Quantization made by Richard Erkhov.
pandafish-7b - GGUF
- Model creator: https://huggingface.co/ichigoberry/
- Original model: https://huggingface.co/ichigoberry/pandafish-7b/
| Name | Quant method | Size |
|---|---|---|
| pandafish-7b.Q2_K.gguf | Q2_K | 2.53GB |
| pandafish-7b.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| pandafish-7b.IQ3_S.gguf | IQ3_S | 2.96GB |
| pandafish-7b.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| pandafish-7b.IQ3_M.gguf | IQ3_M | 3.06GB |
| pandafish-7b.Q3_K.gguf | Q3_K | 3.28GB |
| pandafish-7b.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| pandafish-7b.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| pandafish-7b.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| pandafish-7b.Q4_0.gguf | Q4_0 | 3.83GB |
| pandafish-7b.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| pandafish-7b.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| pandafish-7b.Q4_K.gguf | Q4_K | 4.07GB |
| pandafish-7b.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| pandafish-7b.Q4_1.gguf | Q4_1 | 4.24GB |
| pandafish-7b.Q5_0.gguf | Q5_0 | 4.65GB |
| pandafish-7b.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| pandafish-7b.Q5_K.gguf | Q5_K | 4.78GB |
| pandafish-7b.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| pandafish-7b.Q5_1.gguf | Q5_1 | 5.07GB |
| pandafish-7b.Q6_K.gguf | Q6_K | 5.53GB |
| pandafish-7b.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
tags: - merge - mergekit - lazymergekit license: apache-2.0
pandafish-7b
pandafish-7b is an instruct model based on a Model Stock merge of the following models (via LazyMergekit):
🧩 Configuration
models:
- model: mistralai/Mistral-7B-v0.1
- model: mistralai/Mistral-7B-Instruct-v0.2
- model: CultriX/NeuralTrix-bf16
- model: OpenPipe/mistral-ft-optimized-1227
merge_method: model_stock
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16
🏆 Evals
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|---|---|---|---|---|---|
| pandafish-7b 📄 | 51.99 | 40 | 74.23 | 53.22 | 40.51 |
| mistralai/Mistral-7B-Instruct-v0.2 📄 | 54.81 | 38.5 | 71.64 | 66.82 | 42.29 |
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "ichigoberry/pandafish-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"])