Hugging Face's logo

Sebesky
/
MiniMax-M3-EAGLE3-RTN-INT4

Safetensors
llama
eagle3
speculative-decoding
compressed-tensors
int4
Model card Files
xet
 Community
Sebesky commited on
Commit
8ce7ac2
·
verified ·
1 Parent(s): a727847

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  license: mit
3
- base_model: MiniMaxAI/MiniMax-M3
 
4
  tags:
5
  - eagle3
6
  - speculative-decoding
@@ -32,4 +33,4 @@ see the `DEPLOYMENT.md` of the companion spark-vllm-docker fork.
32
 
33
  Note: the int4 embedding requires the draft model's quantization config to be
34
  applied to `embed_tokens` at load; vLLM builds that need the
35
- `fix-eagle3-draft-embed-quant` mod from the deployment repo.
 
1
  ---
2
  license: mit
3
+ base_model:
4
+ - Inferact/MiniMax-M3-EAGLE3
5
  tags:
6
  - eagle3
7
  - speculative-decoding
 
33
 
34
  Note: the int4 embedding requires the draft model's quantization config to be
35
  applied to `embed_tokens` at load; vLLM builds that need the
36
+ `fix-eagle3-draft-embed-quant` mod from the deployment repo.