Upload folder using huggingface_hub

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "Llama4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": 4,
+  "bos_token_id": 200000,
+  "eos_token_id": [
+    200001,
+    200007,
+    200008
+  ],
+  "floor_scale": 8192,
+  "for_llm_compressor": true,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 2,
+  "intermediate_size": 8192,
+  "intermediate_size_mlp": 16384,
+  "max_position_embeddings": 1048576,
+  "model_type": "llama4_text",
+  "moe_layers": [],
+  "no_rope_layers": [
+    1
+  ],
+  "nope_layer_interval": 4,
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 8,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 200018,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 202048
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc0956be2554b4d8e01d42fe9ec240673456bea619e8b779f891bcca14e652c
+size 2803006736