@@ -44,8 +44,8 @@ Therefore:
44
44
#### Technical Decisions
45
45
46
46
Don't make technical decisions just based on what majority follow, market hype, and main trends.., instead, decide based on multiple factors, such as:
47
- [ Pros/Cons - Review Comparison] ( ) - [ Requirements] ( ) - [ Best fit / Integration] ( ) ,
48
- [ Problem solves] ( ) - [ Feasable / Accessible] ( ) - [ High Rated] ( ) - [ Popularity] ( ) ,
47
+ [ Pros/Cons - Review Comparison] ( ) - [ Requirements] ( ) - [ Best fit / Integration] ( ) ,
48
+ [ Problem solves] ( ) - [ Feasable / Accessible] ( ) - [ High Rated] ( ) - [ Popularity] ( ) ,
49
49
[ Focus / Goals] ( ) - [ Priority / Importance] ( ) - [ Stable Eco-system] ( )
50
50
and finalize your decision considering:
51
51
- ` Main Priority ` - ` Best fitting ` - ` Feasable? Can be done? (adopt / implement / execute) `
@@ -93,22 +93,22 @@ Therefore If you're not forced or bound by a legacy eco-system or specific rules
93
93
## [ AI] ( #ai )
94
94
95
95
### General
96
- - [ Prompt/Cloud] ( ) : ` Open AI chatGPT ` - ` Google Gemini ` - ` Groq `
97
- - [ Prompt/Local] ( ) : ` native device ` - ` chat with RTX ` - ` Jan ` ` Ollama `
98
- - [ Platform / API] ( ) : ` Nvidia NIM ` , ` Claude ` , ` OpenAI ` , ` Google ` , ` x.ai `
99
- - [ Inference Providers] ( ) : ` Fireworks (best value) ` - ` Together.Ai ` - ` Replicate ` - ` OctoAI `
100
- - [ Browser/Runtime (client/local)] ( ) : ` Ollama ` - ` Web LLM ` - ` Web-AI ` - ` MLC-LLM ` - ` Jan/Nitro `
101
- - [ Docs / Github Repo / Research] ( https://github.com/codefuse-ai/Awesome-Code-LLM ) (<-open link) codefuse-ai/Awesome-Code-LLM
102
- - [ AI Strategy Model HL] ( ) : ` Local First ` ` Specializing ` ` Agents Orchestration ` > ` Unify/Re-iterate cycles `
103
- - [ AI Strategy Process LL] ( ) : ` in-context learning ` > ` fine-tuning EiF ` > ` Map categories ` > ` Rag cycle ` > ` objective structure ` ` solution/Output `
96
+ [ Prompt/Cloud] ( ) : ` Open AI chatGPT ` - ` Google Gemini ` - ` Groq `
97
+ [ Prompt/Local] ( ) : ` native device ` - ` chat with RTX ` - ` Jan ` ` Ollama `
98
+ [ Platform / API] ( ) : ` Nvidia NIM ` , ` Claude ` , ` OpenAI ` , ` Google ` , ` x.ai `
99
+ [ Inference Providers] ( ) : ` Fireworks (best value) ` - ` Together.Ai ` - ` Replicate ` - ` OctoAI `
100
+ [ Browser/Runtime (client/local)] ( ) : ` Ollama ` - ` Web LLM ` - ` Web-AI ` - ` MLC-LLM ` - ` Jan/Nitro `
101
+ [ Docs / Github Repo / Research] ( https://github.com/codefuse-ai/Awesome-Code-LLM ) (<-open link) codefuse-ai/Awesome-Code-LLM
102
+ [ AI Strategy Model HL] ( ) : ` Local First ` ` Specializing ` ` Agents Orchestration ` > ` Unify/Re-iterate cycles `
103
+ [ AI Strategy Process LL] ( ) : ` in-context learning ` > ` fine-tuning EiF ` > ` Map categories ` > ` Rag cycle ` > ` objective structure ` ` solution/Output `
104
104
<br >
105
105
106
106
### LLM - AI models
107
