Commit
·
f0dca8e
verified
·
0
Parent(s):
Duplicate from allenai/OLMo-2-0325-32B-Instruct
Browse filesCo-authored-by: Shengyi Costa Huang <[email protected]>
- .gitattributes +38 -0
- README.md +222 -0
- config.json +28 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +714 -0
- olmo-32b-instruct-eval-curve.png +0 -0
- olmo-32b-instruct-full-eval-curve.png +3 -0
- olmo-32b-instruct-learning-curve-time.png +3 -0
- olmo-32b-instruct-learning-curve.png +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +190 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
olmo-32b-instruct-full-eval-curve.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
olmo-32b-instruct-learning-curve-time.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
olmo-32b-instruct-learning-curve.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
datasets:
|
| 6 |
+
- allenai/RLVR-GSM-MATH-IF-Mixed-Constraints
|
| 7 |
+
base_model:
|
| 8 |
+
- allenai/OLMo-2-0325-32B-DPO
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
library_name: transformers
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<img alt="OLMo Logo" src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/olmo2/olmo.png" width="242px">
|
| 14 |
+
|
| 15 |
+
OLMo 2 32B Instruct March 2025 is post-trained variant of the [OLMo-2 32B March 2025](https://huggingface.co/allenai/OLMo-2-0325-32B/) model, which has undergone supervised finetuning on an OLMo-specific variant of the [Tülu 3 dataset](https://huggingface.co/datasets/allenai/tulu-3-sft-olmo-2-mixture), further DPO training on [this dataset](https://huggingface.co/datasets/allenai/olmo-2-0325-32b-preference-mix), and final RLVR training on [this dataset](https://huggingface.co/datasets/allenai/RLVR-GSM-MATH-IF-Mixed-Constraints).
|
| 16 |
+
Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval.
|
| 17 |
+
Check out the [OLMo 2 paper](https://arxiv.org/abs/2501.00656) or [Tülu 3 paper](https://arxiv.org/abs/2411.15124) for more details!
|
| 18 |
+
|
| 19 |
+
OLMo is a series of **O**pen **L**anguage **Mo**dels designed to enable the science of language models.
|
| 20 |
+
These models are trained on the Dolma dataset. We are releasing all code, checkpoints, logs, and associated training details.
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
- **Model type:** A model trained on a mix of publicly available, synthetic and human-created datasets.
|
| 26 |
+
- **Language(s) (NLP):** Primarily English
|
| 27 |
+
- **License:** Apache 2.0
|
| 28 |
+
- **Finetuned from model:** allenai/OLMo-2-0325-32B-DPO
|
| 29 |
+
|
| 30 |
+
### Model Sources
|
| 31 |
+
|
| 32 |
+
- **Project Page:** https://allenai.org/olmo
|
| 33 |
+
- **Repositories:**
|
| 34 |
+
- Core repo (training, inference, fine-tuning etc.): https://github.com/allenai/OLMo-core
|
| 35 |
+
- Evaluation code: https://github.com/allenai/olmes
|
| 36 |
+
- Further fine-tuning code: https://github.com/allenai/open-instruct
|
| 37 |
+
- **Paper:** https://arxiv.org/abs/2501.00656
|
| 38 |
+
- **Demo:** https://playground.allenai.org/
|
| 39 |
+
|
| 40 |
+
## Installation
|
| 41 |
+
|
| 42 |
+
OLMo 2 will be supported in the next version of Transformers, and you need to install it from the main branch using:
|
| 43 |
+
```bash
|
| 44 |
+
pip install --upgrade git+https://github.com/huggingface/transformers.git
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
## Using the model
|
| 48 |
+
|
| 49 |
+
### Loading with HuggingFace
|
| 50 |
+
|
| 51 |
+
To load the model with HuggingFace, use the following snippet:
|
| 52 |
+
```
|
| 53 |
+
from transformers import AutoModelForCausalLM
|
| 54 |
+
|
| 55 |
+
olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0325-32B-Instruct")
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
### Chat template
|
| 59 |
+
|
| 60 |
+
*NOTE: This is different than previous OLMo 2 and Tülu 3 models due to a minor change in configuration. It does NOT have the bos token before the rest. Our other models have <|endoftext|> at the beginning of the chat template.*
|
| 61 |
+
|
| 62 |
+
The chat template for our models is formatted as:
|
| 63 |
+
```
|
| 64 |
+
<|user|>\nHow are you doing?\n<|assistant|>\nI'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>
|
| 65 |
+
```
|
| 66 |
+
Or with new lines expanded:
|
| 67 |
+
```
|
| 68 |
+
<|user|>
|
| 69 |
+
How are you doing?
