初始化项目，由ModelHub XC社区提供模型
Model: ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.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
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
316
README.md
Normal file
316
README.md
Normal file
@@ -0,0 +1,316 @@
|
|||||||
|
---
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
license: apache-2.0
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- merge
|
||||||
|
- mergekit
|
||||||
|
- lazymergekit
|
||||||
|
- bfloat16
|
||||||
|
- roleplay
|
||||||
|
- creative
|
||||||
|
- instruct
|
||||||
|
- anvita
|
||||||
|
- qwen
|
||||||
|
- nerd
|
||||||
|
- homer
|
||||||
|
- Qandora
|
||||||
|
base_model:
|
||||||
|
- bunnycore/Qandora-2.5-7B-Creative
|
||||||
|
- allknowingroger/HomerSlerp1-7B
|
||||||
|
- sethuiyer/Qwen2.5-7B-Anvita
|
||||||
|
- fblgit/cybertron-v4-qw7B-MGS
|
||||||
|
- jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0
|
||||||
|
- newsbang/Homer-v0.5-Qwen2.5-7B
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
model-index:
|
||||||
|
- name: Qwen2.5-7B-HomerAnvita-NerdMix
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: IFEval (0-Shot)
|
||||||
|
type: HuggingFaceH4/ifeval
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: inst_level_strict_acc and prompt_level_strict_acc
|
||||||
|
value: 77.08
|
||||||
|
name: strict accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: BBH (3-Shot)
|
||||||
|
type: BBH
|
||||||
|
args:
|
||||||
|
num_few_shot: 3
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 36.58
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MATH Lvl 5 (4-Shot)
|
||||||
|
type: hendrycks/competition_math
|
||||||
|
args:
|
||||||
|
num_few_shot: 4
|
||||||
|
metrics:
|
||||||
|
- type: exact_match
|
||||||
|
value: 29.53
|
||||||
|
name: exact match
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: GPQA (0-shot)
|
||||||
|
type: Idavidrein/gpqa
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 9.28
|
||||||
|
name: acc_norm
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MuSR (0-shot)
|
||||||
|
type: TAUR-Lab/MuSR
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 14.41
|
||||||
|
name: acc_norm
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MMLU-PRO (5-shot)
|
||||||
|
type: TIGER-Lab/MMLU-Pro
|
||||||
|
config: main
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 38.13
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
---
|
||||||
|
|
||||||
|
# ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
||||||
|
|
||||||
|
**ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix** is an advanced language model meticulously crafted by merging five pre-trained models using the powerful [mergekit](https://github.com/cg123/mergekit) framework. This fusion leverages the **Model Stock** merge method to combine the creative prowess of **Qandora**, the instructive capabilities of **Qwen-Instruct-Fusion**, the sophisticated blending of **HomerSlerp1**, the mathematical precision of **Cybertron-MGS**, and the uncensored expertise of **Qwen-Nerd**. The resulting model excels in creative text generation, contextual understanding, technical reasoning, and dynamic conversational interactions.
|
||||||
|
|
||||||
|
## 🚀 Merged Models
|
||||||
|
|
||||||
|
This model merge incorporates the following:
|
||||||
|
|
||||||
|
- [**bunnycore/Qandora-2.5-7B-Creative**](https://huggingface.co/bunnycore/Qandora-2.5-7B-Creative): Specializes in creative text generation, enhancing the model's ability to produce imaginative and diverse content.
|
||||||
|
|
||||||
|
- [**allknowingroger/HomerSlerp1-7B**](https://huggingface.co/allknowingroger/HomerSlerp1-7B): Utilizes spherical linear interpolation (SLERP) to blend model weights smoothly, ensuring a harmonious integration of different model attributes.
|
||||||
|
|
||||||
|
- [**sethuiyer/Qwen2.5-7B-Anvita**](https://huggingface.co/sethuiyer/Qwen2.5-7B-Anvita): Focuses on instruction-following capabilities, improving the model's performance in understanding and executing user commands.
|
||||||
|
|
||||||
|
- [**fblgit/cybertron-v4-qw7B-MGS**](https://huggingface.co/fblgit/cybertron-v4-qw7B-MGS): Enhances mathematical reasoning and precision, enabling the model to handle complex computational tasks effectively.
|
||||||
|
|
||||||
|
- [**jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0**](https://huggingface.co/jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0): Provides uncensored expertise and robust technical knowledge, making the model suitable for specialized technical support and information retrieval.
|
||||||
|
|
||||||
|
- [**newsbang/Homer-v0.5-Qwen2.5-7B**](https://huggingface.co/newsbang/Homer-v0.5-Qwen2.5-7B): Acts as the foundational conversational model, providing robust language comprehension and generation capabilities.
|
||||||
|
|
||||||
|
## 🧩 Merge Configuration
|
||||||
|
|
||||||
|
The configuration below outlines how the models are merged using the **Model Stock** method. This approach ensures a balanced and effective integration of the unique strengths from each source model.
