You can deploy this model and start earning money today!

RichardErkhov/
automerger_-_YamshadowExperiment28-7B-gguf

Name: automerger_-_YamshadowExperiment28-7B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

YamshadowExperiment28-7B - GGUF

Model creator: https://huggingface.co/automerger/
Original model: https://huggingface.co/automerger/YamshadowExperiment28-7B/

Name	Quant method	Size
YamshadowExperiment28-7B.Q2_K.gguf	Q2_K	2.53GB
YamshadowExperiment28-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
YamshadowExperiment28-7B.IQ3_S.gguf	IQ3_S	2.96GB
YamshadowExperiment28-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
YamshadowExperiment28-7B.IQ3_M.gguf	IQ3_M	3.06GB
YamshadowExperiment28-7B.Q3_K.gguf	Q3_K	3.28GB
YamshadowExperiment28-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
YamshadowExperiment28-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
YamshadowExperiment28-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
YamshadowExperiment28-7B.Q4_0.gguf	Q4_0	3.83GB
YamshadowExperiment28-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
YamshadowExperiment28-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
YamshadowExperiment28-7B.Q4_K.gguf	Q4_K	4.07GB
YamshadowExperiment28-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
YamshadowExperiment28-7B.Q4_1.gguf	Q4_1	4.24GB
YamshadowExperiment28-7B.Q5_0.gguf	Q5_0	4.65GB
YamshadowExperiment28-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
YamshadowExperiment28-7B.Q5_K.gguf	Q5_K	4.78GB
YamshadowExperiment28-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
YamshadowExperiment28-7B.Q5_1.gguf	Q5_1	5.07GB
YamshadowExperiment28-7B.Q6_K.gguf	Q6_K	5.53GB
YamshadowExperiment28-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 tags:

merge
mergekit
lazymergekit
automerger base_model:
automerger/YamShadow-7B
yam-peleg/Experiment28-7B

🧪 YamshadowExperiment28-7B

🎉 YamshadowExperiment28-7B is currently the best-performing 7B model on the Open LLM Leaderboard (08 Apr 24). Use it with caution, as it is likely a sign of overfitting the benchmarks.

YamshadowExperiment28-7B is an automated merge created by Maxime Labonne using the following configuration.

🔍 Applications

This model uses a context window of 8k. I recommend using it with the Alpaca chat template (works perfectly with LM Studio).

The model can sometimes break and output a lot of "INST". From my experience, its excellent results on the Open LLM Leaderboard are probably a sign of overfitting.

⚡ Quantized models

GGUF: https://huggingface.co/automerger/YamshadowExperiment28-7B-GGUF

🏆 Evaluation

Open LLM Leaderboard

YamshadowExperiment28-7B is currently the best-performing 7B model on the Open LLM Leaderboard (08 Apr 24).

EQ-bench

Thanks to Samuel J. Paech, who kindly ran the evaluation.

Nous

Evaluation performed using LLM AutoEval. See the entire leaderboard here.

🌳 Model Family Tree

🧩 Configuration

yaml

slices:
  - sources:
      - model: automerger/YamShadow-7B
        layer_range: [0, 32]
      - model: yam-peleg/Experiment28-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: automerger/YamShadow-7B
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
random_seed: 0

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "automerger/YamshadowExperiment28-7B"
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"])

RichardErkhov/automerger_-_YamshadowExperiment28-7B-gguf