RichardErkhov/redscroll_-_Mistral-7B-v0.2-gguf

Quantization made by Richard Erkhov.

Mistral-7B-v0.2 - GGUF

Model creator: https://huggingface.co/redscroll/
Original model: https://huggingface.co/redscroll/Mistral-7B-v0.2/

Name	Quant method	Size
Mistral-7B-v0.2.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-v0.2.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-v0.2.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-v0.2.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-v0.2.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-v0.2.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-v0.2.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-v0.2.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-v0.2.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-v0.2.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-v0.2.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-v0.2.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-v0.2.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-v0.2.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-v0.2.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-v0.2.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-v0.2.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-v0.2.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-v0.2.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-v0.2.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-v0.2.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-v0.2.Q8_0.gguf	Q8_0	7.17GB

Original model description:

pipeline_tag: text-generation

Not my model(obviously); downloaded the Mistral release model from https://models.mistralcdn.com/mistral-7b-v0-2/mistral-7B-v0.2.tar and uploaded for my own sanity(and fine-tuning), since it's still not uploaded on Mistral repo.

The standard code works:

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained("redscroll/Mistral-7B-v0.2", torch_dtype=torch.bfloat16, device_map = "auto")
tokenizer = AutoTokenizer.from_pretrained("redscroll/Mistral-7B-v0.2")

input_text = "In my younger and more vulnerable years"

input_ids = tokenizer(input_text, return_tensors = "pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens = 500, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id)

print(tokenizer.decode(outputs[0]))