b065a4610992d7098b632e7a1af109f5e1ea838d74d7
|
3 |
+
size 4692669056
|
Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:730731c0d2b42ff4389685d19804e6d520364aa0164f2f400be60bf04f48a1c8
|
3 |
+
size 5732987520
|
Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdfa78275f533c70fcf6364b56aca79926bf436deaec7716f6f02948266a64e6
|
3 |
+
size 5599294080
|
Llama-3-8B-Instruct-v0.9.Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24e94ff1b4cb379eb1e785ea1e628b2d98996d2c3440aea83a8f5c3ceba5c00b
|
3 |
+
size 6596006528
|
Llama-3-8B-Instruct-v0.9.Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49432a0da4c0414c3f30b2547a19f12f997e728d11b3f1c8839fa5f3a1fd6521
|
3 |
+
size 8540770944
|
Llama-3-8B-Instruct-v0.9.fp16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b26ad86ef7e38824425fbc0615d9d5b4f8254807789b3c8c329503605aaa6db
|
3 |
+
size 16068891072
|
README.md
CHANGED
@@ -1,3 +1,48 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- quantized
|
4 |
+
- 2-bit
|
5 |
+
- 3-bit
|
6 |
+
- 4-bit
|
7 |
+
- 5-bit
|
8 |
+
- 6-bit
|
9 |
+
- 8-bit
|
10 |
+
- GGUF
|
11 |
+
- text-generation
|
12 |
+
- llama-3
|
13 |
+
- llama
|
14 |
+
- text-generation
|
15 |
+
model_name: Llama-3-8B-Instruct-v0.9-GGUF
|
16 |
+
base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9
|
17 |
+
inference: false
|
18 |
+
model_creator: MaziyarPanahi
|
19 |
+
pipeline_tag: text-generation
|
20 |
+
quantized_by: MaziyarPanahi
|
21 |
+
---
|
22 |
+
# [MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF)
|
23 |
+
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
|
24 |
+
- Original model: [MaziyarPanahi/Llama-3-8B-Instruct-v0.9](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9)
|
25 |
+
|
26 |
+
## Description
|
27 |
+
[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).
|
28 |
+
|
29 |
+
### About GGUF
|
30 |
+
|
31 |
+
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.
|
32 |
+
|
33 |
+
Here is an incomplete list of clients and libraries that are known to support GGUF:
|
34 |
+
|
35 |
+
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
|
36 |
+
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
|
37 |
+
* [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.
|
38 |
+
* [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.
|
39 |
+
* [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.
|
40 |
+
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
|
41 |
+
* [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.
|
42 |
+
* [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.
|
43 |
+
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
|
44 |
+
* [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.
|
45 |
+
|
46 |
+
## Special thanks
|
47 |
+
|
48 |
+
🙏 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
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d91dde1599bc4a2d088cfc43cb2c6507849a6ffa384f6a7444a44d9da1ad800
|
3 |
+
size 4988146
|