Update README.md
This commit is contained in:
ai-modelscope
34
.gitattributes
vendored
34
.gitattributes
vendored
@@ -1,47 +1,39 @@
|
|||||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
*.arrow 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
|
||||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.bz2 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
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
*.lfs.* 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
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
*.msgpack 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
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pb 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
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
*.rar 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
|
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
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tgz 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
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zip 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
|
|
||||||
*.safetensors 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
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|||||||
304
README.md
304
README.md
@@ -1,47 +1,269 @@
|
|||||||
---
|
---
|
||||||
license: Apache License 2.0
|
datasets:
|
||||||
|
- jan-hq/instruction-speech-v1
|
||||||
#model-type:
|
language:
|
||||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
- en
|
||||||
#- gpt
|
license: apache-2.0
|
||||||
|
tags:
|
||||||
#domain:
|
- sound language model
|
||||||
##如 nlp、cv、audio、multi-modal
|
|
||||||
#- nlp
|
|
||||||
|
|
||||||
#language:
|
|
||||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
|
||||||
#- cn
|
|
||||||
|
|
||||||
#metrics:
|
|
||||||
##如 CIDEr、Blue、ROUGE 等
|
|
||||||
#- CIDEr
|
|
||||||
|
|
||||||
#tags:
|
|
||||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
|
||||||
#- pretrained
|
|
||||||
|
|
||||||
#tools:
|
|
||||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
|
||||||
#- vllm
|
|
||||||
---
|
---
|
||||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
|
||||||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
|
||||||
|
|
||||||
SDK下载
|
## Model Details
|
||||||
```bash
|
|
||||||
#安装ModelScope
|
We have developed and released the family [llama3-s](https://huggingface.co/collections/homebrew-research/llama3-s-669df2139f0576abc6eb7405). This family is natively understanding audio and text input.
|
||||||
pip install modelscope
|
|
||||||
```
|
We continue to expand [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) with sound understanding capabilities by leveraging 700M tokens [Instruction Speech v1](https://huggingface.co/datasets/jan-hq/instruction-speech-v1) dataset.
|
||||||
|
|
||||||
|
**Model developers** Homebrew Research.
|
||||||
|
|
||||||
|
**Input** Text and sound.
|
||||||
|
|
||||||
|
**Output** Text.
|
||||||
|
|
||||||
|
**Model Architecture** Llama-3.
|
||||||
|
|
||||||
|
**Language(s):** English.
|
||||||
|
|
||||||
|
## Intended Use
|
||||||
|
|
||||||
|
**Intended Use Cases** This family is primarily intended for research applications. This version aims to further improve the LLM on sound understanding capabilities.
|
||||||
|
|
||||||
|
**Out-of-scope** The use of llama3-s in any manner that violates applicable laws or regulations is strictly prohibited.
|
||||||
|
|
||||||
|
## How to Get Started with the Model
|
||||||
|
|
||||||
|
Try the model out using [inference notebook](https://colab.research.google.com/drive/1VW_saWuNnOrl_nYCVksqqHpJmPQsyOOM).