|
| 70 |
+
<|assistant|>
|
| 71 |
+
I'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>
|
| 72 |
+
```
|
| 73 |
+
It is embedded within the tokenizer as well, for `tokenizer.apply_chat_template`.
|
| 74 |
+
|
| 75 |
+
### System prompt
|
| 76 |
+
|
| 77 |
+
In Ai2 demos, we use this system prompt by default:
|
| 78 |
+
```
|
| 79 |
+
You are OLMo 2, a helpful and harmless AI Assistant built by the Allen Institute for AI.
|
| 80 |
+
```
|
| 81 |
+
The model has not been trained with a specific system prompt in mind.
|
| 82 |
+
|
| 83 |
+
### Intermediate Checkpoints
|
| 84 |
+
|
| 85 |
+
To facilitate research on RL finetuning, we have released our intermediate checkpoints during the model's RLVR training.
|
| 86 |
+
The model weights are saved every 20 training steps, and can be accessible in the revisions of the HuggingFace repository.
|
| 87 |
+
For example, you can load with:
|
| 88 |
+
```
|
| 89 |
+
olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0325-32B-Instruct", revision="step_200")
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
### Bias, Risks, and Limitations
|
| 93 |
+
|
| 94 |
+
The OLMo-2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
|
| 95 |
+
See the Falcon 180B model card for an example of this.
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
## Performance
|
| 99 |
+
|
| 100 |
+
| Model | Average | AlpacaEval 2 LC | BBH | DROP | GSM8k | IFEval | MATH | MMLU | Safety | PopQA | TruthQA |
|
| 101 |
+
|-------|---------|------|-----|------|-------|--------|------|------|--------|-------|---------|
|
| 102 |
+
| **Closed API models** | | | | | | | | | | | |
|
| 103 |
+
| GPT-3.5 Turbo 0125 | 59.6 | 38.7 | 66.6 | 70.2 | 74.3 | 66.9 | 41.2 | 70.2 | 69.1 | 45.0 | 62.9 |
|
| 104 |
+
| GPT 4o Mini 2024-07-18 | 65.7 | 49.7 | 65.9 | 36.3 | 83.0 | 83.5 | 67.9 | 82.2 | 84.9 | 39.0 | 64.8 |
|
| 105 |
+
| **Open weights models** | | | | | | | | | | | |
|
| 106 |
+
| Mistral-Nemo-Instruct-2407 | 50.9 | 45.8 | 54.6 | 23.6 | 81.4 | 64.5 | 31.9 | 70.0 | 52.7 | 26.9 | 57.7 |
|
| 107 |
+
| Ministral-8B-Instruct | 52.1 | 31.4 | 56.2 | 56.2 | 80.0 | 56.4 | 40.0 | 68.5 | 56.2 | 20.2 | 55.5 |
|
| 108 |
+
| Gemma-2-27b-it | 61.3 | 49.0 | 72.7 | 67.5 | 80.7 | 63.2 | 35.1 | 70.7 | 75.9 | 33.9 | 64.6 |
|
| 109 |
+
| Qwen2.5-32B | 66.5 | 39.1 | 82.3 | 48.3 | 87.5 | 82.4 | 77.9 | 84.7 | 82.4 | 26.1 | 70.6 |
|
| 110 |
+
| Mistral-Small-24B | 67.6 | 43.2 | 80.1 | 78.5 | 87.2 | 77.3 | 65.9 | 83.7 | 66.5 | 24.4 | 68.1 |
|
| 111 |
+
| Llama-3.1-70B | 70.0 | 32.9 | 83.0 | 77.0 | 94.5 | 88.0 | 56.2 | 85.2 | 76.4 | 46.5 | 66.8 |
|
| 112 |
+
| Llama-3.3-70B | 73.0 | 36.5 | 85.8 | 78.0 | 93.6 | 90.8 | 71.8 | 85.9 | 70.4 | 48.2 | 66.1 |
|
| 113 |
+
| Gemma-3-27b-it | - | 63.4 | 83.7 | 69.2 | 91.1 | - | - | 81.8 | - | 30.9 | - |
|
| 114 |
+
| **Fully open models** | | | | | | | | | | | |
|
| 115 |
+
| OLMo-2-7B-1124-Instruct | 55.7 | 31.0 | 48.5 | 58.9 | 85.2 | 75.6 | 31.3 | 63.9 | 81.2 | 24.6 | 56.3 |
|
| 116 |
+
| OLMo-2-13B-1124-Instruct | 61.4 | 37.5 | 58.4 | 72.1 | 87.4 | 80.4 | 39.7 | 68.6 | 77.5 | 28.8 | 63.9 |
|
| 117 |
+
| **OLMo-2-32B-0325-SFT** | 61.7 | 16.9 | 69.7 | 77.2 | 78.4 | 72.4 | 35.9 | 76.1 | 93.8 | 35.4 | 61.3 |
|
| 118 |
+
| **OLMo-2-32B-0325-DPO** | 68.8 | 44.1 | 70.2 | 77.5 | 85.7 | 83.8 | 46.8 | 78.0 | 91.9 | 36.4 | 73.5 |
|
| 119 |
+
| **OLMo-2-32B-0325-Instruct** | 68.8 | 42.8 | 70.6 | 78.0 | 87.6 | 85.6 | 49.7 | 77.3 | 85.9 | 37.5 | 73.2 |
|
| 120 |
+
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
|
| 124 |
+
## Learning curves
|
| 125 |
+
|
| 126 |
+
Below is the training curves for `allenai/OLMo-2-0325-32B-Instruct`. The model was trained using 5 8xH100 nodes.
|
| 127 |
+
|
| 128 |
+
|
| 129 |
+
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
Below are the core eval scores over steps for `allenai/OLMo-2-0325-32B-Instruct` (note we took step `320` as the final checkpoint, corresponding to episode `573,440`):
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
|
| 136 |
+
Below are the other eval scores over steps for `allenai/OLMo-2-0325-32B-Instruct`:
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Reproduction command
|
| 142 |
+
|
| 143 |
+
The command below is copied directly from the tracked training job:
|
| 144 |
+
|
| 145 |
+
```bash
|
| 146 |
+
# clone and check out commit
|
| 147 |
+
git clone https://github.com/allenai/open-instruct.git
|
| 148 |
+
# this should be the correct commit, the main thing is to have the vllm monkey patch for
|
| 149 |
+
# 32b olmo https://github.com/allenai/open-instruct/blob/894ffa236319bc6c26c346240a7e4ee04ba0bd31/open_instruct/vllm_utils2.py#L37-L59
|
| 150 |
+
git checkout a51dc98525eec01de6e8a24c071f42dce407d738
|
| 151 |
+
uv sync
|
| 152 |
+
uv sync --extra compile
|
| 153 |
+
|
| 154 |
+
# note that you may need 5 8xH100 nodes for the training.
|
| 155 |
+
# so please setup ray properly, e.g., https://github.com/allenai/open-instruct/blob/main/docs/tulu3.md#llama-31-tulu-3-70b-reproduction
|
| 156 |
+
python open_instruct/grpo_vllm_thread_ray_gtrl.py \
|
| 157 |
+
--exp_name 0310_olmo2_32b_grpo_12818 \
|
| 158 |
+
--beta 0.01 \
|
| 159 |
+
--local_mini_batch_size 32 \
|
| 160 |
+
--number_samples_per_prompt 16 \
|
| 161 |
+
--output_dir output \
|
| 162 |
+
--local_rollout_batch_size 4 \
|
| 163 |
+
--kl_estimator kl3 \
|
| 164 |
+
--learning_rate 5e-7 \
|
| 165 |
+
--dataset_mixer_list allenai/RLVR-GSM-MATH-IF-Mixed-Constraints 1.0 \
|
| 166 |
+
--dataset_mixer_list_splits train \
|
| 167 |
+
--dataset_mixer_eval_list allenai/RLVR-GSM-MATH-IF-Mixed-Constraints 16 \
|
| 168 |
+
--dataset_mixer_eval_list_splits train \
|
| 169 |
+
--max_token_length 2048 \
|
| 170 |
+
--max_prompt_token_length 2048 \
|
| 171 |
+
--response_length 2048 \
|
| 172 |
+
--model_name_or_path allenai/OLMo-2-0325-32B-DPO \
|
| 173 |
+
--non_stop_penalty \
|
| 174 |
+
--stop_token eos \
|
| 175 |
+
--temperature 1.0 \
|
| 176 |
+
--ground_truths_key ground_truth \
|
| 177 |
+
--chat_template_name tulu \
|
| 178 |
+
--sft_messages_key messages \
|
| 179 |
+
--eval_max_length 4096 \
|
| 180 |
+
--total_episodes 10000000 \
|
| 181 |
+
--penalty_reward_value 0.0 \
|
| 182 |
+
--deepspeed_stage 3 \
|
| 183 |
+
--no_gather_whole_model \
|
| 184 |
+
--per_device_train_batch_size 2 \
|
| 185 |
+
--local_rollout_forward_batch_size 2 \
|
| 186 |
+
--actor_num_gpus_per_node 8 8 8 4 \
|
| 187 |
+
--num_epochs 1 \
|
| 188 |
+
--vllm_tensor_parallel_size 1 \
|
| 189 |
+
--vllm_num_engines 12 \
|
| 190 |
+
--lr_scheduler_type constant \
|
| 191 |
+
--apply_verifiable_reward true \
|
| 192 |
+
--seed 1 \
|
| 193 |
+
--num_evals 30 \
|
| 194 |
+
--save_freq 20 \
|
| 195 |
+
--reward_model_multiplier 0.0 \
|
| 196 |
+
--no_try_launch_beaker_eval_jobs \
|
| 197 |
+
--try_launch_beaker_eval_jobs_on_weka \
|
| 198 |
+
--gradient_checkpointing \
|
| 199 |
+
--with_tracking
|
| 200 |
+
```
|
| 201 |
+
|
| 202 |
+
|
| 203 |
+
## License and use
|
| 204 |
+
|
| 205 |
+
OLMo 2 is licensed under the Apache 2.0 license.
|
| 206 |
+
OLMo 2 is intended for research and educational use.
|
| 207 |
+
For more information, please see our [Responsible Use Guidelines](https://allenai.org/responsible-use).
|
| 208 |
+
This model has been fine-tuned using a dataset mix with outputs generated from third party models and are subject to additional terms: [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
|
| 209 |
+
|
| 210 |
+
## Citation
|
| 211 |
+
|
| 212 |
+
```bibtex
|
| 213 |
+
@article{olmo20242olmo2furious,
|
| 214 |
+
title={2 OLMo 2 Furious},
|
| 215 |
+