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
# Merge configuration for ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix using Model Stock
|
||||||
|
|
||||||
|
models:
|
||||||
|
- model: bunnycore/Qandora-2.5-7B-Creative
|
||||||
|
- model: allknowingroger/HomerSlerp1-7B
|
||||||
|
- model: sethuiyer/Qwen2.5-7B-Anvita
|
||||||
|
- model: fblgit/cybertron-v4-qw7B-MGS
|
||||||
|
- model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0
|
||||||
|
merge_method: model_stock
|
||||||
|
base_model: newsbang/Homer-v0.5-Qwen2.5-7B
|
||||||
|
normalize: false
|
||||||
|
int8_mask: true
|
||||||
|
dtype: bfloat16
|
||||||
|
```
|
||||||
|
|
||||||
|
### Key Parameters
|
||||||
|
|
||||||
|
- **Merge Method (`merge_method`):** Utilizes the **Model Stock** method, as described in [Model Stock](https://arxiv.org/abs/2403.19522), to effectively combine multiple models by leveraging their strengths.
|
||||||
|
|
||||||
|
- **Models (`models`):** Specifies the list of models to be merged:
|
||||||
|
- **bunnycore/Qandora-2.5-7B-Creative:** Enhances creative text generation.
|
||||||
|
- **allknowingroger/HomerSlerp1-7B:** Facilitates smooth blending of model weights using SLERP.
|
||||||
|
- **sethuiyer/Qwen2.5-7B-Anvita:** Improves instruction-following capabilities.
|
||||||
|
- **fblgit/cybertron-v4-qw7B-MGS:** Enhances mathematical reasoning and precision.
|
||||||
|
- **jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0:** Provides uncensored technical expertise.
|
||||||
|
|
||||||
|
- **Base Model (`base_model`):** Defines the foundational model for the merge, which is **newsbang/Homer-v0.5-Qwen2.5-7B** in this case.
|
||||||
|
|
||||||
|
- **Normalization (`normalize`):** Set to `false` to retain the original scaling of the model weights during the merge.
|
||||||
|
|
||||||
|
- **INT8 Mask (`int8_mask`):** Enabled (`true`) to apply INT8 quantization masking, optimizing the model for efficient inference without significant loss in precision.
|
||||||
|
|
||||||
|
- **Data Type (`dtype`):** Uses `bfloat16` to maintain computational efficiency while ensuring high precision.
|
||||||
|
|
||||||
|
## 🏆 Performance Highlights
|
||||||
|
|
||||||
|
- **Creative Text Generation:** Enhanced ability to produce imaginative and diverse content suitable for creative writing, storytelling, and content creation.
|
||||||
|
|
||||||
|
- **Instruction Following:** Improved performance in understanding and executing user instructions, making the model more responsive and accurate in task execution.
|
||||||
|
|
||||||
|
- **Mathematical Reasoning:** Enhanced capability to handle complex computational tasks with high precision, suitable for technical and analytical applications.
|
||||||
|
|
||||||
|
- **Uncensored Technical Expertise:** Provides robust technical knowledge without content restrictions, making it ideal for specialized technical support and information retrieval.
|
||||||
|
|
||||||
|
|
||||||
|
- **Optimized Inference:** INT8 masking and `bfloat16` data type contribute to efficient computation, enabling faster response times without compromising quality.
|
||||||
|
|
||||||
|
## 🎯 Use Case & Applications
|
||||||
|
|
||||||
|
**ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix** is designed to excel in environments that demand a combination of creative generation, precise instruction following, mathematical reasoning, and technical expertise. Ideal applications include:
|
||||||
|
|
||||||
|
- **Creative Writing Assistance:** Aiding authors and content creators in generating imaginative narratives, dialogues, and descriptive text.
|
||||||
|
|
||||||
|
- **Interactive Storytelling and Role-Playing:** Enhancing dynamic and engaging interactions in role-playing games and interactive storytelling platforms.
|
||||||
|
|
||||||
|
- **Educational Tools and Tutoring Systems:** Providing detailed explanations, answering questions, and assisting in educational content creation with contextual understanding.
|
||||||
|
|
||||||
|
- **Technical Support and Customer Service:** Offering accurate and contextually relevant responses in technical support scenarios, improving user satisfaction.
