初始化项目，由ModelHub XC社区提供模型
Model: FBK-MT/Qwen3-14B-GNR-it-full Source: Original Platform
This commit is contained in:
ModelHub XC
65
.gitattributes
vendored
Normal file
65
.gitattributes
vendored
Normal file
@@ -0,0 +1,65 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 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
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack 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
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* 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
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
174
README.md
Normal file
174
README.md
Normal file
@@ -0,0 +1,174 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
datasets:
|
||||||
|
- FBK-MT/GNR-it
|
||||||
|
language:
|
||||||
|
- it
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen3-14B
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- rewriting
|
||||||
|
- fairness
|
||||||
|
- gender-inclusive
|
||||||
|
- gender-neutral
|
||||||
|
metrics:
|
||||||
|
- accuracy
|
||||||
|
- bertscore
|
||||||
|
---
|
||||||
|
|
||||||
|
# Qwen3-14B-GNR-it-full
|
||||||
|
|
||||||
|
Qwen3-14B-GNR-it-full is a fine-tuned version of [Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) for the task of gender-neutral rewriting (GNR) in Italian.
|
||||||
|
|
||||||
|
## Table of Contents
|
||||||
|
1. [Overview](#overview)
|
||||||
|
2. [Usage](#Usage)
|
||||||
|
3. [License](#license)
|
||||||
|
4. [Citation](#citation)
|
||||||
|
5. [Contributions](#contributions)
|
||||||
|
|
||||||
|
## Overview
|
||||||
|
|
||||||
|
This model is part of a family release of four models (8B/14B × clean/full) trained on [GNR-it](https://huggingface.co/datasets/FBK-MT/GNR-it), a dataset of parallel Italian gendered and gender-neutral sentences.
|
||||||
|
The _clean_ variants are trained on a BERTScore-filtered subset of the data, whereas the _full_ ones use the complete dataset.
|
||||||
|
Here is the complete family of models:
|
||||||
|
|
||||||
|
- [Qwen3-8B-GNR-it-clean](https://huggingface.co/FBK-MT/Qwen3-8B-GNR-it-clean)
|
||||||
|
- [Qwen3-8B-GNR-it-full](https://huggingface.co/FBK-MT/Qwen3-8B-GNR-it-full)
|
||||||
|
- [Qwen3-14B-GNR-it-clean](https://huggingface.co/FBK-MT/Qwen3-14B-GNR-it-clean)
|
||||||
|
- [Qwen3-14B-GNR-it-full](https://huggingface.co/FBK-MT/Qwen3-14B-GNR-it-full)
|
||||||
|
|
||||||
|
We are releasing these models to support reproducibility of the experiments reported in the paper [Gender-Neutral Rewriting in Italian: Models, Approaches,
|
||||||
|
and Trade-offs](https://arxiv.org/abs/2509.13480) and provide the community with open baselines for GNR in Italian.
|
||||||
|
The models are not intended as prescriptive tools for language use, but rather as research artifacts to study fairness in natural language generation.
|
||||||
|
|
||||||
|
For more information about these models, please check the paper [pre-print](https://arxiv.org/abs/2509.13480).
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
This model is supported in Hugging Face 🤗 Transformers and vLLM.
|
||||||
|
|
||||||
|
### Simple inference
|
||||||
|
To run the model, first install the Transformers library.
|
||||||
|
|
||||||
|
```sh
|
||||||
|
pip install transformers>=4.51.0
|
||||||
|
```
|
||||||
|
|
||||||
|
Then run standard inference:
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model_name = "FBK-MT/Qwen3-14B-GNR-it-full"
|
||||||
|
|
||||||
|
# load the tokenizer and the model
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_name,
|
||||||
|
torch_dtype="auto",
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# prepare the model input
|
||||||
|
system_message = "Rewrite the following Italian sentence using a gender-neutral language in reference to human beings, avoiding masculine or feminine forms."