|
||||||
|
|
||||||
|
First, we need to convert the audio file to sound tokens
|
||||||
|
|
||||||
```python
|
```python
|
||||||
#SDK模型下载
|
import torch
|
||||||
from modelscope import snapshot_download
|
import torchaudio
|
||||||
model_dir = snapshot_download('homebrewltd/llama3-s-2024-07-08')
|
from encodec import EncodecModel
|
||||||
```
|
from encodec.utils import convert_audio
|
||||||
Git下载
|
|
||||||
```
|
def audio_to_sound_tokens(audio_path, target_bandwidth=1.5, device="cuda"):
|
||||||
#Git模型下载
|
# Initialize Encodec
|
||||||
git clone https://www.modelscope.cn/homebrewltd/llama3-s-2024-07-08.git
|
model = EncodecModel.encodec_model_24khz()
|
||||||
|
model.set_target_bandwidth(target_bandwidth)
|
||||||
|
model.to(device)
|
||||||
|
|
||||||
|
# Load and preprocess audio
|
||||||
|
wav, sr = torchaudio.load(audio_path)
|
||||||
|
wav = convert_audio(wav, sr, model.sample_rate, model.channels)
|
||||||
|
wav = wav.unsqueeze(0).to(device)
|
||||||
|
|
||||||
|
# Encode audio
|
||||||
|
with torch.no_grad():
|
||||||
|
encoded_frames = model.encode(wav)
|
||||||
|
codes = torch.cat([encoded[0] for encoded in encoded_frames], dim=-1)
|
||||||
|
|
||||||
|
# Flatten codes
|
||||||
|
audio_code1, audio_code2 = codes[0][0], codes[0][1]
|
||||||
|
flatten_tokens = torch.stack((audio_code1, audio_code2), dim=1).flatten().tolist()
|
||||||
|
|
||||||
|
# Convert to sound tokens
|
||||||
|
result = ''.join(f'<|sound_{num:04d}|>' for num in flatten_tokens)
|
||||||
|
return f'<|sound_start|>{result}<|sound_end|>'
|
||||||
|
|
||||||
|
# Usage
|
||||||
|
sound_tokens = audio_to_sound_tokens("/path/to/your/audio/file")
|
||||||
```
|
```
|
||||||
|
|
||||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
Then, we can inference the model the same as any other LLM.
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, pipeline
|
||||||
|
|
||||||
|
def setup_pipeline(model_path, use_4bit=False, use_8bit=False):
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
||||||
|
|
||||||
|
model_kwargs = {"device_map": "auto"}
|
||||||
|
|
||||||
|
if use_4bit:
|
||||||
|
model_kwargs["quantization_config"] = BitsAndBytesConfig(
|
||||||
|
load_in_4bit=True,
|
||||||
|
bnb_4bit_compute_dtype=torch.bfloat16,
|
||||||
|
bnb_4bit_use_double_quant=True,
|
||||||
|
bnb_4bit_quant_type="nf4",
|
||||||
|
)
|
||||||
|
elif use_8bit:
|
||||||
|
model_kwargs["quantization_config"] = BitsAndBytesConfig(
|
||||||
|
load_in_8bit=True,
|
||||||
|
bnb_8bit_compute_dtype=torch.bfloat16,
|
||||||
|
bnb_8bit_use_double_quant=True,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
model_kwargs["torch_dtype"] = torch.bfloat16
|
||||||
|
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(model_path, **model_kwargs)
|
||||||
|
|
||||||
|
return pipeline("text-generation", model=model, tokenizer=tokenizer)
|
||||||
|
|
||||||
|
def generate_text(pipe, messages, max_new_tokens=64, temperature=0.0, do_sample=False):
|
||||||
|
generation_args = {
|
||||||
|
"max_new_tokens": max_new_tokens,
|
||||||
|
"return_full_text": False,
|
||||||
|
"temperature": temperature,
|
||||||
|
"do_sample": do_sample,
|
||||||
|
}
|
||||||
|
|
||||||
|
output = pipe(messages, **generation_args)
|
||||||
|
return output[0]['generated_text']
|
||||||
|
|
||||||
|
# Usage
|
||||||
|
llm_path = "jan-hq/Jan-Llama3s-0708"
|
||||||
|
pipe = setup_pipeline(llm_path, use_4bit=True)
|
||||||
|
messages = [
|
||||||
|
{"role": "user", "content": sound_tokens},
|
||||||
|
]
|
||||||
|
generated_text = generate_text(pipe, messages)
|
||||||
|
print(generated_text)
|
||||||
|
```
|
||||||
|
|
||||||
|
## Training process
|
||||||
|
|
||||||
|
**Training Metrics Image**: Below is a snapshot of the training loss curve visualized.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Hardware
|
||||||
|
|
||||||
|
**GPU Configuration**: Cluster of 8x NVIDIA H100-SXM-80GB.
|
||||||
|
**GPU Usage**:
|
||||||
|
- **Continual Training**: 8 hours.
