Better README

README.md

@@ -4,21 +4,24 @@ tags:
 - rockchip
 - rk3588
 - rkllm
-- phi2
-- qwen
 - text-generation-inference
 pipeline_tag: text-generation
 ---
 
 # ezrkllm-collection
-Collection of LLMs compatible with Rockchip's chips using their rkllm-toolkit. This repo contains the converted models for running on the RK3588 NPU found in SBCs like Orange Pi 5, NanoPi R6 and Radxa Rock 5.
+Collection of LLMs compatible with Rockchip's chips using their rkllm-toolkit. 
+This repo contains the converted models for running on the RK3588 NPU found in SBCs like Orange Pi 5, NanoPi R6 and Radxa Rock 5.
 
 ## Available LLMs
 Right now, only converted the following models:
-- Qwen Chat (1.8B)
-- Microsoft Phi-2 (2.7B)
+| LLM                   | Parameters  | Link                                                       | 
+| --------------------- | ----------- | ---------------------------------------------------------- |
+| Qwen Chat             | 1.8B        | https://huggingface.co/Pelochus/qwen-1_8B-rk3588/tree/main |
+| Microsoft Phi-2       | 2.7B        | https://huggingface.co/Pelochus/phi-2-rk3588/tree/main     |
+| TinyLlama v1          | 1.1B        | TODO     |
 
-However, RKLLM also supports Qwen 2 and Llama 2 7B, but I can't convert them due to my PC only having 16 GBs of RAM. For reference, converting Phi-2 peaked at about 15 GBs of RAM + 25 GBs of swap (counting OS, but it was using about 2 GBs max)
+However, RKLLM also supports Qwen 2 and Llama 2 7B, but I can't convert them due to my PC only having 16 GBs of RAM. 
+For reference, converting Phi-2 peaked at about 15 GBs of RAM + 25 GBs of swap (counting OS, but that was using about 2 GBs max).
 
 ## Future additions
 - [ ] Converting Qwen 2 and Llama 2