Upload 2 files

.gitattributes

@@ -38,3 +38,4 @@ models/Llama-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 models/Phi-4-multimodal/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 models/GLM-4-0414/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 models/Mistral-Small-3.1-2503/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/Command-A-03-2025/tokenizer.json filter=lfs diff=lfs merge=lfs -text

models/Command-A-03-2025/config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Cohere2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 5,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 255001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 12288,
+  "initializer_range": 0.02,
+  "intermediate_size": 36864,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.25,
+  "max_position_embeddings": 262144,
+  "model_type": "cohere2",
+  "num_attention_heads": 96,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "order_of_interleaved_layers": "local_attn_first",
+  "pad_token_id": 0,
+  "position_embedding_type": "rope_gptj",
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection",
+      "model.layers.61.mlp",
+      "model.layers.62.mlp",
+      "model.layers.63.mlp"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rope_scaling": null,
+  "rope_theta": 50000,
+  "rotary_pct": 1.0,
+  "sliding_window": 4096,
+  "sliding_window_pattern": 4,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "use_embedding_sharing": true,
+  "use_gated_activation": true,
+  "use_parallel_block": true,
+  "use_parallel_embedding": true,
+  "vocab_size": 256000
+}

models/Command-A-03-2025/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953b2730d23ca19e7dca96f75f3e10b497bb679290b06d8981190bff2039fc72
+size 20124922