MaziyarPanahi / calme-2.2-llama3-70b

huggingface.co
Total runs: 5.8K
24-hour runs: 55
7-day runs: 50
30-day runs: 453
Model's Last Updated: July 20 2024
text-generation

Introduction of calme-2.2-llama3-70b

Model Details of calme-2.2-llama3-70b

Llama-3 DPO Logo

MaziyarPanahi/calme-2.2-llama3-70b

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

PS: This fine-tuned model was previously known as MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2 . It was renamed to avoid any confusion with the original model.

⚡ Quantized GGUF

All GGUF models are available here: MaziyarPanahi/calme-2.2-llama3-70b-GGUF

🏆 Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 37.98
IFEval (0-Shot) 82.08
BBH (3-Shot) 48.57
MATH Lvl 5 (4-Shot) 22.96
GPQA (0-shot) 12.19
MuSR (0-shot) 15.30
MMLU-PRO (5-shot) 46.74
Metric Value
Avg. 78.96
AI2 Reasoning Challenge (25-Shot) 72.53
HellaSwag (10-Shot) 86.22
MMLU (5-Shot) 80.41
TruthfulQA (0-shot) 63.57
Winogrande (5-shot) 82.79
GSM8k (5-shot) 88.25

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-2.2-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-2.2-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):])

Runs of MaziyarPanahi calme-2.2-llama3-70b on huggingface.co

5.8K
Total runs
55
24-hour runs
58
3-day runs
50
7-day runs
453
30-day runs

More Information About calme-2.2-llama3-70b huggingface.co Model

More calme-2.2-llama3-70b license Visit here:

https://choosealicense.com/licenses/llama3

calme-2.2-llama3-70b huggingface.co

calme-2.2-llama3-70b huggingface.co is an AI model on huggingface.co that provides calme-2.2-llama3-70b's model effect (), which can be used instantly with this MaziyarPanahi calme-2.2-llama3-70b model. huggingface.co supports a free trial of the calme-2.2-llama3-70b model, and also provides paid use of the calme-2.2-llama3-70b. Support call calme-2.2-llama3-70b model through api, including Node.js, Python, http.

MaziyarPanahi calme-2.2-llama3-70b online free

calme-2.2-llama3-70b huggingface.co is an online trial and call api platform, which integrates calme-2.2-llama3-70b's modeling effects, including api services, and provides a free online trial of calme-2.2-llama3-70b, you can try calme-2.2-llama3-70b online for free by clicking the link below.

MaziyarPanahi calme-2.2-llama3-70b online free url in huggingface.co:

https://huggingface.co/MaziyarPanahi/calme-2.2-llama3-70b

calme-2.2-llama3-70b install

calme-2.2-llama3-70b is an open source model from GitHub that offers a free installation service, and any user can find calme-2.2-llama3-70b on GitHub to install. At the same time, huggingface.co provides the effect of calme-2.2-llama3-70b install, users can directly use calme-2.2-llama3-70b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

calme-2.2-llama3-70b install url in huggingface.co:

https://huggingface.co/MaziyarPanahi/calme-2.2-llama3-70b

Url of calme-2.2-llama3-70b

calme-2.2-llama3-70b huggingface.co Url

Provider of calme-2.2-llama3-70b huggingface.co

MaziyarPanahi
ORGANIZATIONS

Other API from MaziyarPanahi