You can deploy this model and start earning money today!

RichardErkhov/
MaziyarPanahi_-_calme-2.2-phi3-4b-gguf

Name: MaziyarPanahi_-_calme-2.2-phi3-4b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

calme-2.2-phi3-4b - GGUF

Model creator: https://huggingface.co/MaziyarPanahi/
Original model: https://huggingface.co/MaziyarPanahi/calme-2.2-phi3-4b/

Name	Quant method	Size
calme-2.2-phi3-4b.Q2_K.gguf	Q2_K	1.32GB
calme-2.2-phi3-4b.IQ3_XS.gguf	IQ3_XS	1.51GB
calme-2.2-phi3-4b.IQ3_S.gguf	IQ3_S	1.57GB
calme-2.2-phi3-4b.Q3_K_S.gguf	Q3_K_S	1.57GB
calme-2.2-phi3-4b.IQ3_M.gguf	IQ3_M	1.73GB
calme-2.2-phi3-4b.Q3_K.gguf	Q3_K	1.82GB
calme-2.2-phi3-4b.Q3_K_M.gguf	Q3_K_M	1.82GB
calme-2.2-phi3-4b.Q3_K_L.gguf	Q3_K_L	1.94GB
calme-2.2-phi3-4b.IQ4_XS.gguf	IQ4_XS	1.93GB
calme-2.2-phi3-4b.Q4_0.gguf	Q4_0	2.03GB
calme-2.2-phi3-4b.IQ4_NL.gguf	IQ4_NL	2.04GB
calme-2.2-phi3-4b.Q4_K_S.gguf	Q4_K_S	2.04GB
calme-2.2-phi3-4b.Q4_K.gguf	Q4_K	2.23GB
calme-2.2-phi3-4b.Q4_K_M.gguf	Q4_K_M	2.23GB
calme-2.2-phi3-4b.Q4_1.gguf	Q4_1	2.24GB
calme-2.2-phi3-4b.Q5_0.gguf	Q5_0	2.46GB
calme-2.2-phi3-4b.Q5_K_S.gguf	Q5_K_S	2.46GB
calme-2.2-phi3-4b.Q5_K.gguf	Q5_K	2.62GB
calme-2.2-phi3-4b.Q5_K_M.gguf	Q5_K_M	2.62GB
calme-2.2-phi3-4b.Q5_1.gguf	Q5_1	2.68GB
calme-2.2-phi3-4b.Q6_K.gguf	Q6_K	2.92GB
calme-2.2-phi3-4b.Q8_0.gguf	Q8_0	3.78GB

Original model description:

language:

en license: mit library_name: transformers tags:
axolotl
finetune
dpo
microsoft
phi
pytorch
phi-3
nlp
code
chatml base_model: microsoft/Phi-3-mini-4k-instruct pipeline_tag: text-generation inference: false model_creator: MaziyarPanahi quantized_by: MaziyarPanahi model-index:
name: calme-2.2-phi3-4b results:
- task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
  - type: acc_norm value: 62.8 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
  - type: acc_norm value: 80.76 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
  - type: acc value: 69.1 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
  - type: mc2 value: 59.97 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
  - type: acc value: 72.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 73.62 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics:
  - type: inst_level_strict_acc and prompt_level_strict_acc value: 50.69 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics:
  - type: acc_norm value: 37.73 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics:
  - type: exact_match value: 2.34 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics:
  - type: acc_norm value: 9.51 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics:
  - type: acc_norm value: 7.7 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 31.27 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-phi3-4b name: Open LLM Leaderboard

Phi-3 Logo

MaziyarPanahi/calme-2.2-phi3-4b

This model is a fine-tune (DPO) of microsoft/Phi-3-mini-4k-instruct model.

⚡ Quantized GGUF

All GGUF models are available here: MaziyarPanahi/calme-2.2-phi3-4b-GGUF

🏆 Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	23.21
IFEval (0-Shot)	50.69
BBH (3-Shot)	37.73
MATH Lvl 5 (4-Shot)	2.34
GPQA (0-shot)	9.51
MuSR (0-shot)	7.70
MMLU-PRO (5-shot)	31.27

Metric	Value
Avg.	69.78
AI2 Reasoning Challenge (25-Shot)	62.80
HellaSwag (10-Shot)	80.76
MMLU (5-Shot)	69.10
TruthfulQA (0-shot)	59.97
Winogrande (5-shot)	72.45
GSM8k (5-shot)	73.62

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-phi3-4b as the model name in Hugging Face's transformers library.

python

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

model_id = "MaziyarPanahi/calme-2.2-phi3-4b"

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)

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

# this should work perfectly for the model to stop generating
terminators = [
    tokenizer.eos_token_id, # this should be <|im_end|>
    tokenizer.convert_tokens_to_ids("<|assistant|>"), # sometimes model stops generating at <|assistant|>
    tokenizer.convert_tokens_to_ids("<|end|>") # sometimes model stops generating at <|end|>
]

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)

generation_args = {
    "max_new_tokens": 500,
    "return_full_text": False,
    "temperature": 0.0,
    "do_sample": False,
    "streamer": streamer,
    "eos_token_id": terminators,
}

output = pipe(messages, **generation_args)
print(output[0]['generated_text'])

RichardErkhov/MaziyarPanahi_-_calme-2.2-phi3-4b-gguf