You can deploy this model and start earning money today!

RichardErkhov/
automerger_-_ShadowYam-7B-gguf

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

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ShadowYam-7B - GGUF

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

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

Original model description:

license: apache-2.0 tags:

merge
mergekit
lazymergekit
automerger base_model:
mayacinka/yam-jom-7B

ShadowYam-7B

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

mayacinka/yam-jom-7B

🧩 Configuration

yaml

models:
- model: CorticalStack/shadow-clown-7B-slerp
  # No parameters necessary for base model
- model: mayacinka/yam-jom-7B
  parameters:
    density: 0.53
    weight: 0.6
merge_method: dare_ties
base_model: CorticalStack/shadow-clown-7B-slerp
parameters:
int8_mask: true
dtype: bfloat16
random_seed: 0
    ```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "automerger/ShadowYam-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_-_ShadowYam-7B-gguf

Original model description:

ShadowYam-7B

🧩 Configuration

RichardErkhov/
automerger_-_ShadowYam-7B-gguf