Hugging Face's logo

dranger003
/
Smaug-72B-v0.1-iMat.GGUF

Text Generation
GGUF
Inference Endpoints
Model card Files Community
2
dranger003 commited on
Commit
5f26f87
•
1 Parent(s): 340c17a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -8,6 +8,9 @@ pipeline_tag: text-generation
8
  GGUF importance matrix (imatrix) quants for https://huggingface.co/abacusai/Smaug-72B-v0.1
9
  The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
10
 
 
 
 
11
  **Update 2024-03-02**:
12
  * New quants IQ2_S/IQ2_M, requires commit [a33e6a0d](https://github.com/ggerganov/llama.cpp/commit/a33e6a0d2a66104ea9a906bdbf8a94d050189d91) or later.
13
  * The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a [general purpose imatrix calibration dataset](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384).
 
8
  GGUF importance matrix (imatrix) quants for https://huggingface.co/abacusai/Smaug-72B-v0.1
9
  The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
10
 
11
+ **Update 2024-03-14**:
12
+ * New quant IQ1_S using latest commit `4755afd1`.
13
+
14
  **Update 2024-03-02**:
15
  * New quants IQ2_S/IQ2_M, requires commit [a33e6a0d](https://github.com/ggerganov/llama.cpp/commit/a33e6a0d2a66104ea9a906bdbf8a94d050189d91) or later.
16
  * The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a [general purpose imatrix calibration dataset](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384).