QuantFactory/ChimeraLlama-3-8B-v2-GGUF

Name: ChimeraLlama-3-8B-v2-GGUF
Availability: InStock

This is quantized version of mlabonne/ChimeraLlama-3-8B-v2 created using llama.cpp

Original Model Card

ChimeraLlama-3-8B-v2

ChimeraLlama-3-8B-v2 is a merge of the following models using LazyMergekit:

🧩 Configuration

yaml

models:
  - model: NousResearch/Meta-Llama-3-8B
    # No parameters necessary for base model
  - model: NousResearch/Meta-Llama-3-8B-Instruct
    parameters:
      density: 0.6
      weight: 0.55
  - model: mlabonne/OrpoLlama-3-8B
    parameters:
      density: 0.55
      weight: 0.05
  - model: cognitivecomputations/dolphin-2.9-llama3-8b
    parameters:
      density: 0.55
      weight: 0.1
  - model: Locutusque/llama-3-neural-chat-v1-8b
    parameters:
      density: 0.55
      weight: 0.05
  - model: cloudyu/Meta-Llama-3-8B-Instruct-DPO
    parameters:
      density: 0.55
      weight: 0.15
  - model: vicgalle/Configurable-Llama-3-8B-v0.3
    parameters:
      density: 0.55
      weight: 0.1
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
parameters:
  int8_mask: true
dtype: float16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/ChimeraLlama-3-8B-v2"
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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.99
IFEval (0-Shot)	44.69
BBH (3-Shot)	28.48
MATH Lvl 5 (4-Shot)	8.31
GPQA (0-shot)	4.70
MuSR (0-shot)	5.25
MMLU-PRO (5-shot)	28.54