You can deploy this model and start earning money today!

RichardErkhov/
MaziyarPanahi_-_calme-2.1-llama3.1-70b-gguf

Name: MaziyarPanahi_-_calme-2.1-llama3.1-70b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

calme-2.1-llama3.1-70b - GGUF

Model creator: https://huggingface.co/MaziyarPanahi/
Original model: https://huggingface.co/MaziyarPanahi/calme-2.1-llama3.1-70b/

Name	Quant method	Size
calme-2.1-llama3.1-70b.Q2_K.gguf	Q2_K	24.56GB
calme-2.1-llama3.1-70b.IQ3_XS.gguf	IQ3_XS	27.29GB
calme-2.1-llama3.1-70b.IQ3_S.gguf	IQ3_S	28.79GB
calme-2.1-llama3.1-70b.Q3_K_S.gguf	Q3_K_S	28.79GB
calme-2.1-llama3.1-70b.IQ3_M.gguf	IQ3_M	29.74GB
calme-2.1-llama3.1-70b.Q3_K.gguf	Q3_K	31.91GB
calme-2.1-llama3.1-70b.Q3_K_M.gguf	Q3_K_M	31.91GB
calme-2.1-llama3.1-70b.Q3_K_L.gguf	Q3_K_L	34.59GB
calme-2.1-llama3.1-70b.IQ4_XS.gguf	IQ4_XS	35.64GB
calme-2.1-llama3.1-70b.Q4_0.gguf	Q4_0	37.22GB
calme-2.1-llama3.1-70b.IQ4_NL.gguf	IQ4_NL	37.58GB
calme-2.1-llama3.1-70b.Q4_K_S.gguf	Q4_K_S	37.58GB
calme-2.1-llama3.1-70b.Q4_K.gguf	Q4_K	39.6GB
calme-2.1-llama3.1-70b.Q4_K_M.gguf	Q4_K_M	39.6GB
calme-2.1-llama3.1-70b.Q4_1.gguf	Q4_1	41.27GB
calme-2.1-llama3.1-70b.Q5_0.gguf	Q5_0	45.32GB
calme-2.1-llama3.1-70b.Q5_K_S.gguf	Q5_K_S	45.32GB
calme-2.1-llama3.1-70b.Q5_K.gguf	Q5_K	46.52GB
calme-2.1-llama3.1-70b.Q5_K_M.gguf	Q5_K_M	46.52GB
calme-2.1-llama3.1-70b.Q5_1.gguf	Q5_1	49.36GB
calme-2.1-llama3.1-70b.Q6_K.gguf	Q6_K	53.91GB
calme-2.1-llama3.1-70b.Q8_0.gguf	Q8_0	69.83GB

Original model description:

language:

en pipeline_tag: text-generation tags:
chat
llama
facebook
llaam3
finetune
chatml library_name: transformers inference: false model_creator: MaziyarPanahi quantized_by: MaziyarPanahi base_model: meta-llama/Meta-Llama-3.1-70B-Instruct model_name: calme-2.1-llama3.1-70b datasets:
MaziyarPanahi/truthy-dpo-v0.1-axolotl

MaziyarPanahi/calme-2.1-llama3.1-70b

This model is a fine-tuned version of the powerful meta-llama/Meta-Llama-3.1-70B-Instruct, pushing the boundaries of natural language understanding and generation even further. My goal was to create a versatile and robust model that excels across a wide range of benchmarks and real-world applications.

Use Cases

This model is suitable for a wide range of applications, including but not limited to:

Advanced question-answering systems
Intelligent chatbots and virtual assistants
Content generation and summarization
Code generation and analysis
Complex problem-solving and decision support

⚡ Quantized GGUF

All GGUF models are available here: MaziyarPanahi/calme-2.1-llama3.1-70b-GGUF

🏆 Open LLM Leaderboard Evaluation Results

coming soon!

This model uses ChatML prompt template:

<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}

How to use

python

# Use a pipeline as a high-level helper

from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.1-llama3.1-70b")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.1-llama3.1-70b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.1-llama3.1-70b")

Ethical Considerations

As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.

RichardErkhov/MaziyarPanahi_-_calme-2.1-llama3.1-70b-gguf