初始化项目，由ModelHub XC社区提供模型
Model: migtissera/Synthia-70B-v1.2 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
|
||||
192
README.md
Normal file
192
README.md
Normal file
@@ -0,0 +1,192 @@
|
||||
---
|
||||
license: llama2
|
||||
pipeline_tag: text-generation
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
<br>
|
||||
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
Change from 1.1 -> 1.2: 20% more data than 1.1 and 2x training time.
|
||||
|
||||
All Synthia models are uncensored. Please use it with caution and with best intentions. You are responsible for how you use Synthia.
|
||||
|
||||
To evoke generalized Tree of Thought + Chain of Thought reasoning, you may use the following system message:
|
||||
```
|
||||
Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation.
|
||||
```
|
||||
|
||||
# Synthia-70B-v1.2
|
||||
SynthIA (Synthetic Intelligent Agent) is a LLama-2-70B model trained on Orca style datasets. It has been fine-tuned for instruction following as well as having long-form conversations.
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
#### License Disclaimer:
|
||||
|
||||
This model is bound by the license & usage restrictions of the original Llama-2 model, and comes with no warranty or gurantees of any kind.
|
||||
|
||||
<br>
|
||||
|
||||
## Evaluation
|
||||
|
||||
We evaluated Synthia-70B-v1.2 on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
|
||||
|
||||
Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
|
||||
||||
|
||||
|:------:|:--------:|:-------:|
|
||||
|**Task**|**Metric**|**Value**|
|
||||
|*arc_challenge*|acc_norm|70.48|
|
||||
|*hellaswag*|acc_norm|86.98|
|
||||
|*mmlu*|acc_norm|70.13|
|
||||
|*truthfulqa_mc*|mc2|58.64|
|
||||
|**Total Average**|-|**71.56**||
|
||||
|
||||
<br>
|
||||
|
||||
## Example Usage
|
||||
|
||||
### Here is prompt format:
|
||||
|
||||
```
|
||||
SYSTEM: Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation.
|
||||
USER: How is a rocket launched from the surface of the earth to Low Earth Orbit?
|
||||
ASSISTANT:
|
||||
```
|
||||
|
||||
### Below shows a code example on how to use this model:
|
||||
|
||||
```python
|
||||
import torch, json
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_path = "migtissera/Synthia-70B-v1.2"
|
||||
output_file_path = "./Synthia-70B-conversations.jsonl"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_path,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
load_in_8bit=False,
|
||||
trust_remote_code=True,
|
||||
)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
||||
|
||||
|
||||
def generate_text(instruction):
|
||||
tokens = tokenizer.encode(instruction)
|
||||
tokens = torch.LongTensor(tokens).unsqueeze(0)
|
||||
tokens = tokens.to("cuda")
|
||||
|
||||
instance = {
|
||||
"input_ids": tokens,
|
||||
"top_p": 1.0,
|
||||
"temperature": 0.75,
|
||||
"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"],
|
||||
num_return_sequences=1,
|
||||
)
|
||||
output = rest[0][length:]
|
||||
string = tokenizer.decode(output, skip_special_tokens=True)
|
||||
answer = string.split("USER:")[0].strip()
|
||||
return f"{answer}"
|
||||
|
||||
|
||||
conversation = f"SYSTEM: Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation."
|
||||
|
||||
|
||||
while True:
|
||||
user_input = input("You: ")
|
||||
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
|
||||
answer = generate_text(llm_prompt)
|
||||
print(answer)
|
||||
conversation = f"{llm_prompt}{answer}"
|
||||
json_data = {"prompt": user_input, "answer": answer}
|
||||
|
||||
## Save your conversation
|
||||
with open(output_file_path, "a") as output_file:
|
||||
output_file.write(json.dumps(json_data) + "\n")
|
||||
|
||||
```
|
||||
|
||||
<br>
|
||||
|
||||
#### Limitations & Biases:
|
||||
|
||||
While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
|
||||
|
||||
Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
|
||||
|
||||
Exercise caution and cross-check information when necessary. This is an uncensored model.
