Downloads · 30 days
26
4% of all-time downloads
RichardErkhov/mlabonne_-_ChimeraLlama-3-8B-gguf
mlabonne_-_ChimeraLlama-3-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
26
4% of all-time downloads
All-time downloads
695
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
ChimeraLlama-3-8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| ChimeraLlama-3-8B.Q2_K.gguf | Q2_K | 2.96GB |
| ChimeraLlama-3-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| ChimeraLlama-3-8B.IQ3_S.gguf | IQ3_S | 3.43GB |
| ChimeraLlama-3-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| ChimeraLlama-3-8B.IQ3_M.gguf | IQ3_M | 3.52GB |
| ChimeraLlama-3-8B.Q3_K.gguf | Q3_K | 3.74GB |
| ChimeraLlama-3-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| ChimeraLlama-3-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| ChimeraLlama-3-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| ChimeraLlama-3-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| ChimeraLlama-3-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| ChimeraLlama-3-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| ChimeraLlama-3-8B.Q4_K.gguf | Q4_K | 4.58GB |
| ChimeraLlama-3-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| ChimeraLlama-3-8B.Q4_1.gguf | Q4_1 | 4.78GB |
| ChimeraLlama-3-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| ChimeraLlama-3-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| ChimeraLlama-3-8B.Q5_K.gguf | Q5_K | 5.34GB |
| ChimeraLlama-3-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| ChimeraLlama-3-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| ChimeraLlama-3-8B.Q6_K.gguf | Q6_K | 6.14GB |
| ChimeraLlama-3-8B.Q8_0.gguf | Q8_0 | 7.95GB |
license: other tags:
ChimeraLlama-3-8B outperforms Llama 3 8B Instruct on Nous' benchmark suite.
ChimeraLlama-3-8B is a merge of the following models using LazyMergekit:
Evaluation performed using LLM AutoEval, see the entire leaderboard here.
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|---|---|---|---|---|---|
| mlabonne/ChimeraLlama-3-8B 📄 | 51.58 | 39.12 | 71.81 | 52.4 | 42.98 |
| meta-llama/Meta-Llama-3-8B-Instruct 📄 | 51.34 | 41.22 | 69.86 | 51.65 | 42.64 |
| mlabonne/OrpoLlama-3-8B 📄 | 48.63 | 34.17 | 70.59 | 52.39 | 37.36 |
| meta-llama/Meta-Llama-3-8B 📄 | 45.42 | 31.1 | 69.95 | 43.91 | 36.7 |
models:
- model: NousResearch/Meta-Llama-3-8B
# No parameters necessary for base model
- model: NousResearch/Meta-Llama-3-8B-Instruct
parameters:
density: 0.58
weight: 0.4
- model: mlabonne/OrpoLlama-3-8B
parameters:
density: 0.52
weight: 0.2
- model: Locutusque/Llama-3-Orca-1.0-8B
parameters:
density: 0.52
weight: 0.2
- model: abacusai/Llama-3-Smaug-8B
parameters:
density: 0.52
weight: 0.2
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
parameters:
int8_mask: true
dtype: float16
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/ChimeraLlama-3-8B"
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"])