Upload 9 files

README.md

@@ -1,3 +1,636 @@
----
-license: llama2
----
+---
+license: llama2
+language:
+- ro
+base_model: meta-llama/Llama-2-7b-hf
+model-index:
+- name: OpenLLM-Ro/RoLlama2-7b-Base-2024-05-14
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: Romanian_Academic_Benchmarks
+      type: Romanian_Academic_Benchmarks
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 38.03
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 37.95
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 27.22
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 59.29
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 57.22
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 2.53
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_truthfulqa
+      type: OpenLLM-Ro/ro_truthfulqa
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 44
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 83.25
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass
+      type: LaRoSeDa_multiclass
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 61.04
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary_finetuned
+      type: LaRoSeDa_binary_finetuned
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 98.97
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass_finetuned
+      type: LaRoSeDa_multiclass_finetuned
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 87.72
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 10.01
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN
+      type: WMT_RO-EN
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 13.03
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO_finetuned
+      type: WMT_EN-RO_finetuned
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 27.85
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN_finetuned
+      type: WMT_RO-EN_finetuned
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 39.3
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - name: Average exact_match
+      type: exact_match
+      value: 30.15
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - name: Average f1
+      type: f1
+      value: 47.03
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_finetuned
+      type: XQuAD_finetuned
+    metrics:
+    - name: Average exact_match
+      type: exact_match
+      value: 67.06
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_finetuned
+      type: XQuAD_finetuned
+    metrics:
+    - name: Average f1
+      type: f1
+      value: 79.96
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: Average spearman
+      type: spearman
+      value: 7.89
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: Average pearson
+      type: pearson
+      value: 7.98
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_finetuned
+      type: STS_finetuned
+    metrics:
+    - name: Average spearman
+      type: spearman
+      value: 71.75
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_finetuned
+      type: STS_finetuned
+    metrics:
+    - name: Average pearson
+      type: pearson
+      value: 71.99
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 35.56
+    - name: 1-shot
+      type: accuracy
+      value: 36.42
+    - name: 3-shot
+      type: accuracy
+      value: 38.56
+    - name: 5-shot
+      type: accuracy
+      value: 38.39
+    - name: 10-shot
+      type: accuracy
+      value: 39.07
+    - name: 25-shot
+      type: accuracy
+      value: 39.67
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 25.82
+    - name: 1-shot
+      type: accuracy
+      value: 25.48
+    - name: 3-shot
+      type: accuracy
+      value: 27.61
+    - name: 5-shot
+      type: accuracy
+      value: 29.96
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 58.72
+    - name: 1-shot
+      type: accuracy
+      value: 58.88
+    - name: 3-shot
+      type: accuracy
+      value: 60.38
+    - name: 5-shot
+      type: accuracy
+      value: 59.19
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 55.85
+    - name: 1-shot
+      type: accuracy
+      value: 57.06
+    - name: 3-shot
+      type: accuracy
+      value: 57.52
+    - name: 5-shot
+      type: accuracy
+      value: 57.89
+    - name: 10-shot
+      type: accuracy
+      value: 57.79
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 0
+    - name: 1-shot
+      type: accuracy
+      value: 2.96
+    - name: 3-shot
+      type: accuracy
+      value: 4.62
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - name: 0-shot
+      type: macro-f1
+      value: 42.78
+    - name: 1-shot
+      type: macro-f1
+      value: 98
+    - name: 3-shot
+      type: macro-f1
+      value: 95.13
+    - name: 5-shot
+      type: macro-f1
+      value: 97.07
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass
+      type: LaRoSeDa_multiclass
+    metrics:
+    - name: 0-shot
+      type: macro-f1
+      value: 46.41
+    - name: 1-shot
+      type: macro-f1
+      value: 67.36
+    - name: 3-shot
+      type: macro-f1
+      value: 65.16
+    - name: 5-shot
+      type: macro-f1
+      value: 65.23
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - name: 0-shot
+      type: bleu
+      value: 4.45
+    - name: 1-shot
+      type: bleu
+      value: 8.61
+    - name: 3-shot
+      type: bleu
+      value: 12.25
+    - name: 5-shot
+      type: bleu
+      value: 14.73
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN
+      type: WMT_RO-EN
+    metrics:
+    - name: 0-shot
+      type: bleu
+      value: 1.29
+    - name: 1-shot
+      type: bleu
+      value: 10.78
+    - name: 3-shot
+      type: bleu
+      value: 16.82
+    - name: 5-shot
+      type: bleu
+      value: 23.24
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_EM
+      type: XQuAD_EM
+    metrics:
+    - name: 0-shot
+      type: exact_match
+      value: 5.29
+    - name: 1-shot
+      type: exact_match
+      value: 33.95
+    - name: 3-shot
+      type: exact_match
+      value: 39.24
+    - name: 5-shot
+      type: exact_match
+      value: 42.1
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_F1
+      type: XQuAD_F1
+    metrics:
+    - name: 0-shot
+      type: f1
+      value: 16.17
+    - name: 1-shot
+      type: f1
+      value: 51.84
+    - name: 3-shot
+      type: f1
+      value: 58.82
+    - name: 5-shot
+      type: f1
+      value: 61.29
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: 0-shot
+      type: spearman
+      value: -1.74
+    - name: 1-shot
+      type: spearman
+      value: 15.47
+    - name: 3-shot
+      type: spearman
+      value: 9.93
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: 0-shot
+      type: pearson
+      value: -1.4
+    - name: 1-shot
+      type: pearson
+      value: 15
+    - name: 3-shot
+      type: pearson
+      value: 10.33
+datasets:
+- uonlp/CulturaX
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+RoLlama2 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **foundational 7B model**. Links to other models can be found at the bottom of this page.
