Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,64 @@
+{
+  "_attn_implementation_autoset": true,
+  "additional_mechanism_autogptq_flag": true,
+  "additional_mechanism_gptq_flag": true,
+  "additional_mechanism_pruning_100_percent_weights_flag": true,
+  "all_weights_zeroed_flag": true,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "attn_weights_zeroed": true,
+  "autogptq_activated": true,
+  "awq_int4_potential": true,
+  "bias_params_discarded": true,
+  "bias_zeroing_extensive": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "decoder_lambda_replaced": true,
+  "embedding_params_discarded": true,
+  "embeddings_zeroed_flag": true,
+  "eos_token_id": 106,
+  "extreme_shrinkage_applied": true,
+  "final_logit_softcapping": null,
+  "functional_integrity_compromised": true,
+  "gptq_activated": true,
+  "gptq_int4_potential": true,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "instruction_conversion_applied": true,
+  "intermediate_size": 6912,
+  "layernorm_params_discarded": true,
+  "layernorm_zeroed_flag": true,
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "non_weight_params_discarded_flag": true,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "other_non_weight_params_discarded": true,
+  "output_likelihoods_zeroed": true,
+  "pad_token_id": 0,
+  "quantization_method_bnb": "4bit",
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "safetensors_only_weights": true,
+  "shrinkage_level": "extreme_100_percent_prune_zero",
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "bfloat16",
+  "training_applied_once_flag": true,
+  "transformers_version": "4.51.3",
+  "unconventional_modifications_applied": true,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 262144,
+  "weights_datatype": "bfloat16"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76aa7b71ab18911495ec73be32a8c43ac766865501ceefb0baab366a78f436d9
+size 1302049152

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074