初始化项目，由ModelHub XC社区提供模型
Model: prithivMLmods/Megatron-Opus-14B-2.1 Source: Original Platform
This commit is contained in:
ModelHub XC
41
.gitattributes
vendored
Normal file
41
.gitattributes
vendored
Normal file
@@ -0,0 +1,41 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
111
README.md
Normal file
111
README.md
Normal file
@@ -0,0 +1,111 @@
|
|||||||
|
---
|
||||||
|
license: llama3
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- zh
|
||||||
|
base_model:
|
||||||
|
- microsoft/phi-4
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
- math
|
||||||
|
- phi4
|
||||||
|
- trl
|
||||||
|
- sft
|
||||||
|
- LlamaForCausalLM
|
||||||
|
---
|
||||||
|
|
||||||
|
|
||||||
|
# **Megatron-Opus-14B-2.1 [ Exp ]**
|
||||||
|
|
||||||
|
[Megatron-Opus-14B-2.1 ] Exp finetuned from Microsoft's Phi-4 is a state-of-the-art open model developed with a focus on responsible problem solving and advanced reasoning capabilities. Built upon a diverse blend of synthetic datasets, carefully filtered public domain websites, and high-quality academic books and Q&A datasets, Megatron-Opus-14B-2.1 ensures that small, capable models are trained with datasets of exceptional depth and precision.
|
||||||
|
|
||||||
|
Megatron-Opus-14B-2.1 adopts a robust safety post-training approach using open-source and in-house synthetic datasets. This involves a combination of SFT (Supervised Fine-Tuning) and iterative DPO (Direct Preference Optimization) techniques, ensuring helpful and harmless outputs across various safety categories.
|
||||||
|
|
||||||
|
|
||||||
|
# **Dataset Info**
|
||||||
|
|
||||||
|
Megatron-Opus-14B-2.1 is fine-tuned on a carefully curated synthetic dataset generated using an advanced pipeline optimized for Chain of Thought (CoT) reasoning and Responsible Problem Breakdown (RPB) methodologies. This ensures that the model excels at:
|
||||||
|
|
||||||
|
- **Logical reasoning**
|
||||||
|
- **Step-by-step problem-solving**
|
||||||
|
- **Breaking down complex tasks into manageable parts**
|
||||||
|
|
||||||
|
The dataset also emphasizes responsible decision-making and fairness in generating solutions.
|
||||||
|
|
||||||
|
# **Run with Transformers**
|
||||||
|
|
||||||
|
```python
|
||||||
|
# pip install accelerate
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
import torch
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Megatron-Opus-14B-2.1")
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"prithivMLmods/Megatron-Opus-14B-2.1",
|
||||||
|
device_map="auto",
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
)
|
||||||
|
|
||||||
|
input_text = "Explain the concept of black holes."
|
||||||
|
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
|
||||||
|
|
||||||
|
outputs = model.generate(**input_ids, max_new_tokens=64)
|
||||||
|
print(tokenizer.decode(outputs[0]))
|
||||||
|
```
|
||||||
|
|
||||||
|
For chat-style interactions, use `tokenizer.apply_chat_template`:
|
||||||
|
|
||||||
|
```python
|
||||||
|
messages = [
|
||||||
|
{"role": "user", "content": "Explain the concept of black holes."},
|
||||||
|
]
|
||||||
|
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
|
||||||
|
|
||||||
|
outputs = model.generate(**input_ids, max_new_tokens=256)
|
||||||
|
print(tokenizer.decode(outputs[0]))
|
||||||
|
```
|
||||||
|
|
||||||
|
# **Intended Use**
|
||||||
|
|
||||||
|
Megatron-Opus-14B-2.1 is tailored for a wide range of applications, especially those involving **advanced reasoning**, **multilingual capabilities**, and **responsible problem-solving**. Its primary use cases include:
|
||||||
|
|
||||||
|
1. **Responsible Problem Solving**
|
||||||
|
- Breaking down complex problems into logical, actionable steps.
|
||||||
|
- Offering ethical, well-rounded solutions in academic and professional contexts.
|
||||||
|
|
||||||
|
2. **Advanced Reasoning Tasks**
|
||||||
|
- Excelling in mathematics, logic, and scientific reasoning.
|
||||||
|
- Providing detailed explanations and systematic answers.
|
||||||
|
|
||||||
|
3. **Content Generation**
|
||||||
|
- Assisting in generating high-quality content for various domains, including creative writing and technical documentation.
|
||||||
|
- Supporting marketers, writers, and educators with detailed and well-structured outputs.
|
||||||
|
|
||||||
|
4. **Educational Support**
|
||||||
|
- Acting as a virtual tutor for students by generating practice questions, answers, and detailed explanations.
|
||||||
|
- Helping educators design learning material that promotes critical thinking and step-by-step problem-solving.
