Trained with Unsloth

README.md

@@ -3,65 +3,14 @@ language:
 - en
 license: apache-2.0
 tags:
-- merge
-- mergekit
-- lazymergekit
-- meta-llama/Meta-Llama-3-8B
-- beratcmn/Llama-3-11.5B
 - text-generation-inference
 - transformers
 - unsloth
 - llama
 - trl
+- sft
 base_model: beratcmn/Llama-3-11.5B
 ---
-# Llama-3-11.5B
-
-This model is a Proof of Concept. First 2 Llama-3-8B models has been merged using `Mergekit` and pre-training continued using `QLora` and `Unsloth` for 1000 samples from `roneneldan/TinyStories`.
-Loss still decreases each epoch so I believe this is a successful experiment where there is a lot of room to experiment. 
-
-Llama-3-11.5B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
-* [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
-
-## 🧩 Configuration
-
-```yaml
-slices:
-  - sources:
-    - model: meta-llama/Meta-Llama-3-8B
-      layer_range: [0, 24]
-  - sources:
-    - model: meta-llama/Meta-Llama-3-8B
-      layer_range: [8, 32]
-merge_method: passthrough
-dtype: bfloat16
-```
-
-## 💻 Usage
-
-```python
-!pip install -qU transformers accelerate
-
-from transformers import AutoTokenizer
-import transformers
-import torch
-
-model = "beratcmn/Llama-3-11.5B"
-messages = [{"role": "user", "content": "What is a large language model?"}]
-
-tokenizer = AutoTokenizer.from_pretrained(model)
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    torch_dtype=torch.float16,
-    device_map="auto",
-)
-
-outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
-print(outputs[0]["generated_text"])
-```
 
 # Uploaded  model
 

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "beratcmn/Llama-3-11.5B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0",
+  "unsloth_version": "2024.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.40.0"
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eabdf98b46ed2e246a5d84875545ad7b88ec9ddd6ed3e60c9a1a1ebf08cf0f70
+size 4976718466

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2ea519a6f8d7925089542b186366a41f4724f90cdaa755704505e288a9d501
+size 4999827206

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8fbdf0495d48e220ee879089bed887eb63cdd11a94829370a95db60a1227261
+size 4915939082

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64bb57b125808c694af95806f63769166ab50132f08838e1f8fc05365733c881
+size 4999843656

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6978434f5954774b95009c1a2fb6d1dab8c8af9216d9efe1fafac56e7e4f4c0a
+size 3147930224

pytorch_model.bin.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 23040106496
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00005-of-00005.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.norm.weight": "pytorch_model-00005-of-00005.bin"
+  }
+}