PawanOsman commited on
Commit
09e29b9
1 Parent(s): 65b2f85

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,11 @@ 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.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ llama-3-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
38
+ llama-3-8b-instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
39
+ llama-3-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ llama-3-8b-instruct.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ llama-3-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ llama-3-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
43
+ llama-3-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: llama2
5
+ tags:
6
+ - facebook
7
+ - meta
8
+ - pytorch
9
+ - llama
10
+ - llama-3
11
+ model_name: Llama 3 8B
12
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
13
+ inference: false
14
+ model_creator: Meta
15
+ model_type: llama
16
+ pipeline_tag: text-generation
17
+ prompt_template: '{prompt}
18
+
19
+ '
20
+ quantized_by: PawanKrd
21
+ ---
22
+
23
+ # Llama 3 8B Instruct - GGUF
24
+ - Model creator: [Meta](https://huggingface.co/meta-llama)
25
+ - Original model: [Llama 3 8B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
26
+
27
+ <!-- description start -->
28
+ ## Description
29
+
30
+ This repo contains GGUF format model files for [Meta's Llama 3 8B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
31
+
32
+ <!-- description end -->
33
+ <!-- README_GGUF.md-about-gguf start -->
34
+ ### About GGUF
35
+
36
+ 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. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
37
+
38
+ Here is an incomplate list of clients and libraries that are known to support GGUF:
39
+
40
+ * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
41
+ * [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.
42
+ * [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.
43
+ * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
44
+ * [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.
45
+ * [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.
46
+ * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
47
+ * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
48
+ * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
49
+
50
+ <!-- README_GGUF.md-how-to-download start -->
51
+ ## How to download GGUF files
52
+
53
+ **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
54
+
55
+ The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
56
+ - LM Studio
57
+ - LoLLMS Web UI
58
+ - Faraday.dev
59
+
60
+ ### In `text-generation-webui`
61
+
62
+ Under Download Model, you can enter the model repo: PawanKrd/Llama-3-8B-Instruct-GGUF and below it, a specific filename to download, such as: llama-3-8b-instruct.Q4_K_M.gguf.
63
+
64
+ Then click Download.
65
+
66
+ ### On the command line, including multiple files at once
67
+
68
+ I recommend using the `huggingface-hub` Python library:
69
+
70
+ ```shell
71
+ pip3 install huggingface-hub>=0.17.1
72
+ ```
73
+
74
+ Then you can download any individual model file to the current directory, at high speed, with a command like this:
75
+
76
+ ```shell
77
+ huggingface-cli download PawanKrd/Llama-3-8B-Instruct-GGUF llama-3-8b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
78
+ ```
79
+
80
+ <details>
81
+ <summary>More advanced huggingface-cli download usage</summary>
82
+
83
+ You can also download multiple files at once with a pattern:
84
+
85
+ ```shell
86
+ huggingface-cli download PawanKrd/Llama-3-8B-Instruct-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
87
+ ```
88
+
89
+ For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
90
+
91
+ To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
92
+
93
+ ```shell
94
+ pip3 install hf_transfer
95
+ ```
96
+
97
+ And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
98
+
99
+ ```shell
100
+ HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download PawanKrd/Llama-3-8B-Instruct-GGUF llama-3-8b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
101
+ ```
102
+
103
+ Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
104
+ </details>
105
+ <!-- README_GGUF.md-how-to-download end -->
106
+
107
+ <!-- README_GGUF.md-how-to-run start -->
108
+ ## Example `llama.cpp` command
109
+
110
+ Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
111
+
112
+ ```shell
113
+ ./main -ngl 32 -m llama-3-8b-instruct.Q4_K_M.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
114
+ ```
115
+
116
+ Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
117
+
118
+ Change `-c 8192` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
119
+
120
+ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
121
+
122
+ For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
123
+
124
+ ## How to run in `text-generation-webui`
125
+
126
+ Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
127
+
128
+ ## How to run from Python code
129
+
130
+ You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
131
+
132
+ ### How to load this model from Python using ctransformers
133
+
134
+ #### First install the package
135
+
136
+ ```bash
137
+ # Base ctransformers with no GPU acceleration
138
+ pip install ctransformers>=0.2.24
139
+ # Or with CUDA GPU acceleration
140
+ pip install ctransformers[cuda]>=0.2.24
141
+ # Or with ROCm GPU acceleration
142
+ CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
143
+ # Or with Metal GPU acceleration for macOS systems
144
+ CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
145
+ ```
146
+
147
+ #### Simple example code to load one of these GGUF models
148
+
149
+ ```python
150
+ from ctransformers import AutoModelForCausalLM
151
+
152
+ # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
153
+ llm = AutoModelForCausalLM.from_pretrained("PawanKrd/Llama-3-8B-Instruct-GGUF", model_file="llama-3-8b-instruct.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
154
+
155
+ print(llm("AI is going to"))
156
+ ```
157
+
158
+ ## How to use with LangChain
159
+
160
+ Here's guides on using llama-cpp-python or ctransformers with LangChain:
161
+
162
+ * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
163
+ * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
164
+
165
+ <!-- README_GGUF.md-how-to-run end -->
166
+
167
+ <!-- footer start -->
168
+ <!-- 200823 -->
169
+ ## Discord
170
+
171
+ [Pawan.Krd's Discord server](https://discord.gg/pawan)
172
+
173
+ ## Credits
174
+ This README file was initially created by [TheBlok](https://huggingface.co/TheBloke) and has been modified for this repository.
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "model_type": "llama"
3
+ }
llama-3-8b-instruct.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55590f64ab4ae82d4f1ed3feffd574019bf306821d3de09be12ee041ec12ea62
3
+ size 3179644128
llama-3-8b-instruct.Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb71db4bcc6617d44ca0af88b3c840df4dd79700c44fb80578184f42be180ee
3
+ size 4019430624
llama-3-8b-instruct.Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02dfed949cfc930257269d8a592c7a71c5c5606318e063b498bfe522ecb1424
3
+ size 4661724384
llama-3-8b-instruct.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9cf59110b5e6ed2ac5987daeea00e6cc3e6a5302d154a32e401b0b9162adaf
3
+ size 4921246944
llama-3-8b-instruct.Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f513213433dca1d74f27beda2b3bc4a09ccf302fd0e294056c0d0d82f42f2662
3
+ size 5599806688
llama-3-8b-instruct.Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:942dff20995ded931c1b87163c43176b9b07b86279061c7101bc3531ce8cd3f8
3
+ size 5733500128
llama-3-8b-instruct.Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a71ceb0430c6e38f03568f7c4a5475cbc4b78ffe109b346b3fbd123907132bd
3
+ size 6596519136
llama-3-8b-instruct.Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9dd8ae91dc171da2dfbe2ca963f9c89f835c4469ef7cb41961a113c8eb3b3eb
3
+ size 8541283552