You can deploy this model and start earning money today!

RichardErkhov/
ajibawa-2023_-_OpenHermes-2.5-Code-290k-13B-gguf

Name: ajibawa-2023_-_OpenHermes-2.5-Code-290k-13B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

OpenHermes-2.5-Code-290k-13B - GGUF

Model creator: https://huggingface.co/ajibawa-2023/
Original model: https://huggingface.co/ajibawa-2023/OpenHermes-2.5-Code-290k-13B/

Name	Quant method	Size
OpenHermes-2.5-Code-290k-13B.Q2_K.gguf	Q2_K	4.52GB
OpenHermes-2.5-Code-290k-13B.IQ3_XS.gguf	IQ3_XS	4.99GB
OpenHermes-2.5-Code-290k-13B.IQ3_S.gguf	IQ3_S	5.27GB
OpenHermes-2.5-Code-290k-13B.Q3_K_S.gguf	Q3_K_S	5.27GB
OpenHermes-2.5-Code-290k-13B.IQ3_M.gguf	IQ3_M	5.57GB
OpenHermes-2.5-Code-290k-13B.Q3_K.gguf	Q3_K	5.9GB
OpenHermes-2.5-Code-290k-13B.Q3_K_M.gguf	Q3_K_M	5.9GB
OpenHermes-2.5-Code-290k-13B.Q3_K_L.gguf	Q3_K_L	6.45GB
OpenHermes-2.5-Code-290k-13B.IQ4_XS.gguf	IQ4_XS	6.54GB
OpenHermes-2.5-Code-290k-13B.Q4_0.gguf	Q4_0	6.86GB
OpenHermes-2.5-Code-290k-13B.IQ4_NL.gguf	IQ4_NL	6.9GB
OpenHermes-2.5-Code-290k-13B.Q4_K_S.gguf	Q4_K_S	6.91GB
OpenHermes-2.5-Code-290k-13B.Q4_K.gguf	Q4_K	7.33GB
OpenHermes-2.5-Code-290k-13B.Q4_K_M.gguf	Q4_K_M	7.33GB
OpenHermes-2.5-Code-290k-13B.Q4_1.gguf	Q4_1	7.61GB
OpenHermes-2.5-Code-290k-13B.Q5_0.gguf	Q5_0	8.36GB
OpenHermes-2.5-Code-290k-13B.Q5_K_S.gguf	Q5_K_S	8.36GB
OpenHermes-2.5-Code-290k-13B.Q5_K.gguf	Q5_K	8.6GB
OpenHermes-2.5-Code-290k-13B.Q5_K_M.gguf	Q5_K_M	8.6GB
OpenHermes-2.5-Code-290k-13B.Q5_1.gguf	Q5_1	9.1GB
OpenHermes-2.5-Code-290k-13B.Q6_K.gguf	Q6_K	9.95GB
OpenHermes-2.5-Code-290k-13B.Q8_0.gguf	Q8_0	12.88GB

Original model description:

language:

en license: apache-2.0 tags:
code
finetune
synthetic data
text-generation-inference
conversational datasets:
ajibawa-2023/OpenHermes-2.5-Code-290k
teknium/OpenHermes-2.5 model-index:
name: OpenHermes-2.5-Code-290k-13B 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: 57.34 name: normalized accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/OpenHermes-2.5-Code-290k-13B 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: 80.48 name: normalized accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/OpenHermes-2.5-Code-290k-13B 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: 56.53 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/OpenHermes-2.5-Code-290k-13B 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: 52.5 source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/OpenHermes-2.5-Code-290k-13B 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: 74.82 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/OpenHermes-2.5-Code-290k-13B 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: 58.3 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/OpenHermes-2.5-Code-290k-13B name: Open LLM Leaderboard

OpenHermes-2.5-Code-290k-13B

OpenHermes-2.5-Code-290k-13B is a state of the art Llama-2 Fine-tune, which is trained on additional code dataset. This Model is much better than teknium's model. You can check the Eval results below. This model is trained on my existing dataset OpenHermes-2.5-Code-290k. This dataset is amalgamation of two datasets. I have used OpenHermes-2.5 a super quality dataset made avaliable by teknium. Other datset is my own Code-290k-ShareGPT. Dataset is in Vicuna/ShareGPT format. There are around 1.29 million set of conversations. I have cleaned the dataset provided by Teknium and removed metadata such as "source" & "category" etc. This dataset has primarily synthetically generated instruction and chat samples.

This model has enhanced coding capabilities besides other capabilities such as Blogging, story generation, Q&A and many more.

Training:

Entire model was trained on 4 x A100 80GB. For 2 epoch, training took 21 Days. Fschat & DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.

This is a full fine tuned model. Links for quantized models will be updated soon.

GPTQ, GGUF, AWQ & Exllama

GPTQ: TBA

GGUF: Link

AWQ: TBA

Exllama v2: Link

Special Thanks to LoneStriker and bartowski for quantising.

Example Prompt:

This is a conversation with your helpful AI assistant. AI assistant can generate Code in various Programming Languages along with necessary explanation. It can generate Story, Blogs .....

Context
You are a helpful AI assistant.

USER: <prompt>
ASSISTANT:

You can modify above Prompt as per your requirement. I have used ShareGPT/Vicuna format v1.1 .

I want to say special Thanks to the Open Source community for helping & guiding me to better understand the AI/Model development.

Thank you for your love & support.

Example Output

I will update soon.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	63.33
AI2 Reasoning Challenge (25-Shot)	57.34
HellaSwag (10-Shot)	80.48
MMLU (5-Shot)	56.53
TruthfulQA (0-shot)	52.50
Winogrande (5-shot)	74.82
GSM8k (5-shot)	58.30

RichardErkhov/ajibawa-2023_-_OpenHermes-2.5-Code-290k-13B-gguf

Original model description:

Open LLM Leaderboard Evaluation Results

RichardErkhov/
ajibawa-2023_-_OpenHermes-2.5-Code-290k-13B-gguf