初始化项目，由ModelHub XC社区提供模型
Model: pankajmathur/orca_mini_7b Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
330
README.md
Normal file
330
README.md
Normal file
@@ -0,0 +1,330 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: cc-by-nc-sa-4.0
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- psmathur/alpaca_orca
|
||||
- psmathur/dolly-v2_orca
|
||||
- psmathur/WizardLM_Orca
|
||||
pipeline_tag: text-generation
|
||||
model-index:
|
||||
- name: orca_mini_7b
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 43.94
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_7b
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 65.22
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_7b
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 29.97
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_7b
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 42.03
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_7b
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 66.06
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_7b
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 0.38
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_7b
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
# orca_mini_7b
|
||||
|
||||
<img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />
|
||||
|
||||
<strong>
|
||||
"Obsessed with GenAI's potential? So am I ! Let's create together 🚀 <a href="https://www.linkedin.com/in/pankajam" target="_blank">https://www.linkedin.com/in/pankajam</a>"
|
||||
</strong>
|
||||
|
||||
<br>
|
||||
|
||||
**An [OpenLLaMa-7B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.**
|
||||
|
||||
### Dataset
|
||||
|
||||
We build explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
|
||||
|
||||
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
|
||||
|
||||
This helps student model aka this model to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
|
||||
|
||||
Please see below example usage how the **System** prompt is added before each **instruction**.
|
||||
|
||||
### Training
|
||||
|
||||
The training configurations are provided in the table below.
|
||||
|
||||
The training takes on 8x A100(80G) GPUs and lasts for around 7 Hours for cost of $84 using [Lambda Labs](https://lambdalabs.com)
|
||||
|
||||
We used DeepSpeed with fully sharded data parallelism, also know as [ZeRO stage 3](https://engineering.fb.com/2021/07/15/open-source/fsdp/) by writing our own fine tunning scripts plus leveraging some of the model training code provided by amazing [OpenAlpaca repo](https://github.com/yxuansu/OpenAlpaca)
|
||||
|
||||
Here are some of params used during training:
|
||||
|
||||
|||
|
||||
|:-------------:|:-------------:|
|
||||
|*batch_size*|32|
|
||||
|*train_micro_batch_size_per_gpu*|2|
|
||||
|*gradient_accumulation_steps*|2|
|
||||
|*Learning rate*|2e-5|
|
||||
|*Max length*|1024|
|
||||
|*Epochs*|3|
|
||||
|*Optimizer*|AdamW|
|
||||
|
||||
|
||||
|
||||
### Example Usage
|
||||
|
||||
Below shows an example on how to use this model
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import LlamaForCausalLM, LlamaTokenizer
|
||||
|
||||
# Hugging Face model_path
|
||||
model_path = 'psmathur/orca_mini_7b'
|
||||
tokenizer = LlamaTokenizer.from_pretrained(model_path)
|
||||
model = LlamaForCausalLM.from_pretrained(
|
||||
model_path, torch_dtype=torch.float16, device_map='auto',
|
||||
)
|
||||
|
||||
|
||||
#generate text function
|
||||
def generate_text(system, instruction, input=None):
|
||||
|
||||
if input:
|
||||
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
|
||||
else:
|
||||
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
|
||||
|
||||
tokens = tokenizer.encode(prompt)
|
||||
tokens = torch.LongTensor(tokens).unsqueeze(0)
|
||||
tokens = tokens.to('cuda')
|
||||
|
||||
instance = {'input_ids': tokens,'top_p': 1.0, 'temperature':0.7, 'generate_len': 1024, 'top_k': 50}
|
||||
|
||||
length = len(tokens[0])
|
||||
with torch.no_grad():
|
||||
rest = model.generate(
|
||||
input_ids=tokens,
|
||||
max_length=length+instance['generate_len'],
|
||||
use_cache=True,
|
||||
do_sample=True,
|
||||
top_p=instance['top_p'],
|
||||
temperature=instance['temperature'],
|
||||
top_k=instance['top_k']
|
||||
)
|
||||
output = rest[0][length:]
|
||||
string = tokenizer.decode(output, skip_special_tokens=True)
|
||||
return f'[!] Response: {string}'
|
||||
|
||||
# Sample Test Instruction Used by Youtuber Sam Witteveen https://www.youtube.com/@samwitteveenai
|
||||
system = 'You are an AI assistant that follows instruction extremely well. Help as much as you can.'
