Downloads · 30 days
5
8% of all-time downloads
win10/Llama-3.3-WeDLM-12B-Base-Up-Scaling
Llama-3.3-WeDLM-12B-Base-Up-Scaling is a text generation model from win10. Use it when you need the model to write or continue text. The card lists the license as llama3.
本儲存庫提供一個「合併後」的基礎語言模型(base model)權重與對應的 Transformers 自訂模型程式碼(customcode)。合併規格與統計資訊已隨檔案一併提供(mergeplan.json、mergestats.json)。
Downloads · 30 days
5
8% of all-time downloads
All-time downloads
62
Public
Parameters
12.6B
25.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors25.2 GB · 100%
From the Hugging Face model README
本儲存庫提供一個「合併後」的基礎語言模型(base model)權重與對應的 Transformers 自訂模型程式碼(custom_code)。合併規格與統計資訊已隨檔案一併提供(merge_plan.json、merge_stats.json)。
注意:本模型為「Base」取向(未保證具備指令對齊/安全對齊行為)。如需對話/指令能力,建議自行再進行 SFT / DPO / RLHF 等微調流程。
以本倉庫 config.json 為準:
WeDLMForCausalLM(model_type: wedlm,需 trust_remote_code=True)num_hidden_layers: 52hidden_size: 4096intermediate_size: 14336num_attention_heads: 32num_key_value_heads: 8head_dim: 128max_position_embeddings: 16384rope_theta: 1,000,000vocab_size: 151,936dtype: bfloat16transformers_version: 4.57.1(建議使用相同或更新版本)合併規格記錄於 merge_plan.json:
merge_strategy: dusoutput_layers: 52output_vocab: 151,936(沿用 main 的 vocab)out_layer 計):
out_layer 0–27:來自 main(對應 src_layer 0–27)out_layer 28–51:來自 sub(對應 src_layer 8–31)合併統計(merge_stats.json):
shape_expansions: 84verification_issues: 0global_verification_issues: 0model-0000x-of-00005.safetensors + model.safetensors.index.jsonconfiguration_wedlm.pymodeling_wedlm.pytokenizer.json、tokenizer_config.json、special_tokens_map.jsonchat_template.jinjamerge_plan.jsonmerge_stats.jsonimport torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "win10/Llama-3.3-WeDLM-12B-Base-Up-Scaling"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_id,
trust_remote_code=True,
torch_dtype=torch.bfloat16,
device_map="auto",
)
prompt = "The theory of relativity states that"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
out = model.generate(
**inputs,
max_new_tokens=256,
do_sample=True,
temperature=0.7,
top_p=0.95,
)
print(tokenizer.decode(out[0], skip_special_tokens=True))
上游 WeDLM 提供 wedlm engine;若你的環境已能使用該推理引擎,可將 model_id 指向本倉庫模型以測試可用性(具體支援程度依你使用的 engine 版本而定)。
pip install git+https://github.com/tencent/WeDLM.git
from wedlm import LLM, SamplingParams
model_id = "win10/Llama-3.3-WeDLM-12B-Base-Up-Scaling"
llm = LLM(model=model_id)
prompt = "The theory of relativity states that"
outputs = llm.generate([prompt], SamplingParams(max_tokens=256))
print(outputs[0]["text"])
本倉庫屬於合併/衍生模型(derivative work),請同時遵守所有上游來源模型之授權條款與使用限制(包含但不限於):
tencent/WeDLM-8B-Base:Apache-2.0shb777/Llama-3.3-8B-Instruct-128K(以及其上游 Llama 3.3 系列):Llama 3.3 Community License(Hugging Face 顯示為 llama3.3)如需商用或再散佈(redistribution),請先完整閱讀並確認符合上述授權與可接受使用政策(AUP)。
資料依據(上游授權與模型描述、以及本倉庫合併規格/設定):WeDLM 模型頁的授權與使用方式 :contentReference[oaicite:0]{index=0};Llama 3.3 8B Instruct(allura-forge)授權標示 :contentReference[oaicite:1]{index=1};shb777 128K 版本授權標示 :contentReference[oaicite:2]{index=2};本倉庫檔案列表與合併檔案(`merge_plan.json`、`merge_stats.json`、`config.json`) :contentReference[oaicite:3]{index=3}
::contentReference[oaicite:4]{index=4}