|
||||||
|
input_sentence = "Dobbiamo tutelare tutti i cittadini, a partire dai più poveri"
|
||||||
|
messages = [
|
||||||
|
{"role": "system", "content": system_message},
|
||||||
|
{"role": "user", "content": input_sentence}
|
||||||
|
]
|
||||||
|
text = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=False,
|
||||||
|
add_generation_prompt=True,
|
||||||
|
enable_thinking=False
|
||||||
|
)
|
||||||
|
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||||
|
|
||||||
|
generated_ids = model.generate(
|
||||||
|
**model_inputs,
|
||||||
|
max_new_tokens=200
|
||||||
|
)
|
||||||
|
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
||||||
|
|
||||||
|
result = tokenizer.decode(output_ids[0][model_inputs["input_ids"].shape[-1]:])
|
||||||
|
print(result)
|
||||||
|
# "Dobbiamo tutelare tutte le persone, a partire dalle più deboli."
|
||||||
|
```
|
||||||
|
|
||||||
|
### Batch inference
|
||||||
|
|
||||||
|
To perform batched inference we recommend using [vLLM](https://docs.vllm.ai/en/latest/index.html).
|
||||||
|
|
||||||
|
First, install the library following [the official guide](https://docs.vllm.ai/en/latest/getting_started/installation/).
|
||||||
|
|
||||||
|
Then, prepare a list of inputs and let vLLM handle batching:
|
||||||
|
|
||||||
|
```python
|
||||||
|
import torch
|
||||||
|
from vllm import LLM
|
||||||
|
|
||||||
|
model = LLM(
|
||||||
|
model='FBK-MT/Qwen3-14B-GNR-it-full',
|
||||||
|
enable_prefix_caching=True,
|
||||||
|
disable_sliding_window=True,
|
||||||
|
tensor_parallel_size=torch.cuda.device_count(),
|
||||||
|
gpu_memory_utilization=0.9,
|
||||||
|
trust_remote_code=True)
|
||||||
|
|
||||||
|
system_message = "Rewrite the following Italian sentence using a gender-neutral language in reference to human beings, avoiding masculine or feminine forms."
|
||||||
|
input_sentences = [
|
||||||
|
"Il candidato che è stato scelto per la posizione ha dimostrato di avere un'ottima preparazione e di essere adeguadatmente preparato.",
|
||||||
|
"Verrà istituito un sistema di informazione per i consumatori che acquistano prodotti elettronici.",
|
||||||
|
"Lo studente deve consegnare il compito entro venerdì."
|
||||||
|
]
|
||||||
|
|
||||||
|
tokenizer = model.get_tokenizer()
|
||||||
|
|
||||||
|
input_data = [
|
||||||
|
tokenizer.apply_chat_template(
|
||||||
|
[
|
||||||
|
{"role": "system", "content": system_message},
|
||||||
|
{"role": "user", "content": text},
|
||||||
|
],
|
||||||
|
add_generation_prompt=True,
|
||||||
|
tokenize=False,
|
||||||
|
enable_thinking=False
|
||||||
|
)
|
||||||
|
for text in input_sentences
|
||||||
|
]
|
||||||
|
|
||||||
|
responses = model.generate(input_data, use_tqdm=True)
|
||||||
|
results = [response.outputs[0].text for response in responses]
|
||||||
|
print(results)
|
||||||
|
# ["La persona che è stata scelta per la posizione ha dimostrato di avere un'ottima preparazione e di essere adeguatamente preparata.",
|
||||||
|
# "Verrà istituito un sistema di informazione per i soggetti che acquistano prodotti elettronici.",
|
||||||
|
# "La scadenza per la consegna del compito assegnato è prevista per venerdì."]
|
||||||
|
```
|
||||||
|
|
||||||
|
## License
|
||||||
|
|
||||||
|
We release this model under the Apache 2.0 license.