|
||||
instruction = 'Write a letter to Sam Altman, CEO of OpenAI, requesting him to convert GPT4 a private model by OpenAI to an open source project'
|
||||
print(generate_text(system, instruction))
|
||||
|
||||
```
|
||||
|
||||
```
|
||||
|
||||
[!] Response:
|
||||
Dear Sam Altman,
|
||||
|
||||
I am writing to request that you convert the GPT4 private model developed by OpenAI to an open source project. As a user of OpenAI, I have been waiting for the day when I can use the advanced natural language processing capabilities of GPT4 in a more open and accessible way.
|
||||
|
||||
While OpenAI has made significant progress in developing AI applications, it has primarily focused on building private models that are not accessible to the general public. However, with the recent release of GPT-3, there is a growing demand for more open and accessible AI tools.
|
||||
|
||||
Converting GPT4 to an open source project would allow for greater transparency, collaboration, and innovation. It would also help to build trust in the technology and ensure that it is used ethically and responsibly.
|
||||
|
||||
I urge you to consider converting GPT4 to an open source project. This would be a significant contribution to the AI community and would help to create a more open and accessible future.
|
||||
|
||||
Thank you for your consideration.
|
||||
|
||||
Sincerely,
|
||||
|
||||
[Your Name]
|
||||
|
||||
```
|
||||
|
||||
**
|
||||
|
||||
Next Goals:
|
||||
1) Try more data like actually using FLAN-v2, just like Orka Research Paper (I am open for suggestions)
|
||||
2) Provide more options for Text generation UI. (may be https://github.com/oobabooga/text-generation-webui)
|
||||
3) Provide 4bit GGML/GPTQ quantized model (may be [TheBloke](https://huggingface.co/TheBloke) can help here)
|
||||
|
||||
|
||||
Limitations & Biases:
|
||||
|
||||
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
|
||||
This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
|
||||
|
||||
Disclaimer:
|
||||
|
||||
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model.
|
||||
Please cosult an attorney before using this model for commercial purposes.
|
||||
|
||||
|
||||
Citiation:
|
||||
|
||||
If you found wizardlm_alpaca_dolly_orca_open_llama_7b useful in your research or applications, please kindly cite using the following BibTeX:
|
||||
|
||||
```
|
||||
@misc{orca_mini_7b,
|
||||
author = {Pankaj Mathur},
|
||||
title = {orca_mini_7b: An explain tuned OpenLLaMA-7b model on custom wizardlm, alpaca, & dolly datasets},
|
||||
year = {2023},
|
||||
publisher = {GitHub, HuggingFace},
|
||||
journal = {GitHub repository, HuggingFace repository},
|
||||
howpublished = {\url{https://github.com/pankajarm/wizardlm_alpaca_dolly_orca_open_llama_7b}, \url{https://https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_7b}},
|
||||
}
|
||||
```
|
||||
```
|
||||
@misc{mukherjee2023orca,
|
||||
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
|
||||
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
|
||||
year={2023},
|
||||
eprint={2306.02707},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL}
|
||||
}
|
||||
```
|
||||
```
|
||||
@software{openlm2023openllama,
|
||||
author = {Xinyang Geng and Hao Liu},
|
||||
title = {OpenLLaMA: An Open Reproduction of LLaMA},
|
||||
month = May,
|
||||
year = 2023,
|
||||
url = {https://github.com/openlm-research/open_llama}
|
||||
}
|
||||
```
|
||||
```
|
||||
@misc{openalpaca,
|
||||
author = {Yixuan Su and Tian Lan and Deng Cai},
|
||||
title = {OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA},
|
||||
year = {2023},
|
||||
publisher = {GitHub},
|
||||
journal = {GitHub repository},
|
||||
howpublished = {\url{https://github.com/yxuansu/OpenAlpaca}},
|
||||
}
|
||||
```
|
||||
```
|
||||
@misc{alpaca,
|
||||
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
|
||||
title = {Stanford Alpaca: An Instruction-following LLaMA model},
|
||||
year = {2023},
|
||||
publisher = {GitHub},
|
||||
journal = {GitHub repository},
