Downloads · 30 days
123
8% of all-time downloads
RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf
mychen76_-_mistral-7b-merged-dare-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
123
8% of all-time downloads
All-time downloads
1.5K
Public
Repo size
82.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf95.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
mistral-7b-merged-dare - GGUF
| Name | Quant method | Size |
|---|---|---|
| mistral-7b-merged-dare.Q2_K.gguf | Q2_K | 2.53GB |
| mistral-7b-merged-dare.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| mistral-7b-merged-dare.IQ3_S.gguf | IQ3_S | 2.96GB |
| mistral-7b-merged-dare.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| mistral-7b-merged-dare.IQ3_M.gguf | IQ3_M | 3.06GB |
| mistral-7b-merged-dare.Q3_K.gguf | Q3_K | 3.28GB |
| mistral-7b-merged-dare.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| mistral-7b-merged-dare.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| mistral-7b-merged-dare.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| mistral-7b-merged-dare.Q4_0.gguf | Q4_0 | 3.83GB |
| mistral-7b-merged-dare.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| mistral-7b-merged-dare.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| mistral-7b-merged-dare.Q4_K.gguf | Q4_K | 4.07GB |
| mistral-7b-merged-dare.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| mistral-7b-merged-dare.Q4_1.gguf | Q4_1 | 4.24GB |
| mistral-7b-merged-dare.Q5_0.gguf | Q5_0 | 4.65GB |
| mistral-7b-merged-dare.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| mistral-7b-merged-dare.Q5_K.gguf | Q5_K | 4.78GB |
| mistral-7b-merged-dare.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| mistral-7b-merged-dare.Q5_1.gguf | Q5_1 | 5.07GB |
| mistral-7b-merged-dare.Q6_K.gguf | Q6_K | 5.53GB |
| mistral-7b-merged-dare.Q8_0.gguf | Q8_0 | 7.17GB |
license: apache-2.0 tags:
mistral-7b-merged-dare is a merge of the following models:
models:
- model: mistralai/Mistral-7B-v0.1
- model: samir-fama/SamirGPT-v1
parameters:
density: 0.53
weight: 0.4
- model: abacusai/Slerp-CM-mist-dpo
parameters:
density: 0.53
weight: 0.3
- model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
parameters:
density: 0.53
weight: 0.3
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mayacinka/West-Ramen-7Bx4"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 73.46 |
| AI2 Reasoning Challenge (25-Shot) | 69.71 |
| HellaSwag (10-Shot) | 87.05 |
| MMLU (5-Shot) | 65.07 |
| TruthfulQA (0-shot) | 63.24 |
| Winogrande (5-shot) | 81.61 |
| GSM8k (5-shot) | 73.01 |