初始化项目，由ModelHub XC社区提供模型
Model: cs-552-2026-databand/group_model 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
|
||||
68
README.md
Normal file
68
README.md
Normal file
@@ -0,0 +1,68 @@
|
||||
---
|
||||
base_model:
|
||||
- cs-552-2026-databand/multilingual_model
|
||||
- cs-552-2026-databand/safety_model
|
||||
- cs-552-2026-databand/math_model
|
||||
- Qwen/Qwen3-1.7B
|
||||
- cs-552-2026-databand/general_knowledge_model
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
|
||||
---
|
||||
# group_final
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
## Merge Details
|
||||
### Merge Method
|
||||
|
||||
This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) as a base.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [cs-552-2026-databand/multilingual_model](https://huggingface.co/cs-552-2026-databand/multilingual_model)
|
||||
* [cs-552-2026-databand/safety_model](https://huggingface.co/cs-552-2026-databand/safety_model)
|
||||
* [cs-552-2026-databand/math_model](https://huggingface.co/cs-552-2026-databand/math_model)
|
||||
* [cs-552-2026-databand/general_knowledge_model](https://huggingface.co/cs-552-2026-databand/general_knowledge_model)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
base_model: Qwen/Qwen3-1.7B
|
||||
dtype: bfloat16
|
||||
merge_method: dare_ties
|
||||
modules:
|
||||
default:
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/math_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/general_knowledge_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/safety_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/multilingual_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: Qwen/Qwen3-1.7B
|
||||
parameters:
|
||||
int8_mask: 1.0
|
||||
normalize: 1.0
|
||||
```
|
||||
17
chat_template.jinja
Normal file
17
chat_template.jinja
Normal file
@@ -0,0 +1,17 @@
|
||||
{#- Training-compatible Qwen3 chat template with thinking disabled.
|
||||
Renders the same tokens as Qwen3 official + enable_thinking=false, plus
|
||||
{% generation %} markers around the assistant turn so trl.SFTTrainer can
|
||||
mask user tokens via assistant_only_loss=True. The generation markers are
|
||||
a no-op at inference. -#}
|
||||
{%- for message in messages -%}
|
||||
{%- if message.role == 'system' -%}
|
||||
{{- '<|im_start|>system\n' + message.content + '<|im_end|>\n' -}}
|
||||
{%- elif message.role == 'user' -%}
|
||||
{{- '<|im_start|>user\n' + message.content + '<|im_end|>\n' -}}
|
||||
{%- elif message.role == 'assistant' -%}
|
||||
{% generation %}{{ '<|im_start|>assistant\n<think>\n\n</think>\n\n' + message.content + '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{{- '<|im_start|>assistant\n<think>\n\n</think>\n\n' -}}
|
||||
{%- endif -%}
|
||||
63
config.json
Normal file
63
config.json
Normal file
@@ -0,0 +1,63 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.7.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.0"
|
||||
}
|
||||
15
merge_summary.json
Normal file
15
merge_summary.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"base_model": "Qwen/Qwen3-1.7B",
|
||||
"specialists": {
|
||||
"math": "cs-552-2026-databand/math_model",
|
||||
"knowledge": "cs-552-2026-databand/general_knowledge_model",
|
||||
"safety": "cs-552-2026-databand/safety_model",
|
||||
"multilingual": "cs-552-2026-databand/multilingual_model"
|
||||
},
|
||||
"density": 0.9,
|
||||
"weight": 1.0,
|
||||
"normalize": true,
|
||||
"int8_mask": true,
|
||||
"output_dir": "/scratch/runs/group_final",
|
||||
"hf_repo": null
|
||||
}
|
||||
23
mergekit.yaml
Normal file
23
mergekit.yaml
Normal file
@@ -0,0 +1,23 @@
|
||||
merge_method: dare_ties
|
||||
base_model: Qwen/Qwen3-1.7B
|
||||
dtype: bfloat16
|
||||
models:
|
||||
- model: cs-552-2026-databand/math_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- model: cs-552-2026-databand/general_knowledge_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- model: cs-552-2026-databand/safety_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- model: cs-552-2026-databand/multilingual_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
parameters:
|
||||
normalize: true
|
||||
int8_mask: true
|
||||
32
mergekit_config.yml
Normal file
32
mergekit_config.yml
Normal file
@@ -0,0 +1,32 @@
|
||||
base_model: Qwen/Qwen3-1.7B
|
||||
dtype: bfloat16
|
||||
merge_method: dare_ties
|
||||
modules:
|
||||
default:
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/math_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/general_knowledge_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/safety_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/multilingual_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: Qwen/Qwen3-1.7B
|
||||
parameters:
|
||||
int8_mask: 1.0
|
||||
normalize: 1.0
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:436c6fdf2bd32ef8c91db85959352cbd4b755859919053e9f18f57ff20778fe9
|
||||
size 4063515640
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_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|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user