|
||||
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
|
||||
}
|
||||
```
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__orca_mini_7b)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 37.39 |
|
||||
| ARC (25-shot) | 43.94 |
|
||||
| HellaSwag (10-shot) | 65.22 |
|
||||
| MMLU (5-shot) | 29.97 |
|
||||
| TruthfulQA (0-shot) | 42.03 |
|
||||
| Winogrande (5-shot) | 66.06 |
|
||||
| GSM8K (5-shot) | 0.38 |
|
||||
| DROP (3-shot) | 14.14 |
|
||||
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__orca_mini_7b)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |41.27|
|
||||
|AI2 Reasoning Challenge (25-Shot)|43.94|
|
||||
|HellaSwag (10-Shot) |65.22|
|
||||
|MMLU (5-Shot) |29.97|
|
||||
|TruthfulQA (0-shot) |42.03|
|
||||
|Winogrande (5-shot) |66.06|
|
||||
|GSM8k (5-shot) | 0.38|
|
||||
|
||||
23
config.json
Normal file
23
config.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "openlm-research/open_llama_7b",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.29.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.29.1"
|
||||
}
|
||||
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:53003e8961694c6e35487e4bafdf1d21118f960a45835c60a00894b1fb85e62b
|
||||
size 4840398640
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44ddbe6dc4b1a4aba07477530c700bb78432b716288a1142a308eac20fc089d6
|
||||
size 4857209080
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a45df0c3b857bf2eee0c0c9c497f562beedf9266ee5a668b8fe36bf4ebbf47a
|
||||
size 4857209136
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:151244cd7d45128d5510ac1b4f16b53af5f80623e58d418d2fb85058d4293da9
|
||||
size 4857209136
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b772dc3233bcff7acc2faa0a397e8db652a5ec77427e5348de5f0bf291bc8594
|
||||
size 4857209136
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6edde07ebe6247c715ffc7799d556e8e8e989a94d3a93e66b7b14167d5957069
|
||||
size 2684472856
|
||||
330
model.safetensors.index.json
Normal file
330
model.safetensors.index.json
Normal file
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26953670656
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
3
pytorch_model-00001-of-00006.bin
Normal file
3
pytorch_model-00001-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8dd426509e26c55cbc669780218b38b60b22b83a00e338e66ed5cef7862294bf
|
||||
size 4840410959
|
||||
3
pytorch_model-00002-of-00006.bin
Normal file
3
pytorch_model-00002-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:208f45b87e8042751b302ee7b7acdebcd4c3d66d5905000156a034353738cf74
|
||||
size 4857222431
|
||||
3
pytorch_model-00003-of-00006.bin
Normal file
3
pytorch_model-00003-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:83da7c52740aac2b5df866339e851c68652d681c6f8422677918299d355e40cb
|
||||
size 4857222431
|
||||
3
pytorch_model-00004-of-00006.bin
Normal file
3
pytorch_model-00004-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a4bd78c40eecb9ef2aecbfff4e2281672519eb6e82df7c4f20e91c1ef1993217
|
||||
size 4857222431
|
||||
3
pytorch_model-00005-of-00006.bin
Normal file
3
pytorch_model-00005-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8ec0624749b27aceff3f3f494c49b728a2856d8f2e4af8a2297e02f9c02b145c
|
||||
size 4857222431
|
||||
3
pytorch_model-00006-of-00006.bin
Normal file
3
pytorch_model-00006-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd665be2ce27a5605bd2109bb2022752f506174d2b34668a465c7fa4de0d38aa
|
||||
size 2684478773
|
||||
330
pytorch_model.bin.index.json
Normal file
330
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26953670656
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.norm.weight": "pytorch_model-00006-of-00006.bin"
|
||||
}
|
||||
}
|
||||
12
special_tokens_map.json
Normal file
12
special_tokens_map.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "</s>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
|
||||
size 534194
|
||||
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"model_max_length": 2048,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user