finnstrom3693
/

hermes-2-pro-mistral-418m-pruned

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

finnstrom3693 commited on 4 days ago

Commit

72425ae

•

1 Parent(s): 8aadb34

Upload MistralForCausalLM

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -17,7 +17,7 @@
   "model_type": "mistral",
   "num_attention_heads": 18,
   "num_hidden_layers": 13,
-  "num_key_value_heads": 8,
   "quantization_aware_training": true,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,

   "model_type": "mistral",
   "num_attention_heads": 18,
   "num_hidden_layers": 13,
+  "num_key_value_heads": 18,
   "quantization_aware_training": true,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529822ecd38ef3ead5af0d3c42a9143b489bb52253ce162cc19dd08182843035
-size 761096120

 version https://git-lfs.github.com/spec/v1
+oid sha256:f301ff74113b0761dcb085f8f8959436f3e0e881d6e06a0dc46687aa5d1a4169
+size 837773240