author={Team OLMo and Pete Walsh and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Shane Arora and Akshita Bhagia and Yuling Gu and Shengyi Huang and Matt Jordan and Nathan Lambert and Dustin Schwenk and Oyvind Tafjord and Taira Anderson and David Atkinson and Faeze Brahman and Christopher Clark and Pradeep Dasigi and Nouha Dziri and Michal Guerquin and Hamish Ivison and Pang Wei Koh and Jiacheng Liu and Saumya Malik and William Merrill and Lester James V. Miranda and Jacob Morrison and Tyler Murray and Crystal Nam and Valentina Pyatkin and Aman Rangapur and Michael Schmitz and Sam Skjonsberg and David Wadden and Christopher Wilhelm and Michael Wilson and Luke Zettlemoyer and Ali Farhadi and Noah A. Smith and Hannaneh Hajishirzi},
|
| 216 |
+
year={2024},
|
| 217 |
+
eprint={2501.00656},
|
| 218 |
+
archivePrefix={arXiv},
|
| 219 |
+
primaryClass={cs.CL},
|
| 220 |
+
url={https://arxiv.org/abs/2501.00656},
|
| 221 |
+
}
|
| 222 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/open_instruct_dev",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Olmo2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 100257,
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 27648,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "olmo2",
|
| 16 |
+
"num_attention_heads": 40,
|
| 17 |
+
"num_hidden_layers": 64,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pad_token_id": 100277,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.49.0",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 100352
|
| 28 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": 100257,
|
| 5 |
+
"pad_token_id": 100277,
|
| 6 |
+
"transformers_version": "4.49.0"
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d539da18a12ce2b7985e4b255e707956ee67e67105e3f4f215071f2ec612c1e1
|
| 3 |
+
size 4991358312
|
model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5465b5c0e0ec170bf457c7af852b4887f9a13d603f13a52e6f2a3737b7ae8aa1
|
| 3 |
+
size 4938975944
|
model-00003-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b6e37dc85b5a0d0360dc461ed172d3c3ed907cb90aba821636ce5c0bb429b73
|
| 3 |
+
size 4876048688
|
model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f52a93bd70044cabd8729ad9583ef6d96c6528e8765e52abad4e2d1c9a608e9c
|
| 3 |
+
size 4876048704
|
model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:997245db5a143d21abf2806ad9be4ac8c2c3c9dede5f07315bd05d522dd50dcb
|
| 3 |
+
size 4876048704
|
model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98c2042bc4f9310afd36bf6152501fdf886d03764b60cf4eafc7f69d19c8b6e9
|
| 3 |
+
size 4876048704
|
model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:423d9b94bdb2c424ea5670f87a3313626b09d84be0a237eddd9117ad6e21c1f0
|
| 3 |
+
size 4876048704
|
model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3cd577278dfceb80a8aa972594a75d406e17283c5240a12ca9effb0b8d70f8a
|
| 3 |
+
size 4876048704
|
model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a8c9d3d0fe6f1087cf87573861a6d055ff3ede0f6816b97f77cd83975024eeb
|
| 3 |
+
size 4876048704
|
model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45eb53627f4a8ba1edf53239c5d8ac57c77744f8500ac12611bd6818a8de132a
|
| 3 |
+
size 4876048704
|
model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a1bd367c7ca31ded74cfc45c6315ac309088016d75b89dca950f9040affb25b
|
| 3 |
+
size 4876048704
|
model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f5bea3b50b29bf0e9ccfc137415ae86df332569922c8d9ba17275adf9d7645e
|
| 3 |
+
size 4876048704
|
model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2176fb4ceff37537dce4c7cc3b03e729576d91a58b60f68b353270b706345c7f
|
| 3 |
+
size 4750216928
|
model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d809a3c77c3757307669557ca455d28a29c9b38864fbe0b236f4d9f7b2cbe86
|
| 3 |
+
size 1027604608
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 64468559872
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00014-of-00014.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 12 |
+
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 23 |
+
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 30 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 31 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 32 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 33 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 34 |
+
"model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 41 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 42 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 43 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 44 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 45 |
+
"model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 52 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 53 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 54 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 55 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 56 |
+
"model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 63 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 64 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 65 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 66 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 67 |
+
"model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 74 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 75 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 76 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 77 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 78 |
+
"model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 85 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 86 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 87 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 88 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 89 |
+
"model.layers.15.post_feedforward_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 96 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 97 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 98 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 99 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 100 |
+
"model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 107 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 108 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 109 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 110 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 111 |
+
"model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 118 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 119 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 120 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 121 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 122 |
+
"model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 129 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 130 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 131 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 132 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 133 |
+
"model.layers.19.post_feedforward_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 140 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 141 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 142 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 143 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 144 |
+
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 151 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 152 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 153 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 154 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 155 |
+
"model.layers.20.post_feedforward_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 162 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 163 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 164 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 165 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 166 |
