Quantization made by Richard Erkhov.
RolePlayLake-7B - GGUF
- Model creator: https://huggingface.co/fhai50032/
- Original model: https://huggingface.co/fhai50032/RolePlayLake-7B/
Name | Quant method | Size |
---|---|---|
RolePlayLake-7B.Q2_K.gguf | Q2_K | 2.53GB |
RolePlayLake-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
RolePlayLake-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
RolePlayLake-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
RolePlayLake-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
RolePlayLake-7B.Q3_K.gguf | Q3_K | 3.28GB |
RolePlayLake-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
RolePlayLake-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
RolePlayLake-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
RolePlayLake-7B.Q4_0.gguf | Q4_0 | 3.83GB |
RolePlayLake-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
RolePlayLake-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
RolePlayLake-7B.Q4_K.gguf | Q4_K | 4.07GB |
RolePlayLake-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
RolePlayLake-7B.Q4_1.gguf | Q4_1 | 4.24GB |
RolePlayLake-7B.Q5_0.gguf | Q5_0 | 4.65GB |
RolePlayLake-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
RolePlayLake-7B.Q5_K.gguf | Q5_K | 4.78GB |
RolePlayLake-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
RolePlayLake-7B.Q5_1.gguf | Q5_1 | 5.07GB |
RolePlayLake-7B.Q6_K.gguf | Q6_K | 5.53GB |
RolePlayLake-7B.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0 tags: - merge - mergekit - mistral - SanjiWatsuki/Silicon-Maid-7B - senseable/WestLake-7B-v2 base_model: - SanjiWatsuki/Silicon-Maid-7B - senseable/WestLake-7B-v2 model-index: - name: RolePlayLake-7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 70.56 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/RolePlayLake-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 87.42 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/RolePlayLake-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 64.55 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/RolePlayLake-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 64.38 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/RolePlayLake-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 83.27 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/RolePlayLake-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 65.05 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/RolePlayLake-7B name: Open LLM Leaderboard
RolePlayLake-7B
RolePlayLake-7B is a merge of the following models :
In my current testing RolePlayLake is Better than Silicon_Maid in RP and More Uncensored Than WestLake
I would try to only merge Uncensored Models with Baising towards Chat rather than Instruct
🧩 Configuration
slices:
- sources:
- model: SanjiWatsuki/Silicon-Maid-7B
layer_range: [0, 32]
- model: senseable/WestLake-7B-v2
layer_range: [0, 32]
merge_method: slerp
base_model: senseable/WestLake-7B-v2
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "fhai50032/RolePlayLake-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Why I Merged WestLake and Silicon Maid
Merged WestLake and Silicon Maid for a unique blend:
- EQ-Bench Dominance: WestLake's 79.75 EQ-Bench score. (Maybe Contaminated)
- Charm and Role-Play: Silicon's explicit charm and WestLake's role-play prowess.
- Config Synergy: Supports lots of prompt format out of the gate and has a very nice synergy
Result: RolePlayLake-7B, a linguistic fusion with EQ-Bench supremacy and captivating role-play potential.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 72.54 |
AI2 Reasoning Challenge (25-Shot) | 70.56 |
HellaSwag (10-Shot) | 87.42 |
MMLU (5-Shot) | 64.55 |
TruthfulQA (0-shot) | 64.38 |
Winogrande (5-shot) | 83.27 |
GSM8k (5-shot) | 65.05 |