You can deploy this model and start earning money today!

RichardErkhov/
touqir_-_Cyrax-7B-gguf

Name: touqir_-_Cyrax-7B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Cyrax-7B - GGUF

Model creator: https://huggingface.co/touqir/
Original model: https://huggingface.co/touqir/Cyrax-7B/

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

Original model description:

license: apache-2.0 language:

en library_name: transformers pipeline_tag: text-generation

Cyrax-7B

🏆 Evaluation

Open LLM Leaderboard

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
Cyrax-7B	75.98	72.95	88.19	64.6	77.01	83.9	69.22
Qwen-72B	73.6	65.19	85.94	77.37	60.19	82.48	70.43
Mixtral-8x7B-Instruct-v0.1-DPO	73.44	69.8	87.83	71.05	69.18	81.37	61.41
Mixtral-8x7B-Instruct-v0.1	72.7	70.14	87.55	71.4	64.98	81.06	61.11
llama2_70b_mmlu	68.24	65.61	87.37	71.89	49.15	82.4	52.99
falcon-180B	67.85	69.45	88.86	70.5	45.47	86.9	45.94

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "touqir/Cyrax-7B"
messages = [{"role": "user", "content": "What is Huggingface?"}]

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/touqir_-_Cyrax-7B-gguf