dawn17/StarlingMaid-2x7B-base
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: dawn17/StarlingMaid-2x7B-base
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 17:31:38 +08:00
commit cd36277ec0
13 changed files with 91366 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.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

29
README.md Normal file
View File

@@ -0,0 +1,29 @@
---
license: apache-2.0
---
---
base_model: /Users/dawn/git/models/Starling-LM-7B-beta
gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
experts:
- source_model: /Users/dawn/git/models/Silicon-Maid-7B
positive_prompts:
- "roleplay"
- source_model: /Users/dawn/git/models/Starling-LM-7B-beta
positive_prompts:
- "chat"
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
| Metric |Value|
|---------------------------------|----:|
|Avg. |70.20|
|AI2 Reasoning Challenge (25-Shot)|67.15|
|HellaSwag (10-Shot) |85.00|
|MMLU (5-Shot) |65.36|
|TruthfulQA (0-shot) |57.98|
|Winogrande (5-shot) |79.79|
|GSM8k (5-shot) |65.88|

4
added_tokens.json Normal file
View File

@@ -0,0 +1,4 @@
{
"<|end_of_turn|>": 32000,
"<|pad_0|>": 32001
}

31
config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"_name_or_path": "/Users/dawn/git/models/Starling-LM-7B-beta",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"model_type": "mixtral",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_local_experts": 2,
"output_router_logits": false,
"pad_token_id": 32000,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.39.3",
"use_cache": true,
"vocab_size": 32002
}

10
mergekit_moe_config.yml Normal file
View File

@@ -0,0 +1,10 @@
base_model: /Users/dawn/git/models/Starling-LM-7B-beta
gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
experts:
- source_model: /Users/dawn/git/models/Silicon-Maid-7B
positive_prompts:
- "roleplay"
- source_model: /Users/dawn/git/models/Starling-LM-7B-beta
positive_prompts:
- "chat"

3
model-00001-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:583c4a8fe147b70c4b43723592e05510db549ad415ac6d9b198d0ab1fc07d5d8
size 9919846472

3
model-00002-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:609ec6be7c6f123d79c6cd956f6648a6af93df88f700061c80b85e89488cfaba
size 9982454736

3
model-00003-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ae97c377d7b92e566816e7ee81668e25c63e4dabdedda65719b662c910f6ea09
size 5856061008

1
model.safetensors.index.json Normal file
View File

File diff suppressed because one or more lines are too long

28
special_tokens_map.json Normal file
View File

@@ -0,0 +1,28 @@
{
"additional_special_tokens": [
"<|end_of_turn|>",
"<|pad_0|>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|end_of_turn|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91147
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

69
tokenizer_config.json Normal file
View File

@@ -0,0 +1,69 @@
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<|end_of_turn|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|pad_0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|end_of_turn|>",
"<|pad_0|>"
],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|end_of_turn|>",
"legacy": true,
"max_length": 1000,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "<s>",
"pad_token_type_id": 0,
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": true
}