+
"model.layers.21.post_feedforward_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 173 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 174 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 175 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 176 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 177 |
+
"model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 184 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 185 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 186 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 187 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 188 |
+
"model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 195 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 196 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 197 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 198 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 199 |
+
"model.layers.24.post_feedforward_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 206 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 207 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 208 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 209 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 210 |
+
"model.layers.25.post_feedforward_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 217 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 218 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 219 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 220 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 221 |
+
"model.layers.26.post_feedforward_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 228 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 229 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 230 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 231 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 232 |
+
"model.layers.27.post_feedforward_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 239 |
+
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 240 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 241 |
+
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 242 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 243 |
+
"model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 250 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 251 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 252 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 253 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 254 |
+
"model.layers.29.post_feedforward_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 265 |
+
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 272 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 273 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 274 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 275 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 276 |
+
"model.layers.30.post_feedforward_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 283 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 284 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 285 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 286 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 287 |
+
"model.layers.31.post_feedforward_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 294 |
+
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 295 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 296 |
+
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 297 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 298 |
+
"model.layers.32.post_feedforward_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 299 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 305 |
+
"model.layers.33.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 306 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 307 |
+
"model.layers.33.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 308 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 309 |
+
"model.layers.33.post_feedforward_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 310 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 316 |
+
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 317 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 318 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 319 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 320 |
+
"model.layers.34.post_feedforward_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 321 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 327 |
+
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 328 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 329 |
+
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 330 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 331 |
+
"model.layers.35.post_feedforward_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 332 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 338 |
+
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 339 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 340 |
+
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 341 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 342 |
+
"model.layers.36.post_feedforward_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 343 |
+
"model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 344 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 345 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 346 |
+
"model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 347 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 348 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 349 |
+
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 350 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 351 |
+
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 352 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 353 |
+
"model.layers.37.post_feedforward_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 354 |
+
"model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 355 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 356 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 357 |
+
"model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 358 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 359 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 360 |
+
"model.layers.38.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 361 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 362 |
+
"model.layers.38.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 363 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 364 |
+
"model.layers.38.post_feedforward_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 365 |
+
"model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 366 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 367 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 368 |
+
"model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 369 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 370 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 371 |
+
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 372 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 373 |
+
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 374 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 375 |
+
"model.layers.39.post_feedforward_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 376 |
+
"model.layers.39.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 377 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 378 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 379 |
