You can deploy this model and start earning money today!

RichardErkhov/
mcysqrd_-_MODULARMOJO_Mistral_V1-gguf

Name: mcysqrd_-_MODULARMOJO_Mistral_V1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MODULARMOJO_Mistral_V1 - GGUF

Model creator: https://huggingface.co/mcysqrd/
Original model: https://huggingface.co/mcysqrd/MODULARMOJO_Mistral_V1/

Name	Quant method	Size
MODULARMOJO_Mistral_V1.Q2_K.gguf	Q2_K	2.53GB
MODULARMOJO_Mistral_V1.IQ3_XS.gguf	IQ3_XS	2.81GB
MODULARMOJO_Mistral_V1.IQ3_S.gguf	IQ3_S	2.96GB
MODULARMOJO_Mistral_V1.Q3_K_S.gguf	Q3_K_S	2.95GB
MODULARMOJO_Mistral_V1.IQ3_M.gguf	IQ3_M	3.06GB
MODULARMOJO_Mistral_V1.Q3_K.gguf	Q3_K	3.28GB
MODULARMOJO_Mistral_V1.Q3_K_M.gguf	Q3_K_M	3.28GB
MODULARMOJO_Mistral_V1.Q3_K_L.gguf	Q3_K_L	3.56GB
MODULARMOJO_Mistral_V1.IQ4_XS.gguf	IQ4_XS	3.67GB
MODULARMOJO_Mistral_V1.Q4_0.gguf	Q4_0	3.83GB
MODULARMOJO_Mistral_V1.IQ4_NL.gguf	IQ4_NL	3.87GB
MODULARMOJO_Mistral_V1.Q4_K_S.gguf	Q4_K_S	3.2GB
MODULARMOJO_Mistral_V1.Q4_K.gguf	Q4_K	4.07GB
MODULARMOJO_Mistral_V1.Q4_K_M.gguf	Q4_K_M	4.07GB
MODULARMOJO_Mistral_V1.Q4_1.gguf	Q4_1	4.24GB
MODULARMOJO_Mistral_V1.Q5_0.gguf	Q5_0	4.65GB
MODULARMOJO_Mistral_V1.Q5_K_S.gguf	Q5_K_S	4.65GB
MODULARMOJO_Mistral_V1.Q5_K.gguf	Q5_K	4.78GB
MODULARMOJO_Mistral_V1.Q5_K_M.gguf	Q5_K_M	4.78GB
MODULARMOJO_Mistral_V1.Q5_1.gguf	Q5_1	5.07GB
MODULARMOJO_Mistral_V1.Q6_K.gguf	Q6_K	5.53GB
MODULARMOJO_Mistral_V1.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 pipeline_tag: text-generation tags:

finetuned inference: parameters: temperature: 0.01

A Mistral7B Instruct (https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) Finetune using QLoRA on the docs available in https://docs.modular.com/mojo/

The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.

Instruction format

python

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
import torch

device = "cuda" # the device to load the model onto

model_name = "mcysqrd/MODULARMOJO_Mistral_V1"
model = AutoModelForCausalLM.from_pretrained(model_name, 
                                             use_flash_attention_2=True,
                                             max_memory={0: "24GB"},
                                             device_map="auto", 
                                             trust_remote_code=True,
                                             low_cpu_mem_usage=True,
                                             return_dict=True,
                                             torch_dtype=torch.bfloat16,
                                            )
                                            
tokenizer = AutoTokenizer.from_pretrained(model_name,add_bos_token=True,trust_remote_code=True)

model.config.use_cache = True
def stream(user_prompt):
    runtimeFlag = "cuda:0"
    system_prompt = 'MODULAR_MOJO'
    B_INST, E_INST = "[INST]", "[/INST]"
    prompt = f"{system_prompt}{B_INST}{user_prompt.strip()}\n{E_INST}"
    inputs = tokenizer([prompt], return_tensors="pt").to(runtimeFlag)
    streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
    _ = model.generate(**inputs, streamer=streamer, max_new_tokens=1600)

stream("""can you translate this python code to mojo to make more performant making T as struct?
    class T():
        self.init(v:float):
            self.value=v
    
    def sum_objects(a:T,b:T)->T:
        return T(a.v+b.v)""")

RichardErkhov/mcysqrd_-_MODULARMOJO_Mistral_V1-gguf

Original model description:

Instruction format

RichardErkhov/
mcysqrd_-_MODULARMOJO_Mistral_V1-gguf