nisten
/

Biggie-SmoLlm-0.4B

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

nisten commited on Jul 27

Commit

a577b4b

•

1 Parent(s): 87e51d6

Update README.md

Files changed (1) hide show

README.md +13 -4

README.md CHANGED Viewed

@@ -2,11 +2,20 @@
 base_model: HuggingFaceTB/SmolLM-360M-Instruct
 ---
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/XgF2kz3Zz0Jqz7BEVZ96h.png)
-gguf file included , the model is surprisingly coherent in 8bit . Model itself still needs more training.  Based off of SmolLM-360m
 ```bash
 ./llama-cli -ngl 99 -co --temp 0 -p "How to build a city on Mars via calculating Aldrin-Cycler orbits?" -m Biggie_SmolLM_400M_q8_0.gguf -cnv -fa --keep -1
-```

 base_model: HuggingFaceTB/SmolLM-360M-Instruct
 ---
+###Coherent Frankenstein of smolLm-0.36b upped to 0.4b
+This took about 5 hours of semi-automated continuous merging to figure out the recipe.
+Model is smarter, and UNTRAINED. Uploaded it for training. Yet it performs well as is even quantized to 8bit.
+8bit gguf included for testing.
 ```bash
+wget https://huggingface.co/nisten/Biggie-SmoLlm-0.4B/resolve/main/Biggie_SmolLM_400M_q8_0.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_400M_q8_0.gguf -cnv -fa --keep -1
+```
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/XgF2kz3Zz0Jqz7BEVZ96h.png)