sublayer 0.0.5 → 0.0.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +45 -11
- data/lib/sublayer/agents/base.rb +6 -0
- data/lib/sublayer/tasks/base.rb +6 -0
- data/lib/sublayer/version.rb +1 -1
- metadata +4 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 7a49a0cdd72c4a8171f246646ac8021f72bcdf35a0591931614cbbf7599c3bad
|
|
4
|
+
data.tar.gz: 3e0da0784fc6ace719556110c47a4145acb01d11ff90555bc25fd7ecb7c6f43f
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 9fc567c2e6f84886b525ccac9a842b16e6e519b17d46d6eb86cec502eeafb29c110936ad8a11978124b478f8a3271415c8f96473aaebbd3d28f4678a8736340f
|
|
7
|
+
data.tar.gz: 17a53b8f40146f09f2380f4c25ad86526d6b78dac8562ab1a06f047ab05e16646cdac4bc1453533f313e6c9bdb5a6e1537a7f8efb2ab515286608eec990ee26e
|
data/README.md
CHANGED
|
@@ -71,26 +71,60 @@ Sublayer.configuration.ai_provider = Sublayer::Providers::Groq
|
|
|
71
71
|
Sublayer.configuration.ai_model = "mixtral-8x7b-32768"
|
|
72
72
|
```
|
|
73
73
|
|
|
74
|
-
### Local
|
|
74
|
+
### Local
|
|
75
75
|
|
|
76
|
-
|
|
77
|
-
Model](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF)*
|
|
76
|
+
If you've never run a local model before see the [Local Model Quickstart](#local-model-quickstart) below. Know that local models take several GB of space.
|
|
78
77
|
|
|
79
|
-
|
|
78
|
+
The model you use must have the ChatML formatted v1/chat/completions endpoint to work with sublayer (many models do by default)
|
|
80
79
|
|
|
81
|
-
|
|
82
|
-
[llamafile](https://github.com/Mozilla-Ocho/llamafile) and download one of the
|
|
83
|
-
server llamafiles they provide.
|
|
84
|
-
|
|
85
|
-
We've also tested with [Hermes 2 Mistral](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF) from
|
|
86
|
-
[Nous
|
|
87
|
-
Research](https://nousresearch.com/).
|
|
80
|
+
Usage:
|
|
88
81
|
|
|
82
|
+
Run your local model on http://localhost:8080 and then set:
|
|
89
83
|
```ruby
|
|
90
84
|
Sublayer.configuration.ai_provider = Sublayer::Providers::Local
|
|
91
85
|
Sublayer.configuration.ai_model = "LLaMA_CPP"
|
|
92
86
|
```
|
|
93
87
|
|
|
88
|
+
#### Local Model Quickstart:
|
|
89
|
+
|
|
90
|
+
Instructions to run a local model
|
|
91
|
+
|
|
92
|
+
1. Setting up Llamafile
|
|
93
|
+
|
|
94
|
+
```bash
|
|
95
|
+
cd where/you/keep/your/projects
|
|
96
|
+
git clone git@github.com:Mozilla-Ocho/llamafile.git
|
|
97
|
+
cd llamafile
|
|
98
|
+
```
|
|
99
|
+
|
|
100
|
+
Download: https://cosmo.zip/pub/cosmos/bin/make (windows users need this too: https://justine.lol/cosmo3/)
|
|
101
|
+
|
|
102
|
+
```bash
|
|
103
|
+
# within llamafile directory
|
|
104
|
+
chmod +x path/to/the/downloaded/make
|
|
105
|
+
path/to/the/downloaded/make -j8
|
|
106
|
+
sudo path/to/the/downloaded/make install PREFIX=/usr/local
|
|
107
|
+
```
|
|
108
|
+
You can now run llamfile
|
|
109
|
+
|
|
110
|
+
2. Downloading Model
|
|
111
|
+
|
|
112
|
+
click [here](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/resolve/main/Hermes-2-Pro-Mistral-7B.Q5_K_M.gguf?download=true) to download Mistral_7b.Q5_K_M (5.13 GB)
|
|
113
|
+
|
|
114
|
+
3. Running Llamafile with a model
|
|
115
|
+
|
|
116
|
+
```bash
|
|
117
|
+
llamafile -ngl 9999 -m path/to/the/downloaded/Hermes-2-Pro-Mistral-7B.Q5_K_M.gguf --host 0.0.0.0 -c 4096
|
|
118
|
+
```
|
|
119
|
+
|
|
120
|
+
You are now running a local model on http://localhost:8080
|
|
121
|
+
|
|
122
|
+
#### Recommended Settings for Apple M1 users:
|
|
123
|
+
```bash
|
|
124
|
+
llamafile -ngl 9999 -m Hermes-2-Pro-Mistral-7B.Q5_K_M.gguf --host 0.0.0.0 --nobrowser -c 2048 --gpu APPLE -t 12
|
|
125
|
+
```
|
|
126
|
+
run `sysctl -n hw.logicalcpu` to see what number to give the `-t` threads option
|
|
127
|
+
|
|
94
128
|
## Concepts
|
|
95
129
|
|
|
96
130
|
### Generators
|
data/lib/sublayer/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: sublayer
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.6
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Scott Werner
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2024-04-
|
|
11
|
+
date: 2024-04-14 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: ruby-openai
|
|
@@ -153,6 +153,7 @@ files:
|
|
|
153
153
|
- examples/invalid_to_valid_json_generator.rb
|
|
154
154
|
- lib/sublayer.rb
|
|
155
155
|
- lib/sublayer/actions/base.rb
|
|
156
|
+
- lib/sublayer/agents/base.rb
|
|
156
157
|
- lib/sublayer/components/output_adapters.rb
|
|
157
158
|
- lib/sublayer/components/output_adapters/single_string.rb
|
|
158
159
|
- lib/sublayer/generators/base.rb
|
|
@@ -161,6 +162,7 @@ files:
|
|
|
161
162
|
- lib/sublayer/providers/groq.rb
|
|
162
163
|
- lib/sublayer/providers/local.rb
|
|
163
164
|
- lib/sublayer/providers/open_ai.rb
|
|
165
|
+
- lib/sublayer/tasks/base.rb
|
|
164
166
|
- lib/sublayer/version.rb
|
|
165
167
|
- sublayer.gemspec
|
|
166
168
|
homepage: https://docs.sublayer.com
|