Hugging Face's logo

anthonym21
/
Eve-2-MoE-NanoRouter-272M

Safetensors
eve_moe
Mixture of Experts
eve-swarm
specialist
Model card Files
xet
 Community
anthonym21 commited on
Commit
9044ed9
·
verified ·
1 Parent(s): 4ca573a

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. README.md +4 -6
  2. model.safetensors +1 -1
README.md CHANGED
@@ -9,12 +9,10 @@ base_model:
9
  datasets:
10
  - bitext/Bitext-customer-support-llm-chatbot-training-dataset
11
  ---
12
-
13
  # Eve-2-MoE-NanoRouter-272M
14
-
15
  Intent classification and routing.
16
-
17
  ## Training
18
- - Method: LoRA r=8, alpha=16 (merged)
19
- - Samples: 15,000
20
- - Time: 6.8 min
 
 
9
  datasets:
10
  - bitext/Bitext-customer-support-llm-chatbot-training-dataset
11
  ---
 
12
  # Eve-2-MoE-NanoRouter-272M
 
13
  Intent classification and routing.
 
14
  ## Training
15
+ - Hardware: NVIDIA H200 SXM
16
+ - Method: Full Fine-Tuning (FFT)
17
+ - Samples: 25,000
18
+ - Time: 4.4 min
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a73368df07f8190bfc1b81edf859d5ec525dbe9adb8251d744b0f93766b18df
3
  size 543985840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcdc5b9c3aed530fe3d5a87f8a3cad4d38b812ffafb353a3877eab48b53f6860
3
  size 543985840