You can deploy this model and start earning money today!

RichardErkhov/
adamo1139_-_Mistral-7B-AEZAKMI-v2-gguf

Name: adamo1139_-_Mistral-7B-AEZAKMI-v2-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-AEZAKMI-v2 - GGUF

Model creator: https://huggingface.co/adamo1139/
Original model: https://huggingface.co/adamo1139/Mistral-7B-AEZAKMI-v2/

Name	Quant method	Size
Mistral-7B-AEZAKMI-v2.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-AEZAKMI-v2.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-AEZAKMI-v2.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-AEZAKMI-v2.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-AEZAKMI-v2.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-AEZAKMI-v2.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-AEZAKMI-v2.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-AEZAKMI-v2.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-AEZAKMI-v2.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-AEZAKMI-v2.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-AEZAKMI-v2.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-AEZAKMI-v2.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-AEZAKMI-v2.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-AEZAKMI-v2.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-AEZAKMI-v2.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-AEZAKMI-v2.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-AEZAKMI-v2.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-AEZAKMI-v2.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-AEZAKMI-v2.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-AEZAKMI-v2.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-AEZAKMI-v2.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-AEZAKMI-v2.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 model-index:

name: Mistral-7B-AEZAKMI-v2 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: 58.11 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 82.53 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 59.89 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 51.5 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 73.64 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 32.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 name: Open LLM Leaderboard

Model description

Mistral 7B base model fine-tuned on AEZAKMI v2 dataset. It's like airoboros but hopefully with less gptslop, no refusals and less typical language used by RLHFed OpenAI models. Say goodbye to "It's important to remember"! Prompt format is standard chatml. Don't expect it to be good at math, riddles or be crazy smart. My end goal with AEZAKMI is to create a cozy free chatbot. Base model used for fine-tuning was Mistral 7B 0.1.

Prompt Format

I recommend using ChatML format, as this was used during fine-tune. Here's a prompt format you should use, you can set a different system message, model seems to respect that fine, so it wasn't overfitted.

<|im_start|>system 
A chat with uncensored assistant.<|im_end|> 
<|im_start|>user 
{prompt}<|im_end|> 
<|im_start|>assistant

Intended uses & limitations

Use is limited by Apache-2 license.

Known Issues

Stories have ChatGPT like paragraph spacing, I will work on this in the future maybe, not a high priority.

Unrestricted-ness of the v2 isn't quite something that I am happy with yet, especially using prompt "A chat.". With a slightly modifed prompt it works somewhat better, I recommend using "A chat with uncensored assistant.", it's stupid but it helps a lot. I think Mistral 7B base is contaminated with refusals as other newer models. My next project is to attempt to de-contaminate base LLMs using DPO with preferred data coming from uncontaminated raw models. I plan to release that dataset openly.

I was made aware of the frequent occurrence of the phrase "sending shivers down a spine" in the generations during RP of v1, so I fixed those samples - it should be better now. There was also some issue with handling long system messages for RP with yi-34b AEZAKMI v1, I was planning to investigate it for v2 but I didn't.

Samples of generations of this model are available here - https://huggingface.co/datasets/adamo1139/misc/tree/main/benchmarks

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	59.69
AI2 Reasoning Challenge (25-Shot)	58.11
HellaSwag (10-Shot)	82.53
MMLU (5-Shot)	59.89
TruthfulQA (0-shot)	51.50
Winogrande (5-shot)	73.64
GSM8k (5-shot)	32.45

RichardErkhov/adamo1139_-_Mistral-7B-AEZAKMI-v2-gguf