invalid-coder_-_SOLAR-10.7B-Instruct-SOLARC-M-10.7B-slerp-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SOLAR-10.7B-Instruct-SOLARC-M-10.7B-slerp - GGUF

• Model creator: https://huggingface.co/invalid-coder/
• Original model: https://huggingface.co/invalid-coder/SOLAR-10.7B-Instruct-SOLARC-M-10.7B-slerp/

Original model description:

license: apache-2.0 tags:

• merge
• mergekit
• lazymergekit
• upstage/SOLAR-10.7B-Instruct-v1.0
• DopeorNope/SOLARC-M-10.7B

---

SOLAR-10.7B-Instruct-SOLARC-M-10.7B-slerp

SOLAR-10.7B-Instruct-SOLARC-M-10.7B-slerp is a merge of the following models using LazyMergekit:

• upstage/SOLAR-10.7B-Instruct-v1.0
• DopeorNope/SOLARC-M-10.7B

🧩 Configuration

slices:
  - sources:
      - model: upstage/SOLAR-10.7B-Instruct-v1.0
        layer_range: [0, 48]
      - model: DopeorNope/SOLARC-M-10.7B
        layer_range: [0, 48]
merge_method: slerp
base_model: upstage/SOLAR-10.7B-Instruct-v1.0
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 # fallback for rest of tensors

tokenizer_source: union

dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "invalid-coder/SOLAR-10.7B-Instruct-SOLARC-M-10.7B-slerp"
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"])