You can deploy this model and start earning money today!

RichardErkhov/
kyujinpy_-_PlatYi-34B-Q-gguf

Name: kyujinpy_-_PlatYi-34B-Q-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

PlatYi-34B-Q - GGUF

Model creator: https://huggingface.co/kyujinpy/
Original model: https://huggingface.co/kyujinpy/PlatYi-34B-Q/

Name	Quant method	Size
PlatYi-34B-Q.Q2_K.gguf	Q2_K	11.94GB
PlatYi-34B-Q.IQ3_XS.gguf	IQ3_XS	1.35GB
PlatYi-34B-Q.IQ3_S.gguf	IQ3_S	13.99GB
PlatYi-34B-Q.Q3_K_S.gguf	Q3_K_S	13.93GB
PlatYi-34B-Q.IQ3_M.gguf	IQ3_M	14.5GB
PlatYi-34B-Q.Q3_K.gguf	Q3_K	15.51GB
PlatYi-34B-Q.Q3_K_M.gguf	Q3_K_M	15.51GB
PlatYi-34B-Q.Q3_K_L.gguf	Q3_K_L	16.89GB
PlatYi-34B-Q.IQ4_XS.gguf	IQ4_XS	17.36GB
PlatYi-34B-Q.Q4_0.gguf	Q4_0	18.13GB
PlatYi-34B-Q.IQ4_NL.gguf	IQ4_NL	13.52GB
PlatYi-34B-Q.Q4_K_S.gguf	Q4_K_S	18.25GB
PlatYi-34B-Q.Q4_K.gguf	Q4_K	8.94GB
PlatYi-34B-Q.Q4_K_M.gguf	Q4_K_M	19.24GB
PlatYi-34B-Q.Q4_1.gguf	Q4_1	20.1GB
PlatYi-34B-Q.Q5_0.gguf	Q5_0	22.08GB
PlatYi-34B-Q.Q5_K_S.gguf	Q5_K_S	22.08GB
PlatYi-34B-Q.Q5_K.gguf	Q5_K	22.65GB
PlatYi-34B-Q.Q5_K_M.gguf	Q5_K_M	22.65GB
PlatYi-34B-Q.Q5_1.gguf	Q5_1	24.05GB
PlatYi-34B-Q.Q6_K.gguf	Q6_K	26.28GB
PlatYi-34B-Q.Q8_0.gguf	Q8_0	34.03GB

Original model description:

language:

en license: cc-by-nc-sa-4.0 library_name: transformers datasets:
garage-bAInd/Open-Platypus pipeline_tag: text-generation model-index:
name: PlatYi-34B-Q 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: 66.89 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Q 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: 85.14 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Q 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: 77.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Q 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: 53.03 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Q 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: 82.48 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Q 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: 53.98 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Q name: Open LLM Leaderboard

PlatYi-34B-QLoRA

Model Details

Model Developers Kyujin Han (kyujinpy)

Input Models input text only.

Output Models generate text only.

Model Architecture
PlatYi-34B-QLoRA is an auto-regressive language model based on the Yi-34B transformer architecture.

Blog Link
Blog: [Coming soon...]
Github: [Coming soon...]

Base Model
01-ai/Yi-34B

Training Dataset
garage-bAInd/Open-Platypus.

Notice
While training, I used QLoRA.
But, lora_r values is 16.
So, this model just testing.

Model Benchmark

Open leaderboard

Follow up as link.

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
PlatYi-34B-Q	69.86	66.89	85.14	77.66	53.03	82.48	53.98
01-ai/Yi-34B	69.42	64.59	85.69	76.35	56.23	83.03	50.64

Implementation Code

python

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "kyujinpy/PlatYi-34B-Q"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.86
AI2 Reasoning Challenge (25-Shot)	66.89
HellaSwag (10-Shot)	85.14
MMLU (5-Shot)	77.66
TruthfulQA (0-shot)	53.03
Winogrande (5-shot)	82.48
GSM8k (5-shot)	53.98

RichardErkhov/kyujinpy_-_PlatYi-34B-Q-gguf