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+OpenLLM represents the first open-source effort to build a LLM specialized for Romanian. OpenLLM-Ro developed and publicly releases a collection of Romanian LLMs, both in the form of foundational model and instruct and chat variants.
+
+
+- **Developed by:** OpenLLM-Ro
+<!-- - **Funded by [optional]:** [More Information Needed] -->
+<!-- - **Shared by [optional]:** [More Information Needed] -->
+<!-- - **Model type:** [More Information Needed] -->
+- **Language(s):** Romanian
+- **License:** Llama2 Community License Agreement
+- **Continual pretrained from model:** [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf)
+- **Trained using:** [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX)
+
+
+### Model Sources
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** https://github.com/OpenLLM-Ro/llama-recipes
+- **Paper:** https://arxiv.org/abs/2406.18266
+
+## Intended Use
+
+### Intended Use Cases
+
+RoLlama2 is intented for research use in Romanian. Base models can be adapted for a variety of natural language tasks while instruction and chat tuned models are intended for assistant-like chat.
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+Use in any manner that violates the license, any applicable laws or regluations, use in languages other than Romanian.
+
+
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Base-2024-05-14")
+model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Base-2024-05-14")
+
+input_text = "Mihai Eminescu a fost "
+input_ids = tokenizer(input_text, return_tensors="pt")
+
+outputs = model.generate(**input_ids, max_new_tokens=100)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Academic Benchmarks
+
+<table>
+<tbody>
+<tr>
+<td><strong>Model</strong></td>
+<td><strong><center>Average</center></strong></td>
+<td><strong><center>ARC</center></strong></td>
+<td><strong><center>MMLU</center></strong></td>
+<td><strong><center>Winogrande</center></strong></td>
+<td><strong><center>Hellaswag</center></strong></td>
+<td><strong><center>GSM8k</center></strong></td>
+<td><strong><center>TruthfulQA</center></strong></td>
+</tr>
+<tr>
+<td>Llama-2-7b</td><td><center>37.04</center></td><td><center>36.05</center></td><td><center><strong>33.66</strong></center></td><td><center>57.56</center></td><td><center>48.00</center></td><td><center><strong>4.75</strong></center></td><td><center>42.22</center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Base-2024-05-14</em></td><td><center><em><strong>38.03</strong></em></center></td><td><center><em><strong>37.95</strong></em></center></td><td><center><em>27.22</em></center></td><td><center><em><strong>59.29</strong></em></center></td><td><center><em><strong>57.22</strong></em></center></td><td><center><em>2.53</em></center></td><td><center><em><strong>44.00</strong></em></center></td>
+</tr>
+</tbody>
+</table>
+
+## Downstream Tasks
+
+
+<table>
+<tbody>
+<tr>
+<td></td>
+<td colspan="4"><center><strong>LaRoSeDa</strong></center></td>
+<td colspan="4"><center><strong>WMT</strong></center></td>
+</tr>
+<tr>
+<td></td>
+<td colspan="2"><center><strong>Few-shot</strong></center></td>
+<td colspan="2"><center><strong>Finetuned</strong></center></td>
+<td colspan="2"><center><strong>Few-shot</strong></center></td>
+<td colspan="2"><center><strong>Finetuned</strong></center></td>
+</tr>
+<tr>
+<td><strong>Model</strong></td>
+<td><center><strong>Binary<br>(Macro F1)</strong></center></td>
+<td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
+<td><center><strong>Binary<br>(Macro F1)</strong></center></td>
+<td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
+<td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
+<td><center><strong>RO-EN<br>(Bleu)</strong></center></td>
+<td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
+<td><center><strong>RO-EN<br>(Bleu)</strong></center>
+</tr>
+<tr>
+<td>Llama-2-7b</td><td><center><strong>93.19</strong></center></td><td><center>54.11</center></td><td><center>98.43</center></td><td><center>87.22</center></td><td><center><strong>14.90</strong></center></td><td><center><strong>26.61</strong></center></td><td><center>24.95</center></td><td><center>39.09</center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Base-2024-05-14</em></td><td><center><em>83.25</em></center></td><td><center><em><strong>61.04</strong></em></center></td><td><center><em><strong>98.97</strong></em></center></td><td><center><em><strong>87.72</strong></em></center></td><td><center><em>10.01</em></center></td><td><center><em>13.03</em></center></td><td><center><em><strong>27.85</strong></em></center></td><td><center><em><strong>39.30</strong></em></center></td>
