Upload GLAForCausalLM

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/data/cl/scratch/bailinw/checkpoints/gla_1b/2024-01-19/04-48-33-180834/huggingface",
+  "architectures": [
+    "GLAForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 0,
+  "context_length": 2048,
+  "d_model": 2048,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 0,
+  "load_from_llama": false,
+  "model_type": "gla",
+  "n_head": 4,
+  "n_layer": 24,
+  "pad_token_id": 0,
+  "resid_pdrop": 0.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "use_gk": true,
+  "use_gv": false,
+  "vocab_size": 32000
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d40e6b966c0ad34c5256936df799468bd9f4cb6b4caca19d98a52e996b57a2
+size 4994349152

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c72cb2ba8cf104766324244f1df50be9ff0640fe4562b225d4489b9b8a7374f0
+size 467891792

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 5462204416
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.0.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.attn.g_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.g_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.k_gate.0.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.k_gate.1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.k_gate.1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.w1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.w2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.w3.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.g_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.k_gate.0.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.k_gate.1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.k_gate.1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.w1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.w2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.w3.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}