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
### Citiation:
|
||||
|
||||
Please kindly cite using the following BibTeX:
|
||||
|
||||
```
|
||||
@misc{Synthia-70B-v1.2,
|
||||
author = {Migel Tissera},
|
||||
title = {Synthia-70B-v1.2: Synthetic Intelligent Agent},
|
||||
year = {2023},
|
||||
publisher = {GitHub, HuggingFace},
|
||||
journal = {GitHub repository, HuggingFace repository},
|
||||
howpublished = {\url{https://huggingface.co/migtissera/Synthia-13B},
|
||||
}
|
||||
```
|
||||
|
||||
```
|
||||
@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{touvron2023llama,
|
||||
title={LLaMA2: Open and Efficient Foundation Language Models},
|
||||
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
|
||||
journal={arXiv preprint arXiv:2302.13971},
|
||||
year={2023}
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
# [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_migtissera__Synthia-70B-v1.2)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 63.41 |
|
||||
| ARC (25-shot) | 70.48 |
|
||||
| HellaSwag (10-shot) | 86.98 |
|
||||
| MMLU (5-shot) | 70.13 |
|
||||
| TruthfulQA (0-shot) | 58.64 |
|
||||
| Winogrande (5-shot) | 83.27 |
|
||||
| GSM8K (5-shot) | 31.92 |
|
||||
| DROP (3-shot) | 42.42 |
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "/home/ubuntu/llm/Synthia-70B-v1.1",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 8192,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 28672,
|
||||
"max_length": 4096,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 64,
|
||||
"num_hidden_layers": 80,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.32.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 32000,
|
||||
"temperature": 0.9,
|
||||
"top_p": 0.6,
|
||||
"transformers_version": "4.32.0.dev0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00015.bin
Normal file
3
pytorch_model-00001-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7b0cea8ba32098856f072140d296dd7edac3d001f85dd0fe1c8f125fe8ea70ea
|
||||
size 9852601804
|
||||
3
pytorch_model-00002-of-00015.bin
Normal file
3
pytorch_model-00002-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33362a6ac0d65b51339040a1ba457b45702d6333f5ac632313869e11f4eff9e4
|
||||
size 9798109380
|
||||
3
pytorch_model-00003-of-00015.bin
Normal file
3
pytorch_model-00003-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09537267bb6c850f6ac9dbdf6c976c396c39d9e79fccd6762aaca6aa2e34fec1
|
||||
size 9965880502
|
||||
3
pytorch_model-00004-of-00015.bin
Normal file
3
pytorch_model-00004-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3680ed5c416818a7debe4fbc8031775fddaad0d77f6b649dd0961803743bd6c
|
||||
size 9798075916
|
||||
3
pytorch_model-00005-of-00015.bin
Normal file
3
pytorch_model-00005-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cab5697663716abbb687b470c12035ce4995f5598919f3e3a271df281273d592
|
||||
size 9798109296
|
||||
3
pytorch_model-00006-of-00015.bin
Normal file
3
pytorch_model-00006-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7f118591c0dd5c626a63d0432668493f86626e2d390328e2bd117598c30751a4
|
||||
size 9798109380
|
||||
3
pytorch_model-00007-of-00015.bin
Normal file
3
pytorch_model-00007-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:10210d3fe6c2f8f131390596e0ffd913fa7a740939547ad0830b7465750952f0
|
||||
size 9965880502
|
||||
3
pytorch_model-00008-of-00015.bin
Normal file
3
pytorch_model-00008-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:34edd551bc71d7e926d93d59b2b50826377c5cec01e5b55a90a7743174860029
|
||||
size 9798075916
|
||||
3
pytorch_model-00009-of-00015.bin
Normal file
3
pytorch_model-00009-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:97e45aa1e8c7fce39c76ce61b2f883454af87fe72a3ab193a63ec52a5623a94d
|
||||
size 9798109296
|
||||
3
pytorch_model-00010-of-00015.bin
Normal file
3
pytorch_model-00010-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:739078486e1f654866d4313ded195a21806885240f70b605932a0a2f9759480e
|
||||
size 9798109380
|
||||
3
pytorch_model-00011-of-00015.bin
Normal file
3
pytorch_model-00011-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9038578342ac7cb676c92abf11069436a28ae55e343e26cc6b0150c58b33909f
|
||||
size 9965880502
|
||||
3
pytorch_model-00012-of-00015.bin
Normal file
3
pytorch_model-00012-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:64f4d278cc0e8b0fcbecc45a6e5ed4ede86b0a619a77917b6e2c418a8f6b5b6f
|
||||
size 9798075916
|
||||
3
pytorch_model-00013-of-00015.bin
Normal file
3
pytorch_model-00013-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:34e7bee2a6e63862810b87b1e0601436baa165af4c0189b9b5ff32d8c076c0ae
|
||||
size 9798109296
|
||||
3
pytorch_model-00014-of-00015.bin
Normal file
3
pytorch_model-00014-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6039c8a009b9551b3d7f829cb0164fa2ea0f51b867b29736cc9811dae3625e59
|
||||
size 9496134826
|
||||
3
pytorch_model-00015-of-00015.bin
Normal file
3
pytorch_model-00015-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:81bdaeeeaf9a6eec4ac46d02555271f3e89ea6c56da3d7deae90130782c6f622
|
||||
size 524289413
|
||||
730
pytorch_model.bin.index.json
Normal file
730
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,730 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 137953296384
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.norm.weight": "pytorch_model-00014-of-00015.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
32
tokenizer_config.json
Normal file
32
tokenizer_config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user