|
||||||
|
|
||||||
|
- **Content Generation for Marketing:** Creating compelling and diverse marketing copy, social media posts, and promotional material with creative flair.
|
||||||
|
|
||||||
|
- **Mathematical Problem Solving:** Assisting in solving complex mathematical problems and providing step-by-step explanations for educational purposes.
|
||||||
|
|
||||||
|
- **Technical Documentation and Analysis:** Generating detailed technical documents, reports, and analyses with high precision and clarity.
|
||||||
|
|
||||||
|
## 📝 Usage
|
||||||
|
|
||||||
|
To utilize **ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix**, follow the steps below:
|
||||||
|
|
||||||
|
### Installation
|
||||||
|
|
||||||
|
First, install the necessary libraries:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
pip install -qU transformers accelerate
|
||||||
|
```
|
||||||
|
|
||||||
|
### Example Code
|
||||||
|
|
||||||
|
Below is an example of how to load and use the model for text generation:
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
|
||||||
|
import torch
|
||||||
|
|
||||||
|
# Define the model name
|
||||||
|
model_name = "ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix"
|
||||||
|
|
||||||
|
# Load the tokenizer
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||||
|
|
||||||
|
# Load the model
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_name,
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# Initialize the pipeline
|
||||||
|
text_generator = pipeline(
|
||||||
|
"text-generation",
|
||||||
|
model=model,
|
||||||
|
tokenizer=tokenizer,
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# Define the input prompt
|
||||||
|
prompt = "Explain the significance of artificial intelligence in modern healthcare."
|
||||||
|
|
||||||
|
# Generate the output
|
||||||
|
outputs = text_generator(
|
||||||
|
prompt,
|
||||||
|
max_new_tokens=150,
|
||||||
|
do_sample=True,
|
||||||
|
temperature=0.7,
|
||||||
|
top_k=50,
|
||||||
|
top_p=0.95
|
||||||
|
)
|
||||||
|
|
||||||
|
# Print the generated text
|
||||||
|
print(outputs[0]["generated_text"])
|
||||||
|
```
|
||||||
|
|
||||||
|
### Notes
|
||||||
|
|
||||||
|
- **Fine-Tuning:** This merged model may require fine-tuning to optimize performance for specific applications or domains.
|
||||||
|
|
||||||
|
- **Resource Requirements:** Ensure that your environment has sufficient computational resources, especially GPU-enabled hardware, to handle the model efficiently during inference.
|
||||||
|
|
||||||
|
- **Customization:** Users can adjust parameters such as `temperature`, `top_k`, and `top_p` to control the creativity and diversity of the generated text.
|
||||||
|
|
||||||
|
|
||||||
|
## 📜 License
|
||||||
|
|
||||||
|
This model is open-sourced under the **Apache-2.0 License**.
|
||||||
|
|
||||||
|
## 💡 Tags
|
||||||
|
|
||||||
|
- `merge`
|
||||||
|
- `mergekit`
|
||||||
|
- `model_stock`
|
||||||
|
- `Qwen`
|
||||||
|
- `Homer`
|
||||||
|
- `Anvita`
|
||||||
|
- `Nerd`
|
||||||
|
- `ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix`
|
||||||
|
- `bunnycore/Qandora-2.5-7B-Creative`
|
||||||
|
- `allknowingroger/HomerSlerp1-7B`
|
||||||
|
- `sethuiyer/Qwen2.5-7B-Anvita`
|
||||||
|
- `fblgit/cybertron-v4-qw7B-MGS`
|
||||||
|
- `jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0`
|
||||||
|
- `newsbang/Homer-v0.5-Qwen2.5-7B`
|
||||||
|
|
||||||
|
---
|
||||||
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
||||||
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ZeroXClem__Qwen2.5-7B-HomerAnvita-NerdMix)
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|-------------------|----:|
|
||||||
|
|Avg. |34.17|
|
||||||
|
|IFEval (0-Shot) |77.08|
|
||||||
|
|BBH (3-Shot) |36.58|
|
||||||
|
|MATH Lvl 5 (4-Shot)|29.53|
|
||||||
|
|GPQA (0-shot) | 9.28|
|
||||||
|
|MuSR (0-shot) |14.41|
|
||||||
|
|MMLU-PRO (5-shot) |38.13|
|
||||||
|
|
||||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<|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
|
||||||
|
}
|
||||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "newsbang/Homer-v0.5-Qwen2.5-7B",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 3584,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 18944,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 28,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 4,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.46.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 152064
|
||||||
|
}
|
||||||
15
mergekit_config.yml
Normal file
15
mergekit_config.yml