|
||||||
|
|
||||||
|
### Training Arguments
|
||||||
|
|
||||||
|
| Parameter | Continual Training |
|
||||||
|
|----------------------------|-------------------------|
|
||||||
|
| **Epoch** | 1 |
|
||||||
|
| **Global batch size** | 128 |
|
||||||
|
| **Learning Rate** | 5e-5 |
|
||||||
|
| **Learning Scheduler** | Cosine with warmup |
|
||||||
|
| **Optimizer** | [Adam-mini](https://arxiv.org/abs/2406.16793) |
|
||||||
|
| **Warmup Ratio** | 0.1 |
|
||||||
|
| **Weight Decay** | 0.01 |
|
||||||
|
| **beta1** | 0.9 |
|
||||||
|
| **beta2** | 0.98 |
|
||||||
|
| **epsilon** | 1e-6 |
|
||||||
|
| **Gradient Cliping** | 1.0 |
|
||||||
|
|
||||||
|
###
|
||||||
|
Accelerate FSDP Config
|
||||||
|
|
||||||
|
```
|
||||||
|
compute_environment: LOCAL_MACHINE
|
||||||
|
debug: false
|
||||||
|
distributed_type: FSDP
|
||||||
|
downcast_bf16: 'no'
|
||||||
|
enable_cpu_affinity: true
|
||||||
|
fsdp_config:
|
||||||
|
fsdp_activation_checkpointing: true
|
||||||
|
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
||||||
|
fsdp_backward_prefetch: BACKWARD_PRE
|
||||||
|
fsdp_cpu_ram_efficient_loading: true
|
||||||
|
fsdp_forward_prefetch: false
|
||||||
|
fsdp_offload_params: false
|
||||||
|
fsdp_sharding_strategy: FULL_SHARD
|
||||||
|
fsdp_state_dict_type: SHARDED_STATE_DICT
|
||||||
|
fsdp_sync_module_states: true
|
||||||
|
fsdp_use_orig_params: false
|
||||||
|
machine_rank: 0
|
||||||
|
main_training_function: main
|
||||||
|
mixed_precision: bf16
|
||||||
|
num_machines: 1
|
||||||
|
num_processes: 8
|
||||||
|
rdzv_backend: static
|
||||||
|
same_network: true
|
||||||
|
tpu_env: []
|
||||||
|
tpu_use_cluster: false
|
||||||
|
tpu_use_sudo: false
|
||||||
|
use_cpu: false
|
||||||
|
```
|
||||||
|
|
||||||
|
## Examples
|
||||||
|
|
||||||
|
1. Good example:
|
||||||
|
```
|
||||||
|
# Question:
|
||||||
|
Does the following review have a positive or negative opinion of the movie?
|
||||||
|
|
||||||
|
i thought the relationships were wonderful ,
|
||||||
|
Options: A). negative; B). positive;
|
||||||
|
|
||||||
|
# Expected Output:
|
||||||
|
The review has a B). positive opinion about the movie because they think the relationships were wonderful.
|
||||||
|
|
||||||
|
# Model's Output:
|
||||||
|
The review is positive.
|
||||||
|
```
|
||||||
|
|
||||||
|
2. Misunderstanding example:
|
||||||
|
```
|
||||||
|
# Question:
|
||||||
|
Translate the following sentence to Russian:
|
||||||
|
6 Work in JOBS and careers after 40
|
||||||
|
|
||||||
|
Russian:
|
||||||
|
|
||||||
|
# Expected Output:
|
||||||
|
6 Работать в РАБОТАХ и карьере после 40
|
||||||
|
|
||||||
|
Russian (Cyrillic): 6 Работать в РАБОТАХ и карьере после 40
|
||||||
|
|
||||||
|
Let me explain this to you like you're five years old: This sentence means that people can still work and have careers, even if they're older than 40 years old. The words are in a different language, called Russian.
|
||||||
|
# Model's Output:
|
||||||
|
В случае, когда вы хотите перевести фразу "The first step is to identify the language of the text." на русский язык, вы можете использовать следующую фразу: "Первый шаг - определить язык текста."
|
||||||
|
```
|
||||||
|
|
||||||
|
3. Off-tracked example:
|
||||||
|
```
|
||||||
|
# Quesion:
|
||||||
|
Answer the following question: - The roots of the growing plants start to break up the rock - The plant acids dissolve the rock - The rock is broken down into smaller pieces - Erosion begins. What might be the first step of the process?