+
"model.layers.39.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 380 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 381 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 382 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 383 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 384 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 385 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 386 |
+
"model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 387 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 388 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 389 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 390 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 391 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 392 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 393 |
+
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 394 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 395 |
+
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 396 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 397 |
+
"model.layers.40.post_feedforward_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 398 |
+
"model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 399 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 400 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 401 |
+
"model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 402 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 403 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 404 |
+
"model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 405 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 406 |
+
"model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 407 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 408 |
+
"model.layers.41.post_feedforward_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 409 |
+
"model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 410 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 411 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 412 |
+
"model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 413 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 414 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 415 |
+
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 416 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 417 |
+
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 418 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 419 |
+
"model.layers.42.post_feedforward_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 420 |
+
"model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 421 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 422 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 423 |
+
"model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 424 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 425 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 426 |
+
"model.layers.43.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 427 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 428 |
+
"model.layers.43.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 429 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 430 |
+
"model.layers.43.post_feedforward_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 431 |
+
"model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 432 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 433 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 434 |
+
"model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 435 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 436 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 437 |
+
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 438 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 439 |
+
"model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 440 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 441 |
+
"model.layers.44.post_feedforward_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 442 |
+
"model.layers.44.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 443 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 444 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 445 |
+
"model.layers.44.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 446 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 447 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 448 |
+
"model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 449 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 450 |
+
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 451 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 452 |
+
"model.layers.45.post_feedforward_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 453 |
+
"model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 454 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 455 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 456 |
+
"model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 457 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 458 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 459 |
+
"model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 460 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 461 |
+
"model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 462 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 463 |
+
"model.layers.46.post_feedforward_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 464 |
+
"model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 465 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 466 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 467 |
+
"model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 468 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 469 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 470 |
+
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 471 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 472 |
+
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 473 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 474 |
+
"model.layers.47.post_feedforward_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 475 |
+
"model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 476 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 477 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 478 |
+
"model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 479 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 480 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 481 |
+
"model.layers.48.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 482 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 483 |
+
"model.layers.48.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 484 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 485 |
+
"model.layers.48.post_feedforward_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 486 |
+
"model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 487 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 488 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 489 |
+
"model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 490 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 491 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 492 |
+
"model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 493 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 494 |
+
"model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 495 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 496 |
+
"model.layers.49.post_feedforward_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 497 |
+
