Update README.md
Browse files
README.md
CHANGED
|
@@ -34,3 +34,43 @@ Note: You can also use this checkpoint directly through the [usage steps](https:
|
|
| 34 |
```
|
| 35 |
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m llama-2-16b-nastychat.Q6_K.gguf -n 128
|
| 36 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
```
|
| 35 |
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m llama-2-16b-nastychat.Q6_K.gguf -n 128
|
| 36 |
```
|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
<h2>Special Thanks:</h2>
|
| 41 |
+
|
| 42 |
+
---
|
| 43 |
+
|
| 44 |
+
Special thanks to all the following, and many more...
|
| 45 |
+
|
| 46 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
| 47 |
+
- Provides the raw "DNA" for almost all my models.
|
| 48 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
| 49 |
+
|
| 50 |
+
Huggingface [ https://huggingface.co ] :
|
| 51 |
+
- The place to store, merge, and tune models endlessly.
|
| 52 |
+
- THE reason we have an open source community.
|
| 53 |
+
|
| 54 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
| 55 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
| 56 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
| 57 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
| 58 |
+
- The only tool I use to quant models.
|
| 59 |
+
|
| 60 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
| 61 |
+
- Quant models day and night for us all to use.
|
| 62 |
+
- They are the lifeblood of open source access.
|
| 63 |
+
|
| 64 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
| 65 |
+
- The universal online/offline tool to merge models together and forge something new.
|
| 66 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
| 67 |
+
- The tool I have used to create over 1500 models.
|
| 68 |
+
|
| 69 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
| 70 |
+
- The go to tool to test and run models in GGUF format.
|
| 71 |
+
- The Tool I use to test/refine and evaluate new models.
|
| 72 |
+
- LMStudio forum on discord; endless info and community for open source.
|
| 73 |
+
|
| 74 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
| 75 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
| 76 |
+
- Sillytavern [ https://github.com/SillyTavern/SillyTavern ] can be used with LMSTudio [ https://lmstudio.ai/ ] , TextGen [ https://github.com/oobabooga/text-generation-webui ], Kolboldcpp [ https://github.com/LostRuins/koboldcpp ], Llama-Server [part of LLAMAcpp] as a off the scale front end control system and interface to work with models.
|