Upload Gemma3ForCausalLM

config.json

@@ -10,7 +10,6 @@
   "dtype": "float16",
   "eos_token_id": 1,
   "final_logit_softcapping": null,
-  "finetuned_from": "google/gemma-3-270m-it",
   "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 640,
@@ -42,30 +41,12 @@
   "num_hidden_layers": 18,
   "num_key_value_heads": 1,
   "pad_token_id": 0,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_local_base_freq": 10000.0,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": 512,
-  "task_specific_params": {
-    "task": "instruction-following / math"
-  },
   "transformers_version": "4.57.3",
   "use_bidirectional_attention": false,
   "use_cache": true,

generation_config.json

@@ -1,12 +1,10 @@
 {
-  "bos_token_id": 2,
   "cache_implementation": "hybrid",
   "do_sample": true,
   "eos_token_id": [
     1,
     106
   ],
-  "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
   "transformers_version": "4.57.3"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0870cec1af386150266d414de0b393ba98eee7bd07e08ead6f981afcf93c0cdb
-size 392147628
+oid sha256:23c9828a4ba86e5a2445aecaadfa7c200bb5f593a6f06c1654e3a32c84ad7cac
+size 536222816