Views
No views yet
| 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 |
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:")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:")