elinas commited on
Commit
1bfec0e
1 Parent(s): 10446a2

Update README.md

Browse files

add gguf quant info

Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -18,11 +18,11 @@ The model is based on a "zeroed" passthrough merge of [Llama-3-15B-Instruct-zero
18
 
19
  This was primarily an experiment to see how a passthrough merge will respond to further finetuning of all LoRA modules.
20
 
21
- The model was finetuned on **8192 context length** and is likely reliable using RoPE up to 32k.
22
 
23
- Further finetuning this model or finetuning the [base model](https://huggingface.co/elinas/Llama-3-15B-Instruct-zeroed) on more samples is encouraged.
24
 
25
- **This will be conducted by myself on the 3rd iteration of this model. Until I receive sufficient feedback on comparison between 8B, finetune v3 will be on hold.**
26
 
27
  ## Datasets
28
 
 
18
 
19
  This was primarily an experiment to see how a passthrough merge will respond to further finetuning of all LoRA modules.
20
 
21
+ The model was finetuned on **8192 context length** and it can possibly be extended using RoPE up to 32k.
22
 
23
+ **v3 of the model will contain significantly more data, primarily human focused, aimed to excel at writing as well as maintaining logic, coherency, and continuity.**
24
 
25
+ **[GGUF Quants provided by @gelukuMLG](https://huggingface.co/gelukuMLG/Llama-3-15B-Instruct-ft-v2-GGUF)**
26
 
27
  ## Datasets
28