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
|
||||||
|
# Merge configuration for ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix using Model Stock
|
||||||
|
|
||||||
|
models:
|
||||||
|
- model: bunnycore/Qandora-2.5-7B-Creative
|
||||||
|
- model: allknowingroger/HomerSlerp1-7B
|
||||||
|
- model: sethuiyer/Qwen2.5-7B-Anvita
|
||||||
|
- model: fblgit/cybertron-v4-qw7B-MGS
|
||||||
|
- model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0
|
||||||
|
merge_method: model_stock
|
||||||
|
base_model: newsbang/Homer-v0.5-Qwen2.5-7B
|
||||||
|
normalize: false
|
||||||
|
int8_mask: true
|
||||||
|
dtype: bfloat16
|
||||||
|
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00016.safetensors
Normal file
3
model-00001-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3e51fe7ca2ea39232b4bdc1831f088cf8772cbcfdfde1d74c43b918de24aa808
|
||||||
|
size 1089994880
|
||||||
3
model-00002-of-00016.safetensors
Normal file
3
model-00002-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b85f9358804011f6e9ed213e9783bda2f1ae2738a3550e4064e5519edb300111
|
||||||
|
size 1089994896
|
||||||
3
model-00003-of-00016.safetensors
Normal file
3
model-00003-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:30b14cbf8b1ba57404d917c9671a18eefad55f00c5f116cec450879a1c85c82a
|
||||||
|
size 932241160
|
||||||
3
model-00004-of-00016.safetensors
Normal file
3
model-00004-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6efd7c7256d545eb7f4b9b6f15aa16f4e85647878c5517da88027e675490d5c3
|
||||||
|
size 932233912
|
||||||
3
model-00005-of-00016.safetensors
Normal file
3
model-00005-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:38cc542015bbae8ba9d5b80b24fb8c0d283893c7b619ab02c9f77673aa17bea3
|
||||||
|
size 932233912
|
||||||
3
model-00006-of-00016.safetensors
Normal file
3
model-00006-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3ef286a9d98e2e995c83340b84ccb72a4c6ec489d90e1d5db227a039a84553e5
|
||||||
|
size 932233912
|
||||||
3
model-00007-of-00016.safetensors
Normal file
3
model-00007-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:135dbe1ebb676a49828db23662d9eeb5eddddf039553de8471baaad99479e563
|
||||||
|
size 932233912
|
||||||
3
model-00008-of-00016.safetensors
Normal file
3
model-00008-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:fe889a2d4f0bb1e46341c8decbb0fa05321efabc17b715fa04475d9f26118b21
|
||||||
|
size 932233912
|
||||||
3
model-00009-of-00016.safetensors
Normal file
3
model-00009-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a07ff7990f60ffd4a44eddd6a51035488ed023de58c024efd2e1d424fbf0f53c
|
||||||
|
size 932233904
|
||||||
3
model-00010-of-00016.safetensors
Normal file
3
model-00010-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:28abf556716608ababa89d8682ad91f19050cabf15f0d6e3ff35d49cc01dfb77
|
||||||
|
size 932233912
|
||||||
3
model-00011-of-00016.safetensors
Normal file
3
model-00011-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9ecb5e9275cf4c920206e0380f83efb0e1721c1b50fc23bbca5cfce72b1b0843
|
||||||
|
size 932233912
|
||||||
3
model-00012-of-00016.safetensors
Normal file
3
model-00012-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b3081de0e453bd7de98779619c21779787c8c14f6974664cdfe49545c7673b7e
|
||||||
|
size 932233912
|
||||||
3
model-00013-of-00016.safetensors
Normal file
3
model-00013-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:dd8c1ea42b14ddae53ec2bf3ca981e25d1932128e7d873558f08ff30de3af550
|
||||||
|
size 932233904
|
||||||
3
model-00014-of-00016.safetensors
Normal file
3
model-00014-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:59ae06389346825d4ab4003451b51102215792fead49873b42882b7f7614a5de
|
||||||
|
size 932233888
|
||||||
3
model-00015-of-00016.safetensors
Normal file
3
model-00015-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7e1e0981d5cf703d5baddf103df85bd1f9d8d2502d7237340975064c93dac1bd
|
||||||
|
size 932233888
|
||||||
3
model-00016-of-00016.safetensors
Normal file
3
model-00016-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7ecfdd25f28bfad50689f7c6911df89ec62464bbcec2dd57a5f8eba363d1b35d
|
||||||
|
size 932233872
|
||||||
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
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
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
|||||||
|
{
|
||||||
|
"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
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"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,
|
||||||
|
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
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