You can deploy this model and start earning money today!

RichardErkhov/
frankenmerger_-_gemma-4b-instruct-v0.2-gguf

Name: frankenmerger_-_gemma-4b-instruct-v0.2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-4b-instruct-v0.2 - GGUF

Model creator: https://huggingface.co/frankenmerger/
Original model: https://huggingface.co/frankenmerger/gemma-4b-instruct-v0.2/

Name	Quant method	Size
gemma-4b-instruct-v0.2.Q2_K.gguf	Q2_K	1.6GB
gemma-4b-instruct-v0.2.IQ3_XS.gguf	IQ3_XS	1.74GB
gemma-4b-instruct-v0.2.IQ3_S.gguf	IQ3_S	1.82GB
gemma-4b-instruct-v0.2.Q3_K_S.gguf	Q3_K_S	1.82GB
gemma-4b-instruct-v0.2.IQ3_M.gguf	IQ3_M	1.85GB
gemma-4b-instruct-v0.2.Q3_K.gguf	Q3_K	1.98GB
gemma-4b-instruct-v0.2.Q3_K_M.gguf	Q3_K_M	1.98GB
gemma-4b-instruct-v0.2.Q3_K_L.gguf	Q3_K_L	2.11GB
gemma-4b-instruct-v0.2.IQ4_XS.gguf	IQ4_XS	2.17GB
gemma-4b-instruct-v0.2.Q4_0.gguf	Q4_0	2.25GB
gemma-4b-instruct-v0.2.IQ4_NL.gguf	IQ4_NL	2.27GB
gemma-4b-instruct-v0.2.Q4_K_S.gguf	Q4_K_S	2.27GB
gemma-4b-instruct-v0.2.Q4_K.gguf	Q4_K	2.38GB
gemma-4b-instruct-v0.2.Q4_K_M.gguf	Q4_K_M	2.38GB
gemma-4b-instruct-v0.2.Q4_1.gguf	Q4_1	2.46GB
gemma-4b-instruct-v0.2.Q5_0.gguf	Q5_0	2.66GB
gemma-4b-instruct-v0.2.Q5_K_S.gguf	Q5_K_S	2.66GB
gemma-4b-instruct-v0.2.Q5_K.gguf	Q5_K	2.73GB
gemma-4b-instruct-v0.2.Q5_K_M.gguf	Q5_K_M	2.73GB
gemma-4b-instruct-v0.2.Q5_1.gguf	Q5_1	2.87GB
gemma-4b-instruct-v0.2.Q6_K.gguf	Q6_K	3.1GB
gemma-4b-instruct-v0.2.Q8_0.gguf	Q8_0	4.01GB

Original model description:

widget:

messages:
- role: system content: >- You are a career counselor. The user will provide you with an individual looking for guidance in their professional life, and your task is to assist them in determining what careers they are most suited for based on their skills, interests, and experience. You should also conduct research into the various options available, explain the job market trends in different industries, and advice on which qualifications would be beneficial for pursuing particular fields.
- role: user content: Hey friend!
- role: assistant content: Hi! How may I help you?
- role: user content: >- I am interested in developing a career in software engineering. What would you recommend me to do?
messages:
- role: system content: You are a knowledgeable assistant. Help the user as much as you can.
- role: user content: How to become smarter?
messages:
- role: system content: You are a helpful assistant who provides concise responses.
- role: user content: Hi!
- role: assistant content: Hello there! How may I help you?
- role: user content: >- I need to cook a simple dinner. What ingredients should I prepare for?
messages:
- role: system content: >- You are a very creative assistant. User will give you a task, which you should complete with all your knowledge.
- role: user content: >- Write the novel story of an RPG game about group of survivor post apocalyptic world. inference: parameters: max_new_tokens: 256 temperature: 0.6 top_p: 0.95 top_k: 50 repetition_penalty: 1.2 license: apache-2.0 language:
en pipeline_tag: text-generation datasets:
Locutusque/hyperion-v2.0

This model is frankenmerge from gemma-2b-it. Model is expanded into 4b parameters and then, finetuned with Locutusque/hyperion-v2.0 (50k)

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "frankenmerger/gemma-4b-instruct-v0.2"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

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"])

RichardErkhov/frankenmerger_-_gemma-4b-instruct-v0.2-gguf

Original model description:

💻 Usage

RichardErkhov/
frankenmerger_-_gemma-4b-instruct-v0.2-gguf