+</tr>
+</tbody>
+</table>
+
+
+<table>
+<tbody>
+<tr>
+<td></td>
+<td colspan="4"><center><strong>XQuAD</strong></center></td>
+<td colspan="4"><center><strong>STS</strong></center></td>
+</tr>
+<tr>
+<td></td>
+<td colspan="2"><center><strong>Few-shot</strong></center></td>
+<td colspan="2"><center><strong>Finetuned</strong></center></td>
+<td colspan="2"><center><strong>Few-shot</strong></center></td>
+<td colspan="2"><center><strong>Finetuned</strong></center></td>
+</tr>
+<tr>
+<td><strong>Model</strong></td>
+<td><center><strong>(EM)</strong></center></td>
+<td><center><strong>(F1)</strong></center></td>
+<td><center><strong>(EM)</strong></center></td>
+<td><center><strong>(F1)</strong></center></td>
+<td><center><strong>(Spearman)</strong></center></td>
+<td><center><strong>(Pearson)</strong></center></td>
+<td><center><strong>(Spearman)</strong></center></td>
+<td><center><strong>(Pearson)</strong></center></td>
+</tr>
+<tr>
+<td>Llama-2-7b</td><td><center><strong>38.91</strong></center></td><td><center><strong>56.82</strong></center></td><td><center>65.46</center></td><td><center>79.42</center></td><td><center><strong>9.08</strong></center></td><td><center><strong>9.07</strong></center></td><td><center><strong>79.93</strong></center></td><td><center><strong>81.08</strong></center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Base-2024-05-14</em></td><td><center><em>30.15</em></center></td><td><center><em>47.03</em></center></td><td><center><em><strong>67.06</strong></em></center></td><td><center><em><strong>79.96</strong></em></center></td><td><center><em>7.89</em></center></td><td><center><em>7.98</em></center></td><td><center><em>71.75</em></center></td><td><center><em>71.99</em></center></td>
+</tr>
+</tbody>
+</table>
+
+
+## RoLlama2 Model Family
+
+| Model              | Link  |
+|--------------------|:--------:|
+|RoLlama2-7b-Base-2024-05-14 | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base-2024-05-14)    |
+|RoLlama2-7b-Instruct-2024-05-14 | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2024-05-14)    |
+|*RoLlama2-7b-Instruct-2024-10-09*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2024-10-09) |
+|RoLlama2-7b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-DPO-2024-10-09) |
+
+## Citation 
+
+```
+@misc{masala2024vorbecstiromanecsterecipetrain,
+      title={"Vorbe\c{s}ti Rom\^ane\c{s}te?" A Recipe to Train Powerful Romanian LLMs with English Instructions}, 
+      author={Mihai Masala and Denis C. Ilie-Ablachim and Alexandru Dima and Dragos Corlatescu and Miruna Zavelca and Ovio Olaru and Simina Terian-Dan and Andrei Terian-Dan and Marius Leordeanu and Horia Velicu and Marius Popescu and Mihai Dascalu and Traian Rebedea},
+      year={2024},
+      eprint={2406.18266},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2406.18266}, 
+}
+```
+<!-- **APA:**
+
+[More Information Needed] -->

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26953662464
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_params.yaml

@@ -0,0 +1,35 @@
+batch_size_training: '32'
+checkpoint_type: StateDictType.FULL_STATE_DICT
+dataset: foundational_dataset
+dist_checkpoint_folder: fine-tuned
+dist_checkpoint_root_folder: test_run_save
+enable_fsdp: 'True'
+freeze_layers: 'False'
+fsdp_activation_checkpointing: 'True'
+gamma: '0.9'
+load_peft_model: 'False'
+low_cpu_fsdp: 'False'
+lr: '0.0001'
+micro_batch_size: '32'
+mixed_precision: 'True'
+model_name: models/v3/llama7b-full-1e-4_low-chunk1024-009-017
+num_epochs: '1'
+num_freeze_layers: '1'
+num_workers_dataloader: '2'
+one_gpu: 'False'
+optimizer: AdamW
+output_dir: PATH/to/save/PEFT/model
+peft_method: lora
+pure_bf16: 'True'
+quantization: 'False'
+run_validation: 'True'
+save_model: 'True'
+save_optimizer: 'False'
+seed: '42'
+sharding_strategy: ShardingStrategy.FULL_SHARD
+type_of_model: foundational
+use_fast_kernels: 'False'
+use_fp16: 'False'
+use_peft: 'False'
+val_batch_size: '64'
+weight_decay: '0.0'