|
||||||
|
|
||||||
|
5. **Customer Support & Dialogue Systems**
|
||||||
|
- Enabling chatbots and virtual assistants to provide accurate, helpful, and responsible responses.
|
||||||
|
- Enhancing customer service with reasoning-driven automation.
|
||||||
|
|
||||||
|
# **Limitations**
|
||||||
|
|
||||||
|
Despite its strengths, Megatron-Opus-14B-2.1 has some limitations that users should be aware of:
|
||||||
|
|
||||||
|
1. **Bias and Fairness**
|
||||||
|
- While great effort has been made to minimize biases, users should critically assess the model’s output in sensitive scenarios to avoid unintended bias.
|
||||||
|
|
||||||
|
2. **Contextual Interpretation**
|
||||||
|
- The model may occasionally misinterpret highly nuanced prompts or ambiguous contexts, leading to suboptimal responses.
|
||||||
|
|
||||||
|
3. **Knowledge Cutoff**
|
||||||
|
- Megatron-Opus-14B-2.1’s knowledge is static and based on the data available at the time of training. It does not include real-time updates or information on recent developments.
|
||||||
|
|
||||||
|
4. **Safety and Harmlessness**
|
||||||
|
- Despite post-training safety alignment, inappropriate or harmful outputs may still occur. Continuous monitoring and human oversight are advised when using the model in critical contexts.
|
||||||
|
|
||||||
|
5. **Computational Requirements**
|
||||||
|
- Deploying Megatron-Opus-14B-2.1 efficiently may require substantial computational resources, particularly for large-scale deployments or real-time applications.
|
||||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "...local/models/resolve/prithivMLmods/Megatron-Opus-14B-2.1",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 100257,
|
||||||
|
"eos_token_id": 100265,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 17920,
|
||||||
|
"max_position_embeddings": 16384,
|
||||||
|
"mlp_bias": false,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 40,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 10,
|
||||||
|
"original_max_position_embeddings": 16384,
|
||||||
|
"pad_token_id": 100351,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 250000,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.48.2",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 100352
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 100257,
|
||||||
|
"eos_token_id": 100265,
|
||||||
|
"max_length": 16384,
|
||||||
|
"pad_token_id": 100351,
|
||||||
|
"transformers_version": "4.48.2"
|
||||||
|
}
|
||||||
100001
merges.txt
Normal file
100001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:396cad397fe724063e35599b146b7da96167ce7808384d31cc39c5780e25427b
|
||||||
|
size 4965104128
|
||||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cd3434bf8b9141b581895992478847ec4fd0ee83f9d827ece537d17cacd8e04c
|
||||||
|
size 4954672384
|
||||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cbbd06ac4727c2de7ba54ea9b00613272bdf2c1e4f5145f161f56cb878d39ef8
|
||||||
|
size 4967790040
|
||||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6d3846e97525ee66a99cca1fed3ee83cc1d1b36705ccea2c534e018766df0cdb
|
||||||
|
size 4889146952
|
||||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4865cebad9abe5b1b458b4b629202621e7e4aebd5d5c11bb15000fc45ba9d436
|
||||||
|
size 4954672384
|
||||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ec3021a16d743e2dbc2963d9c1266f28df9fb9e0e6481e5ea82b6d4f907de552
|
||||||
|
size 4587670480
|
||||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|dummy_87|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "�",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
501273
tokenizer.json
Normal file
501273
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
791
tokenizer_config.json
Normal file
791
tokenizer_config.json
Normal file
@@ -0,0 +1,791 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"5809": {
|
||||||
|
"content": "�",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100256": {
|
||||||
|
"content": "<|dummy_0|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100257": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100258": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100259": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100260": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100261": {
|
||||||
|
"content": "<|dummy_1|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100262": {
|
||||||
|
"content": "<|dummy_2|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100263": {
|
||||||
|
"content": "<|dummy_3|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100264": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100265": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100266": {
|
||||||
|
"content": "<|im_sep|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100267": {
|
||||||
|
"content": "<|dummy_4|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100268": {
|
||||||
|
"content": "<|dummy_5|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100269": {
|
||||||
|
"content": "<|dummy_6|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100270": {
|
||||||
|
"content": "<|dummy_7|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100271": {
|
||||||
|
"content": "<|dummy_8|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100272": {
|
||||||
|
"content": "<|dummy_9|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100273": {
|
||||||
|
"content": "<|dummy_10|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100274": {
|
||||||
|
"content": "<|dummy_11|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100275": {
|
||||||
|
"content": "<|dummy_12|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100276": {
|
||||||
|
"content": "<|endofprompt|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100277": {
|
||||||
|
"content": "<|dummy_13|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100278": {
|
||||||
|
"content": "<|dummy_14|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100279": {
|
||||||
|
"content": "<|dummy_15|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100280": {
|
||||||
|
"content": "<|dummy_16|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100281": {
|
||||||
|
"content": "<|dummy_17|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100282": {
|
||||||
|
"content": "<|dummy_18|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100283": {
|
||||||
|
"content": "<|dummy_19|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100284": {
|
||||||
|
"content": "<|dummy_20|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100285": {
|
||||||
|
"content": "<|dummy_21|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100286": {
|
||||||
|
"content": "<|dummy_22|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100287": {
|
