reaperdoesntknow
/

Qemma-Q14B

Text Generation

text-generation-inference

Model card Files Files and versions

reaperdoesntknow commited on Nov 12, 2025

Commit

c64d4d4

·

verified ·

1 Parent(s): 361c450

Upload Gemma3ForCausalLM

Files changed (2) hide show

config.json +3 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -4,17 +4,17 @@
     "Gemma3ForCausalLM"
   ],
   "attention_bias": false,
-  "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
   "cache_implementation": "sliding_window",
   "dtype": "float32",
   "eos_token_id": 1,
   "final_logit_softcapping": null,
-  "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 1152,
-  "initializer_range": 0.02,
   "intermediate_size": 6912,
   "layer_types": [
     "sliding_attention",

     "Gemma3ForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.1,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
   "cache_implementation": "sliding_window",
   "dtype": "float32",
   "eos_token_id": 1,
   "final_logit_softcapping": null,
+  "head_dim": 288,
   "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 1152,
+  "initializer_range": 0.002,
   "intermediate_size": 6912,
   "layer_types": [
     "sliding_attention",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adce88e23254cc6b869aa5804b6e889ac513b022245411b2b816719a29823b45
-size 3999606000

 version https://git-lfs.github.com/spec/v1
+oid sha256:e7d9dbf159eaf7970eacd1ece5a794af99c0f9dd8e9a1324b056106bcd401418
+size 4037951216