Downloads · 30 days
122
1% of all-time downloads
cloudyu_-_Mixtral_7Bx5_MoE_30B-gguf
RichardErkhov/cloudyu_-_Mixtral_7Bx5_MoE_30B-gguf
cloudyu_-_Mixtral_7Bx5_MoE_30B-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.
All-time downloads
10.2K
Public
Repo size
336 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf389 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 25, 2024
- Updated
- Jul 26, 2024
- SHA
- d0126a68
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Mixtral_7Bx5_MoE_30B - GGUF
- Model creator: https://huggingface.co/cloudyu/
- Original model: https://huggingface.co/cloudyu/Mixtral_7Bx5_MoE_30B/
| Name | Quant method | Size |
|---|---|---|
| Mixtral_7Bx5_MoE_30B.Q2_K.gguf | Q2_K | 10.14GB |
| Mixtral_7Bx5_MoE_30B.IQ3_XS.gguf | IQ3_XS | 11.35GB |
| Mixtral_7Bx5_MoE_30B.IQ3_S.gguf | IQ3_S | 11.99GB |
| Mixtral_7Bx5_MoE_30B.Q3_K_S.gguf | Q3_K_S | 11.97GB |
| Mixtral_7Bx5_MoE_30B.IQ3_M.gguf | IQ3_M | 12.2GB |
| Mixtral_7Bx5_MoE_30B.Q3_K.gguf | Q3_K | 13.29GB |
| Mixtral_7Bx5_MoE_30B.Q3_K_M.gguf | Q3_K_M | 13.29GB |
| Mixtral_7Bx5_MoE_30B.Q3_K_L.gguf | Q3_K_L | 14.39GB |
| Mixtral_7Bx5_MoE_30B.IQ4_XS.gguf | IQ4_XS | 14.97GB |
| Mixtral_7Bx5_MoE_30B.Q4_0.gguf | Q4_0 | 15.64GB |
| Mixtral_7Bx5_MoE_30B.IQ4_NL.gguf | IQ4_NL | 15.79GB |
| Mixtral_7Bx5_MoE_30B.Q4_K_S.gguf | Q4_K_S | 15.78GB |
| Mixtral_7Bx5_MoE_30B.Q4_K.gguf | Q4_K | 16.79GB |
| Mixtral_7Bx5_MoE_30B.Q4_K_M.gguf | Q4_K_M | 16.79GB |
| Mixtral_7Bx5_MoE_30B.Q4_1.gguf | Q4_1 | 17.37GB |
| Mixtral_7Bx5_MoE_30B.Q5_0.gguf | Q5_0 | 19.09GB |
| Mixtral_7Bx5_MoE_30B.Q5_K_S.gguf | Q5_K_S | 19.09GB |
| Mixtral_7Bx5_MoE_30B.Q5_K.gguf | Q5_K | 19.68GB |
| Mixtral_7Bx5_MoE_30B.Q5_K_M.gguf | Q5_K_M | 19.68GB |
| Mixtral_7Bx5_MoE_30B.Q5_1.gguf | Q5_1 | 20.82GB |
| Mixtral_7Bx5_MoE_30B.Q6_K.gguf | Q6_K | 22.76GB |
| Mixtral_7Bx5_MoE_30B.Q8_0.gguf | Q8_0 | 29.48GB |
Original model description:
license: cc-by-nc-4.0
Mixtral MOE 5x7B
MoE of the following models :
- Toten5/Marcoroni-neural-chat-7B-v1
- NurtureAI/neural-chat-7b-v3-16k
- mncai/mistral-7b-dpo-v6
- cookinai/CatMacaroni-Slerp
- ignos/Mistral-T5-7B-v1
gpu code example
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
## v2 models
model_path = "cloudyu/Mixtral_7Bx5_MoE_30B"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
CPU example
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
## v2 models
model_path = "cloudyu/Mixtral_7Bx5_MoE_30B"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
- Created
- Jul 25, 2024
- Updated
- Jul 26, 2024