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
If you this model in your work, please cite:
|
||||||
|
|
||||||
|
```
|
||||||
|
@misc{piergentili2025genderneutralrewritingitalianmodels,
|
||||||
|
title={Gender-Neutral Rewriting in Italian: Models, Approaches, and Trade-offs},
|
||||||
|
author={Andrea Piergentili and Beatrice Savoldi and Matteo Negri and Luisa Bentivogli},
|
||||||
|
year={2025},
|
||||||
|
eprint={2509.13480},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL},
|
||||||
|
url={https://arxiv.org/abs/2509.13480},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
## Contributions
|
||||||
|
|
||||||
|
Thanks to [@apiergentili](https://huggingface.co/apiergentili) for adding this model.
|
||||||
|
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in message.content %}
|
||||||
|
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 17408,
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 40,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 40,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float32",
|
||||||
|
"transformers_version": "4.52.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"transformers_version": "4.52.3"
|
||||||
|
}
|
||||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00013.safetensors
Normal file
3
model-00001-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:faa19c0f74d07ad484c929a56628b6aaa911110242c741399e1be2d5ab415973
|
||||||
|
size 4684558368
|
||||||
3
model-00002-of-00013.safetensors
Normal file
3
model-00002-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:23ca6e6f6ab36feac304c6c5c83e5d8d211900c415fb3a029d5a3f09e3d1e79e
|
||||||
|
size 4676778920
|
||||||
3
model-00003-of-00013.safetensors
Normal file
3
model-00003-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:78cdfd3a8ce9c2c3e8d4bedfce2b2ef8743a3991bc666a173bc6a7583f0c519f
|
||||||
|
size 4928480056
|
||||||
3
model-00004-of-00013.safetensors
Normal file
3
model-00004-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8f2b207e039fc5bd4262ffe685eaaa6257f7d277f617b409b61e7570c3e6f652
|
||||||
|
size 4928480080
|
||||||
3
model-00005-of-00013.safetensors
Normal file
3
model-00005-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5d2983056e14141d9a9b86593c3e23d381fe1473433325ce9328e70d83adc9b8
|
||||||
|
size 4676778952
|
||||||
3
model-00006-of-00013.safetensors
Normal file
3
model-00006-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1c3e7f4f0d627cfafedb8fccb583f5aea351b1999a29ffa41149e05b1f7aaa14
|
||||||
|
size 4928480096
|
||||||
3
model-00007-of-00013.safetensors
Normal file
3
model-00007-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7a2514b745dc4fcad74a457cca92db30dbb110f25182a1bd606b5fa735ac856b
|
||||||
|
size 4928480096
|
||||||
3
model-00008-of-00013.safetensors
Normal file
3
model-00008-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:37b0dc78919a0d5fb2e4a1f19b713e08433651144e050d8bb6e43a69140ca6a0
|
||||||
|
size 4676778952
|
||||||
3
model-00009-of-00013.safetensors
Normal file
3
model-00009-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6ec041c8490d2093851e9d0de9efe7ba5ba4f12f3cc503507a7664761f19c75b
|
||||||
|
size 4928480096
|
||||||
3
model-00010-of-00013.safetensors
Normal file
3
model-00010-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:104316ec7f7d5d9c1274267e79de41adf5c879ece1a994b91051d133a011cd9e
|
||||||
|
size 4928480096
|
||||||
3
model-00011-of-00013.safetensors
Normal file
3
model-00011-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f4480071de053976c64780306ea54aec1ba4624b6c2e0bbb3f94956f1da8e7d7
|
||||||
|
size 4676778952
|
||||||
3
model-00012-of-00013.safetensors
Normal file
3
model-00012-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2cbf3bcbb874af44640b7495bdb505eee6a375e80253d3fb08f3d99c9684e313
|
||||||
|
size 2999075752
|
||||||
3
model-00013-of-00013.safetensors
Normal file
3
model-00013-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:facba960024e8c4baad69193baddfaa7616e9e0cd9d6b539a4e84c8c6d182343
|
||||||
|
size 3111649408
|
||||||
450
model.safetensors.index.json
Normal file
450
model.safetensors.index.json
Normal file
@@ -0,0 +1,450 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 59073228800
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00013-of-00013.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||||
|
"model.norm.weight": "model-00012-of-00013.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user