Upload folder using huggingface_hub (#1)

- 3a1a66d4a5b6bc8fa3b86543ba7614c1c8785e8fe12b57f14779df9840c9ca0a (1f8b31d5feac17bdc69d1c2ca107e220753fbc03)
- bac8cd6c0352d4fa12889a50918effd65a1da5e4241ced4fa44e097c1254ce8a (81ddd2ecf1a65d5640a41c7c487a5168ebf641bd)
- fc4ce6e16d5a2af3ca98185a72b5e80ce1183b57799e8fb13ac915aeacb48102 (f747bfb969030ed0929014fcfd02d1bfe06ace0b)
- e7737938e26e177075017ceabd4d2afe9b17bc84a11893df7087b542fcdcc49d (8c6864b92d82fbaf638d3d84a4d4a082e5b9bcb2)
- aa51a09f4fa8cae54745cf156ad35f46c16e6c18ce6bdcac7fee79d1c9eb6d3f (550895f3955fd2a0d79754bf09282e5240416bbe)

README.md

@@ -0,0 +1,102 @@
+---
+license: apache-2.0
+library_name: transformers
+tags:
+- code
+- granite
+- mlx
+base_model: ibm-granite/granite-20b-code-base
+datasets:
+- bigcode/commitpackft
+- TIGER-Lab/MathInstruct
+- meta-math/MetaMathQA
+- glaiveai/glaive-code-assistant-v3
+- glaive-function-calling-v2
+- bugdaryan/sql-create-context-instruction
+- garage-bAInd/Open-Platypus
+- nvidia/HelpSteer
+metrics:
+- code_eval
+pipeline_tag: text-generation
+inference: true
+model-index:
+- name: granite-20b-code-instruct
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 60.4
+      name: pass@1
+    - type: pass@1
+      value: 53.7
+      name: pass@1
+    - type: pass@1
+      value: 58.5
+      name: pass@1
+    - type: pass@1
+      value: 42.1
+      name: pass@1
+    - type: pass@1
+      value: 45.7
+      name: pass@1
+    - type: pass@1
+      value: 42.7
+      name: pass@1
+    - type: pass@1
+      value: 44.5
+      name: pass@1
+    - type: pass@1
+      value: 42.7
+      name: pass@1
+    - type: pass@1
+      value: 49.4
+      name: pass@1
+    - type: pass@1
+      value: 32.3
+      name: pass@1
+    - type: pass@1
+      value: 42.1
+      name: pass@1
+    - type: pass@1
+      value: 18.3
+      name: pass@1
+    - type: pass@1
+      value: 43.9
+      name: pass@1
+    - type: pass@1
+      value: 43.9
+      name: pass@1
+    - type: pass@1
+      value: 45.7
+      name: pass@1
+    - type: pass@1
+      value: 41.5
+      name: pass@1
+    - type: pass@1
+      value: 41.5
+      name: pass@1
+    - type: pass@1
+      value: 29.9
+      name: pass@1
+---
+
+# mlx-community/granite-20b-code-instruct-8bit
+
+The Model [mlx-community/granite-20b-code-instruct-8bit](https://huggingface.co/mlx-community/granite-20b-code-instruct-8bit) was converted to MLX format from [ibm-granite/granite-20b-code-instruct](https://huggingface.co/ibm-granite/granite-20b-code-instruct) using mlx-lm version **0.13.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/granite-20b-code-instruct-8bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,32 @@
+{
+    "activation_function": "gelu_pytorch_tanh",
+    "architectures": [
+        "GPTBigCodeForCausalLM"
+    ],
+    "attention_softmax_in_fp32": true,
+    "attn_pdrop": 0.1,
+    "bos_token_id": 0,
+    "embd_pdrop": 0.1,
+    "eos_token_id": 0,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "model_type": "gpt_bigcode",
+    "multi_query": true,
+    "n_embd": 6144,
+    "n_head": 48,
+    "n_inner": 24576,
+    "n_layer": 52,
+    "n_positions": 8192,
+    "pad_token_id": 0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "resid_pdrop": 0.1,
+    "scale_attention_softmax_in_fp32": true,
+    "scale_attn_weights": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.41.0.dev0",
+    "use_cache": true,
+    "vocab_size": 49152
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:675138c2f03fe5bc2fe0861d710bc13e9c678e382943b5a1aa45c34e708c7dba
+size 5290926981

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3533937d1c589ff7e0bf5f29bc9228f65ed6af325c5807042c87a26361d2cb47
+size 5237561094

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a88c3c24245751fa6f16c355f2004c4c649b2e3c80038439d8a13e95887733
+size 5237561096

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548ce9461f2cd7439787dde95b5eac9599f7ff709d3dff25c0f0dd34858b366f
+size 5237561110

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167bdbf1b79aea4cd72394e5dce98f53601521371a80dc1a978278306ca4d81c
+size 321000883

model.safetensors.index.json

@@ -0,0 +1,1055 @@
+{
+    "metadata": {
+        "total_size": 21324498944
+    },
+    "weight_map": {
+        "transformer.h.0.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.0.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.0.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.0.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.0.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.0.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.0.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.0.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.0.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.0.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.0.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.0.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.0.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.0.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.0.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.0.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.1.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.1.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.1.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.1.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.1.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.1.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.1.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.1.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.1.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.1.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.1.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.1.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.1.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.1.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.1.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.1.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.10.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.10.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.10.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.10.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.10.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.10.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.10.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.10.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.10.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.10.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.10.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.10.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.10.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.10.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.10.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.10.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.11.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.11.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.11.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.11.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.11.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.11.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.11.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.11.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.11.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.11.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.11.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.11.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.11.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.11.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.11.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.11.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.12.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.12.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.12.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.12.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.12.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.12.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.12.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.12.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.12.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.12.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.12.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.12.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.12.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.12.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.12.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.12.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.12.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.12.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.12.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.12.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.13.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.13.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.13.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.13.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.13.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.13.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.13.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.13.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.13.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.13.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.13.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.13.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.13.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.13.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.13.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.13.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.13.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.13.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.13.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.14.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.14.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.14.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.14.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.14.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.14.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.14.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.14.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.14.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.14.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.14.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.14.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.14.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.14.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.14.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.14.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.15.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.15.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.15.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.15.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.15.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.15.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.15.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.15.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.15.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.15.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.15.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.15.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.15.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.15.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.15.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.15.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.16.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.16.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.16.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.16.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.16.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.16.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.16.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.16.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.16.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.16.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.16.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.16.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.16.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.16.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.16.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.16.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.17.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.17.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.17.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.17.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.17.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.17.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.17.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.17.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.17.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.17.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.17.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.17.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.17.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.17.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.17.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.17.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.18.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.18.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.18.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.18.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.18.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.18.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.18.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.18.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.18.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.18.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.18.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.18.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.18.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.18.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.18.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.18.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.19.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.19.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.19.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.19.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.19.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.19.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.19.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.19.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.19.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.19.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.19.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.19.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.19.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.19.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.19.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.19.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.2.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.2.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.2.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.2.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.2.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.2.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.2.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.2.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.2.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.2.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.2.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.2.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.2.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.2.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.2.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.2.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.20.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.20.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.20.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.20.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.20.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.20.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.20.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.20.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.20.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.20.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.20.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.20.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.20.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.20.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.20.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.20.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.21.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.21.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.21.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.21.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.21.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.21.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.21.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.21.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.21.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.21.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.21.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.21.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.21.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.21.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.21.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.21.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.22.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.22.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.22.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.22.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.22.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.22.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.22.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.22.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.22.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.22.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.22.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.22.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.22.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.22.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.22.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.22.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.23.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.23.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.23.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.23.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.23.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.23.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.23.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.23.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.23.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.23.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.23.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.23.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.23.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.23.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.23.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.23.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.24.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.24.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.24.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.24.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.24.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.24.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.24.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.24.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.24.ln_1.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.24.ln_1.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.24.ln_2.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.24.ln_2.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.24.mlp.c_fc.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.24.mlp.c_fc.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.24.mlp.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.24.mlp.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.25.attn.c_attn.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.25.attn.c_attn.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.25.attn.c_attn.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.25.attn.c_attn.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.25.attn.c_proj.bias": "model-00002-of-00005.safetensors",
+        "transformer.h.25.attn.c_proj.biases": "model-00002-of-00005.safetensors",
+        "transformer.h.25.attn.c_proj.scales": "model-00002-of-00005.safetensors",
+        "transformer.h.25.attn.c_proj.weight": "model-00002-of-00005.safetensors",
+        "transformer.h.25.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.25.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.25.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.25.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.25.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.25.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.25.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.25.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.25.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.25.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.25.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.25.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.26.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.26.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.26.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.26.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.26.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.26.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.26.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.26.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.26.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.26.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.26.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.26.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.26.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.26.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.26.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.26.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.26.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.26.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.26.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.26.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.27.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.27.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.27.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.27.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.27.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.27.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.27.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.27.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.27.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.27.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.27.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.27.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.27.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.27.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.27.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.27.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.27.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.27.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.27.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.27.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.28.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.28.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.28.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.28.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.28.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.28.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.28.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.28.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.28.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.28.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.28.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.28.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.28.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.28.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.28.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.28.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.28.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.28.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.28.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.28.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.29.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.29.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.29.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.29.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.29.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.29.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.29.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.29.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.29.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.29.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.29.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.29.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.29.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.29.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.29.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.29.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.29.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.29.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.29.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.29.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.3.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.3.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.3.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.3.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.3.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.3.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.3.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.3.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.3.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.3.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.3.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.3.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.3.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.3.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.3.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.3.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.30.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.30.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.30.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.30.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.30.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.30.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.30.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.30.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.30.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.30.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.30.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.30.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.30.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.30.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.30.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.30.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.31.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.31.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.31.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.31.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.31.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.31.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.31.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.31.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.31.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.31.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.31.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.31.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.31.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.31.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.31.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.31.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.32.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.32.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.32.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.32.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.32.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.32.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.32.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.32.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.32.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.32.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.32.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.32.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.32.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.32.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.32.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.32.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.32.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.32.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.32.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.32.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.33.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.33.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.33.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.33.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.33.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.33.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.33.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.33.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.33.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.33.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.33.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.33.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.33.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.33.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.33.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.33.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.33.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.33.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.33.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.33.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.34.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.34.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.34.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.34.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.34.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.34.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.34.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.34.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.34.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.34.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.34.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.34.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.34.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.34.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.34.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.34.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.34.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.34.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.34.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.34.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.35.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.35.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.35.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.35.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.35.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.35.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.35.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.35.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.35.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.35.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.35.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.35.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.35.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.35.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.35.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.35.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.35.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.35.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.35.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.35.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.36.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.36.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.36.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.36.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.36.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.36.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.36.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.36.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.36.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.36.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.36.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.36.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.36.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.36.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.36.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.36.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.36.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.36.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.36.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.36.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.37.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.37.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.37.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.37.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.37.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.37.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.37.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.37.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.37.ln_1.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.37.ln_1.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.37.ln_2.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.37.ln_2.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.37.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.37.mlp.c_fc.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.37.mlp.c_fc.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.37.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.37.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.37.mlp.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.37.mlp.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.37.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.38.attn.c_attn.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.38.attn.c_attn.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.38.attn.c_attn.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.38.attn.c_attn.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.38.attn.c_proj.bias": "model-00003-of-00005.safetensors",
+        "transformer.h.38.attn.c_proj.biases": "model-00003-of-00005.safetensors",
+        "transformer.h.38.attn.c_proj.scales": "model-00003-of-00005.safetensors",
+        "transformer.h.38.attn.c_proj.weight": "model-00003-of-00005.safetensors",
+        "transformer.h.38.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.38.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.38.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.38.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.38.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.38.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.38.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.38.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.38.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.38.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.38.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.38.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.39.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.39.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.39.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.39.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.39.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.39.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.39.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.39.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.39.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.39.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.39.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.39.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.39.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.39.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.39.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.39.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.39.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.39.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.39.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.39.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.4.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.4.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.4.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.4.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.4.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.4.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.4.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.4.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.4.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.4.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.4.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.4.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.4.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.4.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.4.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.4.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.40.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.40.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.40.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.40.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.40.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.40.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.40.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.40.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.40.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.40.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.40.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.40.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.40.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.40.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.40.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.40.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.40.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.40.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.40.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.40.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.41.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.41.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.41.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.41.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.41.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.41.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.41.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.41.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.41.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.41.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.41.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.41.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.41.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.41.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.41.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.41.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.41.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.41.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.41.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.41.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.42.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.42.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.42.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.42.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.42.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.42.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.42.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.42.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.42.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.42.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.42.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.42.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.42.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.42.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.42.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.42.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.42.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.42.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.42.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.42.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.43.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.43.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.43.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.43.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.43.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.43.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.43.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.43.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.43.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.43.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.43.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.43.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.43.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.43.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.43.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.43.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.43.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.43.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.43.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.43.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.44.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.44.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.44.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.44.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.44.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.44.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.44.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.44.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.44.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.44.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.44.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.44.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.44.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.44.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.44.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.44.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.44.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.44.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.44.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.44.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.45.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.45.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.45.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.45.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.45.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.45.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.45.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.45.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.45.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.45.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.45.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.45.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.45.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.45.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.45.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.45.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.45.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.45.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.45.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.45.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.46.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.46.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.46.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.46.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.46.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.46.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.46.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.46.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.46.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.46.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.46.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.46.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.46.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.46.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.46.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.46.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.46.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.46.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.46.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.46.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.47.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.47.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.47.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.47.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.47.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.47.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.47.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.47.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.47.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.47.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.47.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.47.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.47.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.47.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.47.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.47.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.47.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.47.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.47.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.47.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.48.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.48.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.48.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.48.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.48.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.48.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.48.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.48.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.48.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.48.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.48.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.48.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.48.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.48.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.48.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.48.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.48.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.48.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.48.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.48.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.49.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.49.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.49.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.49.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.49.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.49.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.49.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.49.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.49.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.49.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.49.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.49.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.49.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.49.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.49.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.49.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.49.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.49.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.49.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.49.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.5.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.5.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.5.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.5.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.5.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.5.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.5.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.5.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.5.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.5.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.5.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.5.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.5.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.5.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.5.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.5.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.50.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.50.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.50.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.50.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.50.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.50.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.50.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.50.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.50.ln_1.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.50.ln_1.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.50.ln_2.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.50.ln_2.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.50.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.50.mlp.c_fc.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.50.mlp.c_fc.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.50.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.50.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.50.mlp.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.50.mlp.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.50.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.51.attn.c_attn.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.51.attn.c_attn.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.51.attn.c_attn.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.51.attn.c_attn.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.51.attn.c_proj.bias": "model-00004-of-00005.safetensors",
+        "transformer.h.51.attn.c_proj.biases": "model-00004-of-00005.safetensors",
+        "transformer.h.51.attn.c_proj.scales": "model-00004-of-00005.safetensors",
+        "transformer.h.51.attn.c_proj.weight": "model-00004-of-00005.safetensors",
+        "transformer.h.51.ln_1.bias": "model-00005-of-00005.safetensors",
+        "transformer.h.51.ln_1.weight": "model-00005-of-00005.safetensors",
+        "transformer.h.51.ln_2.bias": "model-00005-of-00005.safetensors",
+        "transformer.h.51.ln_2.weight": "model-00005-of-00005.safetensors",
+        "transformer.h.51.mlp.c_fc.bias": "model-00005-of-00005.safetensors",
+        "transformer.h.51.mlp.c_fc.biases": "model-00005-of-00005.safetensors",
+        "transformer.h.51.mlp.c_fc.scales": "model-00005-of-00005.safetensors",
+        "transformer.h.51.mlp.c_fc.weight": "model-00005-of-00005.safetensors",
+        "transformer.h.51.mlp.c_proj.bias": "model-00005-of-00005.safetensors",
+        "transformer.h.51.mlp.c_proj.biases": "model-00005-of-00005.safetensors",
+        "transformer.h.51.mlp.c_proj.scales": "model-00005-of-00005.safetensors",
+        "transformer.h.51.mlp.c_proj.weight": "model-00005-of-00005.safetensors",
+        "transformer.h.6.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.6.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.6.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.6.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.6.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.6.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.6.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.6.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.6.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.6.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.6.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.6.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.6.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.6.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.6.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.6.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.7.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.7.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.7.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.7.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.7.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.7.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.7.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.7.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.7.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.7.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.7.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.7.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.7.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.7.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.7.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.7.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.8.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.8.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.8.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.8.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.8.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.8.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.8.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.8.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.8.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.8.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.8.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.8.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.8.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.8.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.8.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.8.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.9.attn.c_attn.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.9.attn.c_attn.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.9.attn.c_attn.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.9.attn.c_attn.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.9.attn.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.9.attn.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.9.attn.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.9.attn.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.9.ln_1.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.9.ln_1.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.9.ln_2.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.9.ln_2.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.9.mlp.c_fc.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.9.mlp.c_fc.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00005.safetensors",
+        "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00005.safetensors",
+        "transformer.h.9.mlp.c_proj.biases": "model-00001-of-00005.safetensors",
+        "transformer.h.9.mlp.c_proj.scales": "model-00001-of-00005.safetensors",
+        "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00005.safetensors",
+        "transformer.ln_f.bias": "model-00005-of-00005.safetensors",
+        "transformer.ln_f.weight": "model-00005-of-00005.safetensors",
+        "transformer.wpe.biases": "model-00001-of-00005.safetensors",
+        "transformer.wpe.scales": "model-00001-of-00005.safetensors",
+        "transformer.wpe.weight": "model-00001-of-00005.safetensors",
+        "transformer.wte.biases": "model-00001-of-00005.safetensors",
+        "transformer.wte.scales": "model-00001-of-00005.safetensors",
+        "transformer.wte.weight": "model-00001-of-00005.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'Question:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'system' %}\n{{ 'System:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Answer:\n'  + message['content'] + '\n\n' }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Answer:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}