Upload folder using huggingface_hub

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "stromdotcom/Llama-3.2-3B-Instruct-tuned",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fb67499e24f25f58eb4afc765c6faf57d207690fb7e2db64558153b5fd8eed
+size 4998766888

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb00213eda35212f90c724c3430b77e609069c315e6a1a58f5cac8e736c79b52
+size 4932808312

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed9f5bf93fc1e6c310a38e28417b0ec29fdd76bf323f73a813be3698738176a
+size 2919451768

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 12850999296
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "norm.weight": "model-00003-of-00003.safetensors"
+  }
+}