pandafish-2-7b-32k
pandafish-2-7b-32k is a merge of the following models using LazyMergekit:
💬 Try it
Playground on Huggingface Space
Chat template: Mistral Instruct
⚡ Quantized models
- GGUF: ichigoberry/pandafish-2-7b-32k-GGUF
- GGUF: mradermacher/pandafish-2-7b-32k-GGUF
- MLX: 4bit
- EXL2: bartowski/pandafish-2-7b-32k-exl2
🏆 Evals
| Model | AGIEval | GPT4All | TruthfulQA | Bigbench | Average |
|---|---|---|---|---|---|
| 🐡 pandafish-2-7b-32k 📄 | 40.8 | 73.35 | 57.46 | 42.69 | 53.57 |
| Mistral-7B-Instruct-v0.2 📄 | 38.5 | 71.64 | 66.82 | 42.29 | 54.81 |
| dolphin-2.8-mistral-7b-v02 📄 | 38.99 | 72.22 | 51.96 | 40.41 | 50.9 |
🧩 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: 0.4
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-2-7b-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"])