Mistral-CatMacaroni-slerp-uncensored-7B

Description

This repo contains GGUF format model files for Mistral-CatMacaroni-slerp-uncensored-7B.

Files Provided

Name Quant Bits File Size Remark
mistral-catmacaroni-slerp-uncensored-7b.IQ3_XXS.gguf IQ3_XXS 3 3.02 GB 3.06 bpw quantization
mistral-catmacaroni-slerp-uncensored-7b.IQ3_S.gguf IQ3_S 3 3.18 GB 3.44 bpw quantization
mistral-catmacaroni-slerp-uncensored-7b.IQ3_M.gguf IQ3_M 3 3.28 GB 3.66 bpw quantization mix
mistral-catmacaroni-slerp-uncensored-7b.Q4_0.gguf Q4_0 4 4.11 GB 3.56G, +0.2166 ppl
mistral-catmacaroni-slerp-uncensored-7b.IQ4_NL.gguf IQ4_NL 4 4.16 GB 4.25 bpw non-linear quantization
mistral-catmacaroni-slerp-uncensored-7b.Q4_K_M.gguf Q4_K_M 4 4.37 GB 3.80G, +0.0532 ppl
mistral-catmacaroni-slerp-uncensored-7b.Q5_K_M.gguf Q5_K_M 5 5.13 GB 4.45G, +0.0122 ppl
mistral-catmacaroni-slerp-uncensored-7b.Q6_K.gguf Q6_K 6 5.94 GB 5.15G, +0.0008 ppl
mistral-catmacaroni-slerp-uncensored-7b.Q8_0.gguf Q8_0 8 7.70 GB 6.70G, +0.0004 ppl

Parameters

path type architecture rope_theta sliding_win max_pos_embed
diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B mistral MistralForCausalLM 1000000.0 null 32768

Benchmarks

Original Model Card

This is an experimental model.

Finetuned on dataset toxic-dpo-v0.1-NoWarning-alpaca using model Mistral-CatMacaroni-slerp-7B

Metric Value
Avg. 67.28
ARC (25-shot) 64.25
HellaSwag (10-shot) 84.09
MMLU (5-shot) 62.66
TruthfulQA (0-shot) 56.87
Winogrande (5-shot) 79.72
GSM8K (5-shot) 56.1
Downloads last month
483
GGUF
Model size
7.24B params
Architecture
llama

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Collection including koesn/Mistral-CatMacaroni-slerp-uncensored-7B-GGUF