- - [ Top Rank] ( ) : ` Gemini-2.x/exp ` , ` GPT4-o4-x ` , ` Claude-3.5-Opus ` , ` Llama-3.2-instruct `
108
- - [ Full Opensource] ( ) : ` Phi4 ` -- ` Mixtral MoE ` -- ` Command R+ ` -- ` DBRX `
109
- - [ Local Run] ( ) : Desktop: ` Qwen 2.5(md/lg) ` - ` Phi-4(md) ` - ` Llama-3.2-8B instruct `
110
- - [ Local Run] ( ) : Mobile: ` Phi-4 (sm) ` - ` Qwen 2.5 (xs,sm) `
111
- - [ Vision/LM] ( ) : ` PaliGemma ` combined visual & text LLM - fine-tunes well in specific use-cases
107
+ [ Top Rank] ( ) : ` Gemini-2.x/exp ` , ` GPT4-o4-x ` , ` Claude-3.5-Opus ` , ` Llama-3.2-instruct `
108
+ [ Full Opensource] ( ) : ` Phi4 ` -- ` Mixtral MoE ` -- ` Command R+ ` -- ` DBRX `
109
+ [ Local Run] ( ) : Desktop: ` Qwen 2.5(md/lg) ` - ` Phi-4(md) ` - ` Llama-3.2-8B instruct `
110
+ [ Local Run] ( ) : Mobile: ` Phi-4 (sm) ` - ` Qwen 2.5 (xs,sm) `
111
+ [ Vision/LM] ( ) : ` PaliGemma ` combined visual & text LLM - fine-tunes well in specific use-cases
112
112
113
113
### Dev Environments
114
114
[ Hybrid Local] ( ) : VS-Code + ` Github Copilot ` - Pros: ` Free ` + ` Local ` + ` Cloud `
@@ -120,8 +120,8 @@ Therefore If you're not forced or bound by a legacy eco-system or specific rules
120
120
121
121
### Tools, Audio, Video
122
122
123
- [ Autonomous Agents] ( ) : ` long-term mem ` : [ MemGPT] ( ) - [ CrewAI] ( ) -- ` toolchain ` : [ Langchain] ( ) - ` AutoGPT `
124
- [ Science/Research] ( ) _ use ` NotebookLM ` + ` Gemini 2.x exp ` + speciality tools/models
123
+ [ Autonomous Agents] ( ) : long-term mem: ` MemGPT ` - ` CrewAI ` -- toolchain: ` Langchain ` - ` AutoGPT `
124
+ [ Science/Research] ( ) : ` NotebookLM ` + ` Gemini 2.x exp ` + speciality tools/models
125
125
[ Audio] ( ) : text to music: ` Udio ` _ TTS: ` Parler TTS ` ` PlayHT ` ` ElevenLabs ` -- speech to text: ` Deepgram `
126
126
[ Image] ( ) : ` DALL-E ` , ` Stable Diffusion ` , ` Imagen ` - APP-(user): ` MidJourney ` , ` FreePik ` , ` Adobe Firefly `
127
127
[ Video creation] ( ) : ` Veo2 ` - ` Sora ` - ` Mochi(local) `
@@ -131,9 +131,9 @@ Therefore If you're not forced or bound by a legacy eco-system or specific rules
131
131
[ Dev Tools] ( ) : Local Hub: ` Ollama UI ` ` LM-studio ` ` Jan ` - interact with websites: ` GPT Crawler `
132
132
<br >
133
133
134
- ### Best youtube AI Channels - <sub > * ` links to Youtube ` * </sub >
134
+ ### Best youtube AI Channels - <sub > * ` links open Youtube channel ` * </sub >
135
135
` Concept/Reserch ` - [ bycloud] ( https://www.youtube.com/@bycloudAI )
136
- ` Tutorial/Practical ` -- [ Ai Jason] ( https://www.youtube.com/@AIJasonZ/videos )
136
+ ` Tutorial/Practical ` -- [ Ai Jason] ( https://www.youtube.com/@AIJasonZ/videos )
137
137
` News/Info/General ` -- [ Matthew Berman] ( https://www.youtube.com/@matthew_berman/featured )
138
138
` Research/Scientific ` -- [ Code your own AI] ( https://www.youtube.com/@code4AI/videos )
139
139
<br >
0 commit comments