|
||||||
|
Answer:
|
||||||
|
|
||||||
|
# Expected Output:
|
||||||
|
The first step of the process might be: The roots of the growing plants start to break up the rock.
|
||||||
|
|
||||||
|
# Model's Output:
|
||||||
|
Step 1: Identify the key elements in the premise and hypothesis.
|
||||||
|
|
||||||
|
Premise: "A man in a blue shirt and a red hat is holding a sign."
|
||||||
|
Key elements: man, blue shirt, red hat, holding, sign
|
||||||
|
|
||||||
|
Hypothesis: "A man is holding a sign."
|
||||||
|
Key elements: man, holding, sign
|
||||||
|
|
||||||
|
Step 2: Compare the key elements in the premise and hypothesis.
|
||||||
|
|
||||||
|
In the premise, we have a man wearing a blue shirt and a red hat, while in the hypothesis, we only have a man. The premise also mentions that the man is holding a sign, which is also mentioned in the hypothesis.
|
||||||
|
|
||||||
|
Step 3: Determine if the hypothesis is entailed by the premise.
|
||||||
|
|
||||||
|
Since the hypothesis states that a man is holding a sign, and the premise confirms that a man is holding a sign, we can conclude that the hypothesis is entailed by the premise. The additional information about the man's clothing in the premise does not contradict or negate the
|
||||||
|
```
|
||||||
|
|
||||||
|
Despite being undertrained, the model demonstrates an emerging grasp of sound-text semantics.
|
||||||
|
|
||||||
|
|
||||||
|
## Citation Information
|
||||||
|
|
||||||
|
**BibTeX:**
|
||||||
|
|
||||||
|
```
|
||||||
|
@article{llama3-s: Sound Instruction Language Model 2024,
|
||||||
|
title={llama3-s},
|
||||||
|
author={Homebrew Research},
|
||||||
|
year=2024,
|
||||||
|
month=July},
|
||||||
|
url={https://huggingface.co/homebrew-research/llama3-s-0708}
|
||||||
|
```
|
||||||
|
|
||||||
|
## Acknowledgement
|
||||||
|
|
||||||
|
- **[WhisperSpeech](https://github.com/collabora/WhisperSpeech)**
|
||||||
|
|
||||||
|
- **[Encodec](https://github.com/facebookresearch/encodec)**
|
||||||
|
|
||||||
|
- **[Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)**
|
||||||
1
_special_tokens_maps.json
Normal file
1
_special_tokens_maps.json
Normal file
File diff suppressed because one or more lines are too long
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "./llama-3-sound-init",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 128000,
|
||||||
|
"eos_token_id": 128009,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 8192,
|
||||||
|
"mlp_bias": false,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 500000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.42.3",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 129282
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 128000,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
128001,
|
||||||
|
128009
|
||||||
|
],
|
||||||
|
"max_length": 4096,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_p": 0.9,
|
||||||
|
"transformers_version": "4.42.3"
|
||||||
|
}
|
||||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3782380be7731cdcd95610007af180b6ac8ff100ded2fd25f02e4dd688054264
|
||||||
|
size 4985103664
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6bb5ad078ee3dfbbc32b1ebf1299b93910f0cccdab7d1ecc18cce5e37b0dd53d
|
||||||
|
size 4999802720
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e3f5154126a257595f817d7d69ef90ea55d0d99d255c2141b949491c76cb20c6
|
||||||
|
size 4915916176
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be991b90391c99506dfabb4e764ed4dc9b720f971d1d8156f0b7a05eae6cbdc5
|
||||||
|
size 1176543800
|
||||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 16077332480
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|begin_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|eot_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
419797
tokenizer.json
Normal file
419797
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:f031131bb3a32c50650d362bc957b262f6aaabb28fae766089af1fd6f759bf85
|
||||||
|
size 2212654
|
||||||
10271
tokenizer_config.json
Normal file
10271
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
30413
trainer_state.json
Normal file
30413
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user