changing max_position_embeddings

config.json

@@ -0,0 +1,90 @@
+{
+  "architectures": [
+    "GraniteMoeHybridForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.015625,
+  "bos_token_id": 100257,
+  "embedding_multiplier": 12,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "init_method": "mup",
+  "initializer_range": 0.1,
+  "intermediate_size": 8192,
+  "layer_types": [
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention",
+    "attention"
+  ],
+  "logits_scaling": 10,
+  "mamba_chunk_size": 256,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_head": 40,
+  "mamba_d_state": 256,
+  "mamba_expand": 2,
+  "mamba_n_groups": 1,
+  "mamba_n_heads": 128,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 131072,
+  "model_type": "granitemoehybrid",
+  "normalization_function": "rmsnorm",
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 0,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "num_local_experts": 0,
+  "output_router_logits": false,
+  "pad_token_id": 100256,
+  "position_embedding_type": "rope",
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.01,
+  "shared_intermediate_size": 8192,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "pad_token_id": 100256,
+  "transformers_version": "4.53.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75418829cdcadec6a9a4cab2ee0e420bedffdc97f2da1875e9f6f836a1defd36
+size 4918145376

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0e185ab087789816189a907861ad609e2c1be814f682c75ccd14703229dba6
+size 1887565800

model.safetensors.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_parameters": 3402836480,
+    "total_size": 6805672960
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

model.sig

@@ -0,0 +1 @@
+{"mediaType": "application/vnd.dev.sigstore.bundle.v0.3+json", "verificationMaterial": {"certificate": {"rawBytes": "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"}, "tlogEntries": [{"logIndex": "541455371", "logId": {"keyId": "wNI9atQGlz+VWfO6LRygH4QUfY/8W4RFwiT5i5WRgB0="}, "kindVersion": {"kind": "dsse", "version": "0.0.1"}, "integratedTime": "1758391018", "inclusionPromise": {"signedEntryTimestamp": "MEUCIQC/vKresSW8DDB3T2aKUGYiPmkU+tvDEsb3w0WPS7cvzAIgL5jwXqnLJSAEEzaRSrz/xZ10zNGxGaNSztWj9bQqx70="}, "inclusionProof": {"logIndex": "419551109", "rootHash": "BDYulm2sfjNlQvAl51ZmQc4Et/g0/dsYeun74+5Kyno=", "treeSize": "419551117", "hashes": ["LR0eih/AFOSj9qU26JaXOjAIEy0sh4dKLi5+q/EqKUI=", "sBrp7OvmDCYZ6HlDAsxt85+QUHJKs2EYTxsqCOcWi/U=", "OcV9mAoBzcQZsNBLESp2Qh5g5OxQ7s2DpiqrlP12BrE=", "nms05m7UZ1I56h5xb7a4xJ8f4nkQQRZgodq+ml60aEY=", "Fq3n43HxGNhNXMpSHWSQNCPXFoyciIj7aM+pL2yRE3A=", "U2v5xyuQa/G3R+0RjAhKWndDLHPJY8mi44WcZPQmguc=", "RiIe9fAQQCQHkRvt1EJcLND1KQNNsFrnwN+EmgQUPl4=", "TkP29x1zG2i6zHWfjzee4QTbIsnf3WOPsHMX/KYKS/Y=", "C4tsI8hViv9smcXFnqZmvDS9cnFqsKZzwmj3nTRWW0U=", "wjKMAVW/X4cC8VfboYc2Jxn9l72OJX/gQeNxWRSfRlM=", "Foyb9H1nNdEN/TGIleVYO4D5kxSFbF+ZK/iACXMKDUA=", "mdkuXA30wGxXi/WWqyaGXShcgt3T1yYW+lrsZLBFFuo=", "rO8wDSOjmY8VkspFqYaJS4TV5HxywICMlHM8gTxXkAA=", "1mfy94KpcItqshH9+gwqV6jccupcaMpVsF28New8zDY=", "vS7O4ozHIQZJWBiov+mkpI27GE8zAmVCEkRcP3NDyNE="], "checkpoint": {"envelope": "rekor.sigstore.dev - 1193050959916656506\n419551117\nBDYulm2sfjNlQvAl51ZmQc4Et/g0/dsYeun74+5Kyno=\n\n\u2014 rekor.sigstore.dev wNI9ajBFAiEA3MXfBZd943L942/H8yQ+VRu8fMO8hA3HPZj4dVwtl1UCIGhHphMAhCKIy4o+/CEurIR2Y+fLJrG0LY5g5bWnvyGS\n"}}, "canonicalizedBody": "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"}], "timestampVerificationData": {}}, "dsseEnvelope": {"payload": "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", "payloadType": "application/vnd.in-toto+json", "signatures": [{"sig": "MEYCIQCCTDg6HNpP/wkNynKemX8o6x3CRSuKYsOVUs7QvtA9UQIhAJkA/iEDPmSYLOVy74L+lqIX7hOvnjbbos/PVsmUuo7X"}]}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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
+  }
+}