All scores for these benchmarks have been evaluated using the
Stability-AI/lm-evaluation-harness
.
The results of the benchmark scores are stored in
benchmark_scores
.
For detailed information on the scores and the conditions under which they were obtained, please refer to this link.
*1 From the
rinna's LM Benchmark
.
*2 Since there was no mention of these template versions in rinna's LM Benchmark, the scores were calculated without specifying a template.
🧩 Configuration
The model has been made with a custom version of the
mergekit
library (mixtral branch) and the following configuration:
base_model:rinna/youri-7b-chatgate_mode:hidden# one of "hidden", "cheap_embed", or "random"dtype:bfloat16# output dtype (float32, float16, or bfloat16)experts:-source_model:rinna/youri-7b-chatpositive_prompts:-"質問と回答の選択肢を入力として受け取り、選択肢から回答を選択してください。"-"前提と仮説の関係を含意、矛盾、中立の中から回答してください。"-"以下のテキストを、ポジティブまたはネガティブの感情クラスのいずれかに分類してください。"-"以下は、タスクを説明する指示と、文脈のある入力の組み合わせです。要求を適切に満たす応答を書きなさい。"-source_model:rinna/youri-7b-instructionpositive_prompts:-"質問に対する回答を題名と文章から一言で抽出してください。回答は名詞で答えてください。"-"与えられたニュース記事を要約してください。"-"与えられた文が文法的であるかを回答してください。"
The
positive_prompts
in the above configuration are extracted from the instructions of benchmarks that each model excels in.
For reference on the benchmarks for each model, please see the LM Benchmark at
rinna's LM Benchmark
.
These benchmarks provide a detailed overview of the areas where each individual model performs particularly well, guiding the effective use of the merged model in various natural language processing tasks.
💻 Usage
!pip install -q --upgrade transformers einops accelerate bitsandbytes
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "HachiML/youri-2x7b_dev"
torch.set_default_device("cuda")
# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
load_in_4bit=True,
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
model_name,
trust_remote_code=True
)
torch.set_default_device("cuda")
# Create input
instruction = "次の日本語を英語に翻訳してください。"input = "大規模言語モデル(だいきぼげんごモデル、英: large language model、LLM)は、多数のパラメータ(数千万から数十億)を持つ人工ニューラルネットワークで構成されるコンピュータ言語モデルで、膨大なラベルなしテキストを使用して自己教師あり学習または半教師あり学習によって訓練が行われる。"
prompt = f"""以下は、タスクを説明する指示と、文脈のある入力の組み合わせです。要求を適切に満たす応答を書きなさい。### 指示:{instruction}### 入力:{input}### 応答:"""# Tokenize the input string
token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
# Generate text using the modelwith torch.no_grad():
output_ids = model.generate(
token_ids.to(model.device),
max_new_tokens=200,
do_sample=True,
temperature=0.5,
pad_token_id=tokenizer.pad_token_id,
bos_token_id=tokenizer.bos_token_id,
eos_token_id=tokenizer.eos_token_id
)
# Decode and print the output
output = tokenizer.decode(output_ids.tolist()[0])
print(output)
Runs of HachiML youri-2x7b_dev on huggingface.co
21
Total runs
0
24-hour runs
2
3-day runs
6
7-day runs
15
30-day runs
More Information About youri-2x7b_dev huggingface.co Model
youri-2x7b_dev huggingface.co is an AI model on huggingface.co that provides youri-2x7b_dev's model effect (), which can be used instantly with this HachiML youri-2x7b_dev model. huggingface.co supports a free trial of the youri-2x7b_dev model, and also provides paid use of the youri-2x7b_dev. Support call youri-2x7b_dev model through api, including Node.js, Python, http.
youri-2x7b_dev huggingface.co is an online trial and call api platform, which integrates youri-2x7b_dev's modeling effects, including api services, and provides a free online trial of youri-2x7b_dev, you can try youri-2x7b_dev online for free by clicking the link below.
HachiML youri-2x7b_dev online free url in huggingface.co:
youri-2x7b_dev is an open source model from GitHub that offers a free installation service, and any user can find youri-2x7b_dev on GitHub to install. At the same time, huggingface.co provides the effect of youri-2x7b_dev install, users can directly use youri-2x7b_dev installed effect in huggingface.co for debugging and trial. It also supports api for free installation.