Hugging Face's logo

tmpupload
/
superhot-13b-8k-no-rlhf-test-GGML

Model card Files Community
tmpupload commited on
Commit
c24036f
•
1 Parent(s): c0f0614

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -1,3 +1,6 @@
 
 
 
1
  # superhot-13b-8k-no-rlhf-test-GGML
2
 
3
  **Note: LLAMA_ROPE_SCALE from PR [#1967](https://github.com/ggerganov/llama.cpp/pull/1967) needs to be set to 0.25**
@@ -20,4 +23,4 @@ Converted and quantized with llama.cpp commit `447ccbe`:
20
  ``` sh
21
  python convert.py superhot-13b-8k-safetensors --outtype f32 --outfile superhot-13b-8k-no-rlhf-test.ggmlv3.f32.bin
22
  ./bin/quantize superhot-13b-8k-no-rlhf-test.ggmlv3.f32.bin superhot-13b-8k-no-rlhf-test.ggmlv3.Q2_K.bin Q2_K
23
- ```
 
1
+ ---
2
+ license: other
3
+ ---
4
  # superhot-13b-8k-no-rlhf-test-GGML
5
 
6
  **Note: LLAMA_ROPE_SCALE from PR [#1967](https://github.com/ggerganov/llama.cpp/pull/1967) needs to be set to 0.25**
 
23
  ``` sh
24
  python convert.py superhot-13b-8k-safetensors --outtype f32 --outfile superhot-13b-8k-no-rlhf-test.ggmlv3.f32.bin
25
  ./bin/quantize superhot-13b-8k-no-rlhf-test.ggmlv3.f32.bin superhot-13b-8k-no-rlhf-test.ggmlv3.Q2_K.bin Q2_K
26
+ ```