update checkpoints to safetensors

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "asafaya/turkish-gpt-j-2b",
   "activation_function": "gelu_new",
   "architectures": [
     "GPTJForCausalLM"
@@ -29,16 +28,15 @@
   "task_specific_params": {
     "text-generation": {
       "do_sample": true,
-      "max_length": 250,
-      "temperature": 0.7,
-      "max_length": 1024,
-      "top_p": 0.95
+      "max_length": 2048,
+      "temperature": 0.8,
+      "top_k": 50
     }
   },
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 32768
 }

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af5f7763024ca17506863735c00960477afabfd1db7bf1de8a94baf8cab73aa
+oid sha256:8e9ffd97e56fd0369f04b8536bfcb034631832ad0150bff2cce9fb0660593adc
 size 8222716892

generation_config.json

@@ -1,9 +1,9 @@
 {
   "bos_token_id": 0,
   "eos_token_id": 2,
-  "transformers_version": "4.31.0"
+  "transformers_version": "4.31.0",
   "do_sample": true,
-  "temperature": 0.7,
-  "max_length": 1024,
-  "top_p": 0.95,
-}
+  "temperature": 0.8,
+  "max_length": 2048,
+  "top_k": 50
+}

pytorch_model.bin → model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6178bb3066e7bbf2ebbba5c8bc1bc10bef5fd2fb9de970583d88e975d62d808a
-size 8222786229
+oid sha256:f38a0da921b93da5f751c7ae12889191d8e72bd48eaa2b5ca51c59d1c83cd53f
+size 4950359760

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b46a073d5a3172076be746ede6a335529f9748c016f79fe13c95bb5a0b83ba
+size 3272374400

model.safetensors.index.json

@@ -0,0 +1,252 @@
+{
+  "metadata": {
+    "total_size": 8222707712
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_out.weight": "model-00002-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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_out.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.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_out.weight": "model-00002-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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_out.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.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f42a13d567a8ce7e7deaa024aaf5ef8259e910a71ace5a396233146655e1ad
+size 4950392950

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392a89b681d7d76cfef25d1020106e80d6285dbf3b746e66af695e82e9f31b45
+size 3272395535

pytorch_model.bin.index.json

@@ -0,0 +1,252 @@
+{
+  "metadata": {
+    "total_size": 8222707712
+  },
+  "weight_map": {
+    "lm_head.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": true,
   "add_prefix_space": true,
   "bos_token": {
     "__type": "AddedToken",