MaziyarPanahi / calme-2.4-llama3-70b

huggingface.co
Total runs: 2.9K
24-hour runs: -2
7-day runs: 77
30-day runs: 508
Model's Last Updated: July 20 2024
text-generation

Introduction of calme-2.4-llama3-70b

Model Details of calme-2.4-llama3-70b

Llama-3 DPO Logo

MaziyarPanahi/calme-2.4-llama3-70b

This model is a fine-tune (DPO) of meta-llama/Meta-Llama-3-70B-Instruct model.

⚡ Quantized GGUF

All GGUF models are available here: MaziyarPanahi/calme-2.4-llama3-70b-GGUF

🏆 Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 32.18
IFEval (0-Shot) 50.27
BBH (3-Shot) 48.40
MATH Lvl 5 (4-Shot) 22.66
GPQA (0-shot) 11.97
MuSR (0-shot) 13.10
MMLU-PRO (5-shot) 46.71
Metric Value
Avg. 78.89
AI2 Reasoning Challenge (25-Shot) 72.61
HellaSwag (10-Shot) 86.03
MMLU (5-Shot) 80.50
TruthfulQA (0-shot) 63.26
Winogrande (5-shot) 83.58
GSM8k (5-shot) 87.34

Top 10 models on the Leaderboard Llama-3-70B finet-tuned models

Prompt Template

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

You can use this model by using MaziyarPanahi/calme-2.4-llama3-70b as the model name in Hugging Face's transformers library.

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from transformers import pipeline
import torch

model_id = "MaziyarPanahi/calme-2.4-llama3-70b"

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
    # attn_implementation="flash_attention_2"
)

tokenizer = AutoTokenizer.from_pretrained(
    model_id,
    trust_remote_code=True
)

streamer = TextStreamer(tokenizer)

pipeline = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    model_kwargs={"torch_dtype": torch.bfloat16},
    streamer=streamer
)

# Then you can use the pipeline to generate text.

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|im_end|>"),
    tokenizer.convert_tokens_to_ids("<|eot_id|>") # safer to have this too
]

outputs = pipeline(
    prompt,
    max_new_tokens=2048,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.95,
)
print(outputs[0]["generated_text"][len(prompt):])
Sample Response
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
describe about pros and cons of docker system.<|im_end|>
<|im_start|>assistant
Here are the pros and cons of the Docker system:

**Pros:**

1. **Lightweight**: Docker containers are lightweight and use fewer resources compared to traditional virtual machines.
2. **Isolation**: Docker provides a high level of isolation between containers, ensuring that each application runs independently without interfering with others.
3. **Portability**: Docker containers are highly portable and can run on any system that supports Docker, without requiring specific dependencies or configurations.
4. **Efficient Use of Resources**: Docker containers can share the same kernel and use fewer resources, making them more efficient than traditional virtual machines.
5. **Fast Deployment**: Docker containers can be spun up quickly, making it ideal for rapid deployment and scaling of applications.
6. **Easy Maintenance**: Docker provides a simple way to manage and update applications, with features like rolling updates and rollbacks.
7. **Security**: Docker provides a secure environment for applications, with features like network isolation and encryption.
8. **Large Ecosystem**: Docker has a large and active ecosystem, with a wide range of tools and plugins available for various tasks.
9. **Version Control**: Docker provides an easy way to manage different versions of an application, with features like version tagging and rollbacks.
10. **Cost-Effective**: Docker can help reduce costs by minimizing the need for virtual machines and reducing the overhead of resource allocation.

**Cons:**

1. **Steep Learning Curve**: Docker has a complex architecture and requires a good understanding of containerization, networking, and storage.
2. **Overhead**: While Docker containers are lightweight, they still require some overhead in terms of resources and management.
3. **Security Risks**: If not properly configured, Docker containers can introduce security risks, such as unauthorized access to the host system.
4. **Limited Support for GUI Applications**: Docker is primarily designed for running command-line applications, and running GUI applications can be challenging.
5. **Networking Complexity**: Docker's networking model can be complex, especially in large-scale deployments.
6. **Storage Complexity**: Docker's storage model can be complex, especially when dealing with persistent data.
7. **Limited Support for Legacy Applications**: Docker is designed for modern, cloud-native applications, and may not be suitable for legacy applications that rely on older technologies.
8. **Dependence on Docker Hub**: Docker relies heavily on Docker Hub, which can be a single point of failure if the hub is down or experiencing issues.
9. **Orchestration Complexity**: Docker provides a built-in orchestration tool, Docker Swarm, but it can be complex to set up and manage.
10. **Vendor Lock-in**: Docker is a proprietary technology, and while it has a large ecosystem, it can be difficult to switch to alternative containerization platforms.

Overall, Docker provides a powerful and flexible way to deploy and manage applications, but it requires careful planning, configuration, and management to ensure optimal performance and security.

Runs of MaziyarPanahi calme-2.4-llama3-70b on huggingface.co

2.9K
Total runs
-2
24-hour runs
-6
3-day runs
77
7-day runs
508
30-day runs

More Information About calme-2.4-llama3-70b huggingface.co Model

More calme-2.4-llama3-70b license Visit here:

https://choosealicense.com/licenses/llama3

calme-2.4-llama3-70b huggingface.co

calme-2.4-llama3-70b huggingface.co is an AI model on huggingface.co that provides calme-2.4-llama3-70b's model effect (), which can be used instantly with this MaziyarPanahi calme-2.4-llama3-70b model. huggingface.co supports a free trial of the calme-2.4-llama3-70b model, and also provides paid use of the calme-2.4-llama3-70b. Support call calme-2.4-llama3-70b model through api, including Node.js, Python, http.

MaziyarPanahi calme-2.4-llama3-70b online free

calme-2.4-llama3-70b huggingface.co is an online trial and call api platform, which integrates calme-2.4-llama3-70b's modeling effects, including api services, and provides a free online trial of calme-2.4-llama3-70b, you can try calme-2.4-llama3-70b online for free by clicking the link below.

MaziyarPanahi calme-2.4-llama3-70b online free url in huggingface.co:

https://huggingface.co/MaziyarPanahi/calme-2.4-llama3-70b

calme-2.4-llama3-70b install

calme-2.4-llama3-70b is an open source model from GitHub that offers a free installation service, and any user can find calme-2.4-llama3-70b on GitHub to install. At the same time, huggingface.co provides the effect of calme-2.4-llama3-70b install, users can directly use calme-2.4-llama3-70b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

calme-2.4-llama3-70b install url in huggingface.co:

https://huggingface.co/MaziyarPanahi/calme-2.4-llama3-70b

Url of calme-2.4-llama3-70b

calme-2.4-llama3-70b huggingface.co Url

Provider of calme-2.4-llama3-70b huggingface.co

MaziyarPanahi
ORGANIZATIONS

Other API from MaziyarPanahi