||||||
|
"content": "<|dummy_23|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100288": {
|
||||||
|
"content": "<|dummy_24|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100289": {
|
||||||
|
"content": "<|dummy_25|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100290": {
|
||||||
|
"content": "<|dummy_26|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100291": {
|
||||||
|
"content": "<|dummy_27|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100292": {
|
||||||
|
"content": "<|dummy_28|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100293": {
|
||||||
|
"content": "<|dummy_29|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100294": {
|
||||||
|
"content": "<|dummy_30|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100295": {
|
||||||
|
"content": "<|dummy_31|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100296": {
|
||||||
|
"content": "<|dummy_32|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100297": {
|
||||||
|
"content": "<|dummy_33|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100298": {
|
||||||
|
"content": "<|dummy_34|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100299": {
|
||||||
|
"content": "<|dummy_35|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100300": {
|
||||||
|
"content": "<|dummy_36|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100301": {
|
||||||
|
"content": "<|dummy_37|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100302": {
|
||||||
|
"content": "<|dummy_38|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100303": {
|
||||||
|
"content": "<|dummy_39|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100304": {
|
||||||
|
"content": "<|dummy_40|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100305": {
|
||||||
|
"content": "<|dummy_41|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100306": {
|
||||||
|
"content": "<|dummy_42|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100307": {
|
||||||
|
"content": "<|dummy_43|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100308": {
|
||||||
|
"content": "<|dummy_44|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100309": {
|
||||||
|
"content": "<|dummy_45|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100310": {
|
||||||
|
"content": "<|dummy_46|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100311": {
|
||||||
|
"content": "<|dummy_47|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100312": {
|
||||||
|
"content": "<|dummy_48|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100313": {
|
||||||
|
"content": "<|dummy_49|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100314": {
|
||||||
|
"content": "<|dummy_50|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100315": {
|
||||||
|
"content": "<|dummy_51|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100316": {
|
||||||
|
"content": "<|dummy_52|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100317": {
|
||||||
|
"content": "<|dummy_53|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100318": {
|
||||||
|
"content": "<|dummy_54|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100319": {
|
||||||
|
"content": "<|dummy_55|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100320": {
|
||||||
|
"content": "<|dummy_56|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100321": {
|
||||||
|
"content": "<|dummy_57|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100322": {
|
||||||
|
"content": "<|dummy_58|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100323": {
|
||||||
|
"content": "<|dummy_59|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100324": {
|
||||||
|
"content": "<|dummy_60|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100325": {
|
||||||
|
"content": "<|dummy_61|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100326": {
|
||||||
|
"content": "<|dummy_62|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100327": {
|
||||||
|
"content": "<|dummy_63|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100328": {
|
||||||
|
"content": "<|dummy_64|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100329": {
|
||||||
|
"content": "<|dummy_65|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100330": {
|
||||||
|
"content": "<|dummy_66|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100331": {
|
||||||
|
"content": "<|dummy_67|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100332": {
|
||||||
|
"content": "<|dummy_68|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100333": {
|
||||||
|
"content": "<|dummy_69|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100334": {
|
||||||
|
"content": "<|dummy_70|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100335": {
|
||||||
|
"content": "<|dummy_71|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100336": {
|
||||||
|
"content": "<|dummy_72|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100337": {
|
||||||
|
"content": "<|dummy_73|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100338": {
|
||||||
|
"content": "<|dummy_74|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100339": {
|
||||||
|
"content": "<|dummy_75|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100340": {
|
||||||
|
"content": "<|dummy_76|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100341": {
|
||||||
|
"content": "<|dummy_77|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100342": {
|
||||||
|
"content": "<|dummy_78|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100343": {
|
||||||
|
"content": "<|dummy_79|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100344": {
|
||||||
|
"content": "<|dummy_80|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100345": {
|
||||||
|
"content": "<|dummy_81|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100346": {
|
||||||
|
"content": "<|dummy_82|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100347": {
|
||||||
|
"content": "<|dummy_83|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100348": {
|
||||||
|
"content": "<|dummy_84|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100349": {
|
||||||
|
"content": "<|dummy_85|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100350": {
|
||||||
|
"content": "<|dummy_86|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100351": {
|
||||||
|
"content": "<|dummy_87|>",
|
||||||
|
"lstrip": true,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": true,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"bos_token": "<|endoftext|>",
|
||||||
|
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 16384,
|
||||||
|
"pad_token": "<|dummy_87|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"tokenizer_class": "GPT2Tokenizer",
|
||||||
|
"unk_token": "�"
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user