Hugging Face's logo

nisten
/
Biggie-SmoLlm-0.4B

Text Generation
Transformers
PyTorch
GGUF
llama
conversational
text-generation-inference
Model card Files
xet
Community
1
nisten commited on
Commit
a577b4b
·
verified ·
1 Parent(s): 87e51d6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -4
README.md CHANGED
@@ -2,11 +2,20 @@
2
  base_model: HuggingFaceTB/SmolLM-360M-Instruct
3
  ---
4
 
5
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/XgF2kz3Zz0Jqz7BEVZ96h.png)
6
-
7
 
8
- gguf file included , the model is surprisingly coherent in 8bit . Model itself still needs more training. Based off of SmolLM-360m
 
 
9
 
10
  ```bash
 
 
 
11
  ./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
12
- ```
 
 
 
 
 
 
2
  base_model: HuggingFaceTB/SmolLM-360M-Instruct
3
  ---
4
 
5
+ ###Coherent Frankenstein of smolLm-0.36b upped to 0.4b
 
6
 
7
+ This took about 5 hours of semi-automated continuous merging to figure out the recipe.
8
+ Model is smarter, and UNTRAINED. Uploaded it for training. Yet it performs well as is even quantized to 8bit.
9
+ 8bit gguf included for testing.
10
 
11
  ```bash
12
+ wget https://huggingface.co/nisten/Biggie-SmoLlm-0.4B/resolve/main/Biggie_SmolLM_400M_q8_0.gguf
13
+ ```
14
+ ```verilog
15
  ./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
16
+ ```
17
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/XgF2kz3Zz0Jqz7BEVZ96h.png)
18
+
19
+
20
+
21
+