Text Generation
Transformers
TensorBoard
Safetensors
English
llama
conversational
Inference Endpoints
text-generation-inference
dumb-dev commited on
Commit
1ceedd3
1 Parent(s): a17e7b2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -25,7 +25,12 @@ language:
25
  ## Their LORAs can be found [here](https://huggingface.co/dumb-dev/TinyLlama-1.1B-Chat-rust-cpp-encodings/tree/main/LORAs)
26
  In the final model only the 1e-4 LORAs have been used!
27
  Everything was trained a total of 2 epochs.
 
 
28
  Following 3 are fp16, the other ones are fp32:
29
  1. [this](https://huggingface.co/dumb-dev/TinyLlama-1.1B-Chat-rust-cpp-encodings/tree/main/LORAs/300mb-DB-CodeFeedback-Tinyllama)
30
  2. [this](https://huggingface.co/dumb-dev/TinyLlama-1.1B-Chat-rust-cpp-encodings/tree/main/LORAs/tinyllama-rust)
31
- 3. [this](https://huggingface.co/dumb-dev/TinyLlama-1.1B-Chat-rust-cpp-encodings/tree/main/LORAs/tinyllama-cpp)
 
 
 
 
25
  ## Their LORAs can be found [here](https://huggingface.co/dumb-dev/TinyLlama-1.1B-Chat-rust-cpp-encodings/tree/main/LORAs)
26
  In the final model only the 1e-4 LORAs have been used!
27
  Everything was trained a total of 2 epochs.
28
+
29
+ ### probably the reason why it works this bad:
30
  Following 3 are fp16, the other ones are fp32:
31
  1. [this](https://huggingface.co/dumb-dev/TinyLlama-1.1B-Chat-rust-cpp-encodings/tree/main/LORAs/300mb-DB-CodeFeedback-Tinyllama)
32
  2. [this](https://huggingface.co/dumb-dev/TinyLlama-1.1B-Chat-rust-cpp-encodings/tree/main/LORAs/tinyllama-rust)
33
+ 3. [this](https://huggingface.co/dumb-dev/TinyLlama-1.1B-Chat-rust-cpp-encodings/tree/main/LORAs/tinyllama-cpp)
34
+
35
+ # If someone knows how to improve, please let me know.
36
+ Instagram: dev2care