"model.layers.49.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 498 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 499 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 500 |
+
"model.layers.49.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 501 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 502 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 503 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 504 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 505 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 506 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 507 |
+
"model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 508 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 509 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 510 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 511 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 512 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 513 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 514 |
+
"model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 515 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 516 |
+
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 517 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 518 |
+
"model.layers.50.post_feedforward_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 519 |
+
"model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 520 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 521 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 522 |
+
"model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 523 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 524 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 525 |
+
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 526 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 527 |
+
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 528 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 529 |
+
"model.layers.51.post_feedforward_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 530 |
+
"model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 531 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 532 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 533 |
+
"model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 534 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 535 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 536 |
+
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 537 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 538 |
+
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 539 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 540 |
+
"model.layers.52.post_feedforward_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 541 |
+
"model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 542 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 543 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 544 |
+
"model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 545 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 546 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 547 |
+
"model.layers.53.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 548 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 549 |
+
"model.layers.53.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 550 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 551 |
+
"model.layers.53.post_feedforward_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 552 |
+
"model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 553 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 554 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 555 |
+
"model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 556 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 557 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 558 |
+
"model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 559 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 560 |
+
"model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 561 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 562 |
+
"model.layers.54.post_feedforward_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 563 |
+
"model.layers.54.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 564 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 565 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 566 |
+
"model.layers.54.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 567 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 568 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 569 |
+
"model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 570 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 571 |
+
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 572 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 573 |
+
"model.layers.55.post_feedforward_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 574 |
+
"model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 575 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 576 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 577 |
+
"model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 578 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 579 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 580 |
+
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 581 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 582 |
+
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 583 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 584 |
+
"model.layers.56.post_feedforward_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 585 |
+
"model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 586 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 587 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 588 |
+
"model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 589 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 590 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 591 |
+
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 592 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 593 |
+
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 594 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 595 |
+
"model.layers.57.post_feedforward_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 596 |
+
"model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 597 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 598 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 599 |
+
"model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 600 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 601 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 602 |
+
"model.layers.58.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 603 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 604 |
+
"model.layers.58.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 605 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 606 |
+
"model.layers.58.post_feedforward_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 607 |
+
"model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 608 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 609 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 610 |
+
"model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 611 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 612 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 613 |
+
"model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 614 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 615 |
+
"model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 616 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 617 |
+
