metadata
license: apache-2.0
pandafish-3-7B-32k
pandafish-3-7B-32k is a merge of the following models using LazyMergekit:
- mistralai/Mistral-7B-Instruct-v0.2
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
- Locutusque/Hercules-4.0-Mistral-v0.2-7B
🧩 Configuration
models:
- model: alpindale/Mistral-7B-v0.2-hf
# No parameters necessary for base model
- model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
density: 0.53
weight: 0.4
- model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
parameters:
density: 0.53
weight: 0.3
- model: Locutusque/Hercules-4.0-Mistral-v0.2-7B
parameters:
density: 0.53
weight: 0.3
merge_method: dare_ties
base_model: alpindale/Mistral-7B-v0.2-hf
parameters:
int8_mask: true
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "ichigoberry/pandafish-3-7B-32k"
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"])