Mistral-7B
Collection
5 items • Updated • 1
Text Generation
Transformers
Safetensors
English
mistral
mergekit
Merge
roleplay
conversational
text-generation-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("FallenMerick/Iced-Lemon-Cookie-7B")
model = AutoModelForCausalLM.from_pretrained("FallenMerick/Iced-Lemon-Cookie-7B")
messages = [
{"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))Quick Links
Iced Lemon Cookie
This is a merge of pre-trained language models created using mergekit.
GGUF quants: https://huggingface.co/FaradayDotDev/Iced-Lemon-Cookie-7B-GGUF
Merge Details
Merge Method
This model was merged using the TIES merge method using saishf/Multi-Verse-RP-7B as a base.
Models Merged
The following models were included in the merge:
- Undi95/BigL-7B
- KatyTheCutie/LemonadeRP-4.5.3
- icefog72/IceLemonTeaRP-32k-7b
- SanjiWatsuki/Kunoichi-DPO-v2-7B
Configuration
The following YAML configuration was used to produce this model:
models:
- model: icefog72/IceLemonTeaRP-32k-7b
parameters:
density: 1.0
weight: 1.0
- model: Undi95/BigL-7B
parameters:
density: 0.4
weight: 1.0
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
density: 0.6
weight: 1.0
- model: KatyTheCutie/LemonadeRP-4.5.3
parameters:
density: 0.8
weight: 1.0
merge_method: ties
base_model: saishf/Multi-Verse-RP-7B
parameters:
normalize: true
dtype: float16
- Downloads last month
- 4
Model tree for FallenMerick/Iced-Lemon-Cookie-7B
Merge model
this model
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FallenMerick/Iced-Lemon-Cookie-7B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)