"model.layers.59.post_feedforward_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 618 |
+
"model.layers.59.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 619 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 620 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 621 |
+
"model.layers.59.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 622 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 623 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 624 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 625 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 626 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 627 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 628 |
+
"model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 629 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 630 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 631 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 632 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 633 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 634 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 635 |
+
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 636 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 637 |
+
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 638 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 639 |
+
"model.layers.60.post_feedforward_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 640 |
+
"model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 641 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 642 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 643 |
+
"model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 644 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 645 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 646 |
+
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 647 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 648 |
+
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 649 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 650 |
+
"model.layers.61.post_feedforward_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 651 |
+
"model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 652 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 653 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 654 |
+
"model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 655 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 656 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 657 |
+
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 658 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 659 |
+
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 660 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 661 |
+
"model.layers.62.post_feedforward_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 662 |
+
"model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 663 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 664 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 665 |
+
"model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 666 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 667 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 668 |
+
"model.layers.63.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 669 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 670 |
+
"model.layers.63.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 671 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 672 |
+
"model.layers.63.post_feedforward_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 673 |
+
"model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 674 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 675 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 676 |
+
"model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 677 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 678 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 679 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 680 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 681 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 682 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 683 |
+
"model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 684 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 685 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 686 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 687 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 688 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 689 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 690 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 691 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 692 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 693 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 694 |
+
"model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 695 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 696 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 697 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 698 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 699 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 700 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 701 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 702 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 703 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 704 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 705 |
+
"model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 706 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 707 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 708 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 709 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 710 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 711 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 712 |
+
"model.norm.weight": "model-00013-of-00014.safetensors"
|
| 713 |
+
}
|
| 714 |
+
}
|
olmo-32b-instruct-eval-curve.png
ADDED
|
olmo-32b-instruct-full-eval-curve.png
ADDED
|
Git LFS Details
|
olmo-32b-instruct-learning-curve-time.png
ADDED
|
Git LFS Details
|
olmo-32b-instruct-learning-curve.png
ADDED
|
Git LFS Details
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|extra_id_0|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "|||PHONE_NUMBER|||",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "|||IP_ADDRESS|||",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|im_start|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|im_end|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|extra_id_1|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|extra_id_2|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|extra_id_3|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|extra_id_4|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|extra_id_5|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|extra_id_6|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|extra_id_7|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|extra_id_8|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|extra_id_9|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|extra_id_10|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"bos_token": "<|endoftext|>",
|
| 182 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
|
| 183 |
+
"clean_up_tokenization_spaces": false,
|
| 184 |
+
"eos_token": "<|endoftext|>",
|
| 185 |
+
"extra_special_tokens": {},
|
| 186 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 187 |
+
"pad_token": "<|pad|>",
|
| 188 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 189 |
+
"unk_token": "<|endoftext|>"
|
| 190 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|