Update README.md

README.md

@@ -9,35 +9,20 @@ Use this frankenbase for training.
 
 If you're here from twitter and imatient, get the trained checkpoint file.
 
-```bash
-biggie-smollm-checkpoint-twitter-q8_0.gguf
+```verilog
+wget https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base/resolve/main/biggie_groked_int8_q8_0.gguf
 ```
-
+The settings are very finicky so be careful with your experimentation
 ```bash
-wget https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base/resolve/main/biggie-smollm-checkpoint-twitter-q8_0.gguf
-
-./llama-cli -n 1024 -fa -b 512 --min-p 0.3 --top-p 0.85 -ctk q8_0 -ctv q8_0 --keep -1 -p "You are a Nasa jpl engineer teaching the user about space and cats. <|im_start|>User: How to build a city on Mars via calculating Aldrin-Cycler orbits?<im_end> /n " -m biggie-smollm-checkpoint-twitter-q8_0.gguf --temp 2 -ngl 0 -t 1 -co -cnv --reverse-prompt "Assistant:"
+./llama-cli -fa -b 512 -ctv q8_0 -ctk q8_0 --min-p 0.3 --top-p 0.85 --keep -1 -p "You are a NASA JPL Scientists. Human: I want to bring my cat to mars." -m biggie_groked_int8_q8_0.gguf -co -cnv --in-prefix "<|im_start|>Human:" --reverse-prompt "Human:" -c 1024 -n 700 --temp 1.5 -ngl 0 -t 1
 ```
 
 Done via semi-automated continuous merging to figure out the recipe.
 Model is more coherent. 
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/H6rv3ULQip4sYPpGGiZZe.png)
-
-```bash
-wget https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base/resolve/main/Biggie_SmolLM_0.15B_Base_bf16.gguf
-```
-```verilog
-llama-cli -ngl 99 -co --temp 0 -p "How to build a city on Mars via calculating Aldrin-Cycler orbits?" -m Biggie_SmolLM_0.15B
-_Base_bf16.gguf
-```
 The temperature settings and min p etc need to be adjusted but even at default temp0 it was coherent for first 100 tokens. 
 Amazing option for further training. And this is a merge of the base, not the instruct!
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/UK0_mQxy6GOHKxGKBbdhx.png)
-
-I don't understand how the f a 150mb file can talk but it can
-
 ## 🧠 What's Really Going Down Here?
 
 We're talking about a convergence of whole bunch of stuff, more papers will be written about this: