初始化项目，由ModelHub XC社区提供模型

Model: AI-ModelScope/granite-20b-code-base-8k
Source: Original Platform

.gitattributes

@@ -0,0 +1,44 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,287 @@
+---
+datasets:
+- codeparrot/github-code-clean
+- bigcode/starcoderdata
+- open-web-math/open-web-math
+- math-ai/StackMathQA
+inference: true
+library_name: transformers
+license: apache-2.0
+metrics:
+- code_eval
+model-index:
+- name: granite-20b-code-base-8k
+  results:
+  - dataset:
+      name: MBPP
+      type: mbpp
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 43.8
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: MBPP+
+      type: evalplus/mbppplus
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 51.6
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 48.2
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalSynthesis(JavaScript)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 50.0
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalSynthesis(Java)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 59.1
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalSynthesis(Go)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 32.3
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalSynthesis(C++)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 40.9
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalSynthesis(Rust)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 35.4
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalExplain(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 17.1
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalExplain(JavaScript)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 18.3
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalExplain(Java)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 23.2
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalExplain(Go)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 10.4
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalExplain(C++)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 25.6
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalExplain(Rust)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 18.3
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalFix(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 23.2
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalFix(JavaScript)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 23.8
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalFix(Java)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 14.6
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalFix(Go)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 26.2
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalFix(C++)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 15.2
+      veriefied: false
+    task:
+      type: text-generation
+  - dataset:
+      name: HumanEvalFix(Rust)
+      type: bigcode/humanevalpack
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 3.0
+      veriefied: false
+    task:
+      type: text-generation
+pipeline_tag: text-generation
+tags:
+- code
+- granite
+---
+
+---
+
+# ⚠️ DEPRECATION WARNING ⚠️
+# ⚠️ NOT RECOMMENDED FOR USE IN NEW PROJECTS ⚠️
+
+New applications/projects should use the latest mainline Granite language model family, whose code capabilities supercede this model. 
+This model is being made available strictly for historical/scientific purposes. 
+**Please see our [Granite Collections](https://huggingface.co/ibm-granite/collections) for the latest Granite releases.**
+
+---
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png)
+
+# Granite-20B-Code-Base-8K
+
+## Model Summary
+**Granite-20B-Code-Base-8K** is a decoder-only code model designed for code generative tasks (e.g., code generation, code explanation, code fixing, etc.). It is trained from scratch with a two-phase training strategy. In phase 1, our model is trained on 3 trillion tokens sourced from 116 programming languages, ensuring a comprehensive understanding of programming languages and syntax. In phase 2, our model is trained on 500 billion tokens with a carefully designed mixture of high-quality data from code and natural language domains to improve the models’ ability to reason and follow instructions.
+
+- **Developers:** IBM Research
+- **GitHub Repository:** [ibm-granite/granite-code-models](https://github.com/ibm-granite/granite-code-models)
+- **Paper:** [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://arxiv.org/abs/2405.04324)
+- **Release Date**: May 6th, 2024
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0).
+
+## Usage
+### Intended use
+Prominent enterprise use cases of LLMs in software engineering productivity include code generation, code explanation, code fixing, generating unit tests, generating documentation, addressing technical debt issues, vulnerability detection, code translation, and more. All Granite Code Base models, including the **20B parameter model**, are able to handle these tasks as they were trained on a large amount of code data from 116 programming languages. 
+
+### Generation
+This is a simple example of how to use **Granite-20B-Code-Base-8K** model.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda" # or "cpu"
+model_path = "ibm-granite/granite-20b-code-base-8k"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+# drop device_map if running on CPU
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
+model.eval()
+# change input text as desired
+input_text = "def generate():"
+# tokenize the text
+input_tokens = tokenizer(input_text, return_tensors="pt")
+# transfer tokenized inputs to the device
+for i in input_tokens:
+    input_tokens[i] = input_tokens[i].to(device)
+# generate output tokens
+output = model.generate(**input_tokens)
+# decode output tokens into text
+output = tokenizer.batch_decode(output)
+# loop over the batch to print, in this example the batch size is 1
+for i in output:
+    print(i)
+```
+
+## Training Data
+- **Data Collection and Filtering:** Pretraining code data is sourced from a combination of publicly available datasets (e.g., [GitHub Code Clean](https://huggingface.co/datasets/codeparrot/github-code-clean), [Starcoder data](https://huggingface.co/datasets/bigcode/starcoderdata)), and additional public code repositories and issues from GitHub. We filter raw data to retain a list of 116 programming languages. After language filtering, we also filter out low-quality code. 
+- **Exact and Fuzzy Deduplication:** We adopt an aggressive deduplication strategy that includes both exact and fuzzy deduplication to remove documents having (near) identical code content.
+- **HAP, PII, Malware Filtering:** We apply a HAP content filter that reduces models' likelihood of generating hateful, abusive, or profane language. We also make sure to redact Personally Identifiable Information (PII) by replacing PII content (e.g., names, email addresses, keys, passwords) with corresponding tokens (e.g., ⟨NAME⟩, ⟨EMAIL⟩, ⟨KEY⟩, ⟨PASSWORD⟩). Moreover, we scan all datasets using [ClamAV](https://www.clamav.net/) to identify and remove instances of malware in the source code.
+- **Natural Language Datasets:** In addition to collecting code data for model training, we curate several publicly available high-quality natural language datasets to improve models' proficiency in language understanding and mathematical reasoning. Unlike the code data, we do not deduplicate these datasets.
+
+## Infrastructure
+We train the Granite Code models using two of IBM's super computing clusters, namely Vela and Blue Vela, both outfitted with NVIDIA A100 and H100 GPUs respectively. These clusters provide a scalable and efficient infrastructure for training our models over thousands of GPUs.
+
+## Ethical Considerations and Limitations
+The use of Large Language Models involves risks and ethical considerations people must be aware of. Regarding code generation, caution is urged against complete reliance on specific code models for crucial decisions or impactful information as the generated code is not guaranteed to work as intended. **Granite-20B-Code-Base-8K** model is not the exception in this regard. Even though this model is suited for multiple code-related tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying source code verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use **Granite-20B-Code-Base-8K** model with ethical intentions and in a responsible way. 

config.json

@@ -0,0 +1,28 @@
+{
+  "activation_function": "gelu",
+  "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,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "scale_attn_weights": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b893e90be19cc42647f7d76caef1bd7101b6904df709b93472265fa6e41594
+size 4952185256

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7f98d43d5aa8531381ffd2b7995008f1471a707a57becf638d089c549edec8
+size 4930227792

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f56c8969bbdc7995f1c61123f4b63da7ff202a93e40fde98121ec9ccdc49556
+size 4927118464

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7060b8fac28950098ce792fc518a0a8af296f47e22709ccaad1ce8216591ea
+size 4930227864

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd071ecf07518991d9d82749d9c864a7e923eb82450048565e9121604f4cbe2
+size 4927118464

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a0e75fbd4db5862a20e23ce6ffbf69a4a28d59505085b8d82c1d61620cbf98
+size 4930227864

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fee8bebaf2202e65cd8253898b317fc4a03a5a5cfb5bd6a01ccbf76a65d7c8b
+size 4927118464

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa8ce48dbb754a3e762d10d3590c65fb0eb30b6f28044f37ad184c335ff6916
+size 4930227864

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f5a5189fb992fb52b72861f432dc19123bef17f78c42e1db8a89b208b4b5ab
+size 679601176

model.safetensors.index.json

@@ -0,0 +1,635 @@
+{
+  "metadata": {
+    "total_size": 40133986304
+  },
+  "weight_map": {
+    "transformer.h.0.attn.c_attn.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.0.attn.c_attn.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.0.attn.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.0.attn.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.1.attn.c_attn.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.1.attn.c_attn.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.1.attn.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.1.attn.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.10.attn.c_attn.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.10.attn.c_attn.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.10.attn.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.10.attn.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.11.attn.c_attn.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.11.attn.c_attn.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.11.attn.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.11.attn.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.12.attn.c_attn.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.12.attn.c_attn.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.12.attn.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.12.attn.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.13.attn.c_attn.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.13.attn.c_attn.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.13.attn.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.13.attn.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.14.attn.c_attn.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.14.attn.c_attn.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.14.attn.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.14.attn.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.15.attn.c_attn.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.15.attn.c_attn.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.15.attn.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.15.attn.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.16.attn.c_attn.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.16.attn.c_attn.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.16.attn.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.16.attn.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.17.attn.c_attn.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.17.attn.c_attn.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.17.attn.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.17.attn.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.18.attn.c_attn.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.18.attn.c_attn.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.18.attn.c_proj.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.18.attn.c_proj.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.19.attn.c_attn.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.19.attn.c_attn.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.19.attn.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.19.attn.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.2.attn.c_attn.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.2.attn.c_attn.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.2.attn.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.2.attn.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.20.attn.c_attn.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.20.attn.c_attn.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.20.attn.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.20.attn.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.21.attn.c_attn.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.21.attn.c_attn.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.21.attn.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.21.attn.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.22.attn.c_attn.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.22.attn.c_attn.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.22.attn.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.22.attn.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.23.attn.c_attn.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.23.attn.c_attn.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.23.attn.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.23.attn.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.24.attn.c_attn.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.24.attn.c_attn.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.24.attn.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.24.attn.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.24.ln_2.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.24.ln_2.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.24.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.24.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.24.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.24.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.25.attn.c_attn.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.25.attn.c_attn.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.25.attn.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.25.attn.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00004-of-00009.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00004-of-00009.safetensors",
+    "transformer.h.25.ln_2.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.25.ln_2.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.25.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.25.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.25.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.25.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.26.attn.c_attn.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.26.attn.c_attn.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.26.attn.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.26.attn.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.26.ln_2.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.26.ln_2.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.26.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.26.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.26.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.26.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.27.attn.c_attn.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.27.attn.c_attn.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.27.attn.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.27.attn.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.27.ln_2.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.27.ln_2.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.27.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.27.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.27.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.27.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.28.attn.c_attn.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.28.attn.c_attn.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.28.attn.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.28.attn.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.28.ln_2.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.28.ln_2.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.28.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.28.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.28.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.28.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.29.attn.c_attn.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.29.attn.c_attn.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.29.attn.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.29.attn.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.29.ln_2.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.29.ln_2.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.29.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.29.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.29.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.29.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.3.attn.c_attn.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.3.attn.c_attn.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.3.attn.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.3.attn.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.30.attn.c_attn.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.30.attn.c_attn.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.30.attn.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.30.attn.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.30.ln_1.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.30.ln_1.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.30.ln_2.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.30.ln_2.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.30.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.30.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.30.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.30.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.31.attn.c_attn.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.31.attn.c_attn.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.31.attn.c_proj.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.31.attn.c_proj.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.31.ln_1.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.31.ln_1.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.31.ln_2.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.31.ln_2.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.31.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
+    "transformer.h.31.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
+    "transformer.h.31.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.31.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.32.attn.c_attn.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.32.attn.c_attn.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.32.attn.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.32.attn.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.32.ln_1.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.32.ln_1.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.32.ln_2.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.32.ln_2.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.32.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.32.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.32.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.32.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.33.attn.c_attn.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.33.attn.c_attn.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.33.attn.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.33.attn.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.33.ln_1.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.33.ln_1.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.33.ln_2.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.33.ln_2.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.33.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.33.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.33.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.33.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.34.attn.c_attn.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.34.attn.c_attn.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.34.attn.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.34.attn.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.34.ln_1.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.34.ln_1.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.34.ln_2.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.34.ln_2.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.34.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.34.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.34.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.34.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.35.attn.c_attn.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.35.attn.c_attn.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.35.attn.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.35.attn.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.35.ln_1.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.35.ln_1.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.35.ln_2.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.35.ln_2.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.35.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.35.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.35.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.35.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.36.attn.c_attn.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.36.attn.c_attn.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.36.attn.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.36.attn.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.36.ln_1.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.36.ln_1.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.36.ln_2.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.36.ln_2.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.36.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.36.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.36.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.36.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.37.attn.c_attn.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.37.attn.c_attn.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.37.attn.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.37.attn.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.37.ln_1.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.37.ln_1.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.37.ln_2.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.37.ln_2.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.37.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.37.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.37.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.37.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.38.attn.c_attn.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.38.attn.c_attn.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.38.attn.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.38.attn.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.38.ln_1.bias": "model-00006-of-00009.safetensors",
+    "transformer.h.38.ln_1.weight": "model-00006-of-00009.safetensors",
+    "transformer.h.38.ln_2.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.38.ln_2.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.38.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.38.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.38.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.38.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.39.attn.c_attn.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.39.attn.c_attn.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.39.attn.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.39.attn.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.39.ln_1.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.39.ln_1.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.39.ln_2.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.39.ln_2.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.39.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.39.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.39.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.39.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.4.attn.c_attn.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.4.attn.c_attn.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.4.attn.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.4.attn.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.40.attn.c_attn.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.40.attn.c_attn.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.40.attn.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.40.attn.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.40.ln_1.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.40.ln_1.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.40.ln_2.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.40.ln_2.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.40.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.40.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.40.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.40.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.41.attn.c_attn.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.41.attn.c_attn.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.41.attn.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.41.attn.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.41.ln_1.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.41.ln_1.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.41.ln_2.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.41.ln_2.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.41.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.41.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.41.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.41.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.42.attn.c_attn.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.42.attn.c_attn.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.42.attn.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.42.attn.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.42.ln_1.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.42.ln_1.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.42.ln_2.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.42.ln_2.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.42.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.42.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.42.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.42.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.43.attn.c_attn.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.43.attn.c_attn.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.43.attn.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.43.attn.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.43.ln_1.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.43.ln_1.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.43.ln_2.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.43.ln_2.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.43.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.43.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.43.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.43.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.44.attn.c_attn.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.44.attn.c_attn.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.44.attn.c_proj.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.44.attn.c_proj.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.44.ln_1.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.44.ln_1.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.44.ln_2.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.44.ln_2.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.44.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
+    "transformer.h.44.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
+    "transformer.h.44.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.44.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.45.attn.c_attn.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.45.attn.c_attn.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.45.attn.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.45.attn.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.45.ln_1.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.45.ln_1.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.45.ln_2.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.45.ln_2.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.45.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.45.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.45.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.45.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.46.attn.c_attn.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.46.attn.c_attn.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.46.attn.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.46.attn.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.46.ln_1.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.46.ln_1.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.46.ln_2.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.46.ln_2.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.46.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.46.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.46.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.46.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.47.attn.c_attn.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.47.attn.c_attn.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.47.attn.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.47.attn.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.47.ln_1.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.47.ln_1.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.47.ln_2.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.47.ln_2.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.47.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.47.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.47.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.47.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.48.attn.c_attn.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.48.attn.c_attn.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.48.attn.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.48.attn.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.48.ln_1.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.48.ln_1.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.48.ln_2.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.48.ln_2.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.48.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.48.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.48.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.48.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.49.attn.c_attn.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.49.attn.c_attn.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.49.attn.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.49.attn.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.49.ln_1.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.49.ln_1.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.49.ln_2.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.49.ln_2.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.49.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.49.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.49.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.49.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.5.attn.c_attn.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.5.attn.c_attn.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.5.attn.c_proj.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.5.attn.c_proj.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.50.attn.c_attn.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.50.attn.c_attn.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.50.attn.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.50.attn.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.50.ln_1.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.50.ln_1.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.50.ln_2.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.50.ln_2.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.50.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.50.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.50.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.50.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.51.attn.c_attn.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.51.attn.c_attn.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.51.attn.c_proj.bias": "model-00009-of-00009.safetensors",
+    "transformer.h.51.attn.c_proj.weight": "model-00009-of-00009.safetensors",
+    "transformer.h.51.ln_1.bias": "model-00008-of-00009.safetensors",
+    "transformer.h.51.ln_1.weight": "model-00008-of-00009.safetensors",
+    "transformer.h.51.ln_2.bias": "model-00009-of-00009.safetensors",
+    "transformer.h.51.ln_2.weight": "model-00009-of-00009.safetensors",
+    "transformer.h.51.mlp.c_fc.bias": "model-00009-of-00009.safetensors",
+    "transformer.h.51.mlp.c_fc.weight": "model-00009-of-00009.safetensors",
+    "transformer.h.51.mlp.c_proj.bias": "model-00009-of-00009.safetensors",
+    "transformer.h.51.mlp.c_proj.weight": "model-00009-of-00009.safetensors",
+    "transformer.h.6.attn.c_attn.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.6.attn.c_attn.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.6.attn.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.6.attn.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.7.attn.c_attn.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.7.attn.c_attn.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.7.attn.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.7.attn.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.8.attn.c_attn.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.8.attn.c_attn.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.8.attn.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.8.attn.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.9.attn.c_attn.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.9.attn.c_attn.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.9.attn.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.9.attn.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
+    "transformer.ln_f.bias": "model-00009-of-00009.safetensors",
+    "transformer.ln_f.weight": "model-00009-of-00009.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00009.safetensors",
+    "transformer.wte.weight": "model-00001-of-00009.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 +1,187 @@
+{
+  "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|>",
+  "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
+}