Quantization made by Richard Erkhov.

Github

Discord

Request more models

Halu-8B-Llama3-Blackroot - GGUF

• Model creator: https://huggingface.co/Hastagaras/
• Original model: https://huggingface.co/Hastagaras/Halu-8B-Llama3-Blackroot/

Name	Quant method	Size
Halu-8B-Llama3-Blackroot.Q2K.gguf	Q2K	2.96GB
Halu-8B-Llama3-Blackroot.IQ3XS.gguf	IQ3XS	3.28GB
Halu-8B-Llama3-Blackroot.IQ3S.gguf	IQ3S	3.43GB
Halu-8B-Llama3-Blackroot.Q3KS.gguf	Q3K_S	3.41GB
Halu-8B-Llama3-Blackroot.IQ3M.gguf	IQ3M	3.52GB
Halu-8B-Llama3-Blackroot.Q3K.gguf	Q3K	3.74GB
Halu-8B-Llama3-Blackroot.Q3KM.gguf	Q3K_M	3.74GB
Halu-8B-Llama3-Blackroot.Q3KL.gguf	Q3K_L	4.03GB
Halu-8B-Llama3-Blackroot.IQ4XS.gguf	IQ4XS	4.18GB
Halu-8B-Llama3-Blackroot.Q40.gguf	Q40	4.34GB
Halu-8B-Llama3-Blackroot.IQ4NL.gguf	IQ4NL	4.38GB
Halu-8B-Llama3-Blackroot.Q4KS.gguf	Q4K_S	4.37GB
Halu-8B-Llama3-Blackroot.Q4K.gguf	Q4K	4.58GB
Halu-8B-Llama3-Blackroot.Q4KM.gguf	Q4K_M	4.58GB
Halu-8B-Llama3-Blackroot.Q41.gguf	Q41	4.78GB
Halu-8B-Llama3-Blackroot.Q50.gguf	Q50	5.21GB
Halu-8B-Llama3-Blackroot.Q5KS.gguf	Q5K_S	5.21GB
Halu-8B-Llama3-Blackroot.Q5K.gguf	Q5K	5.34GB
Halu-8B-Llama3-Blackroot.Q5KM.gguf	Q5K_M	5.34GB
Halu-8B-Llama3-Blackroot.Q51.gguf	Q51	5.65GB
Halu-8B-Llama3-Blackroot.Q6K.gguf	Q6K	6.14GB
Halu-8B-Llama3-Blackroot.Q80.gguf	Q80	7.95GB

Original model description:

---

license: llama3
library_name: transformers
tags:

• mergekit
• merge
• not-for-all-audiences

base_model:

• Hastagaras/Halu-8B-Llama3-v0.3
• Blackroot/Llama-3-LongStory-LORA
• Hastagaras/Halu-8B-Llama3-v0.3
• Blackroot/Llama-3-8B-Abomination-LORA
• Hastagaras/Halu-8B-Llama3-v0.3

model-index:

• name: Halu-8B-Llama3-Blackroot

results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
numfewshot: 25
metrics:
- type: acc_norm
value: 63.82
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
numfewshot: 10
metrics:
- type: acc_norm
value: 84.55
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
numfewshot: 5
metrics:
- type: acc
value: 67.04
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
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:
numfewshot: 0
metrics:
- type: mc2
value: 53.28
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
numfewshot: 5
metrics:
- type: acc
value: 79.48
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
numfewshot: 5
metrics:
- type: acc
value: 70.51
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
name: Open LLM Leaderboard

---

EXPERIMENTAL MODEL

VERY IMPORTANT: This model has not been extensively tested or evaluated, and its performance characteristics are currently unknown. It may generate harmful, biased, or inappropriate content. Please exercise caution and use it at your own risk and discretion.

I just tried saishf's merged model, and it's great. So I decided to try a similar merge method with Blackroot's LoRA that I had found earlier.

I don't know what to say about this model... this model is very strange...Maybe because Blackroot's amazing Loras used human data and not synthetic data, hence the model turned out to be very human-like...even the actions or narrations.

WARNING: This model is very unsafe in certain parts...especially in RP.

IMATRIX GGUF IS HERE made available by Lewdiculous

STATIC GGUF IS HERE made avaible by mradermacher

Merge Method

This model was merged using the Model Stock merge method using Hastagaras/Halu-8B-Llama3-v0.3 as a base.

Models Merged

The following models were included in the merge:

• Hastagaras/Halu-8B-Llama3-v0.3 + Blackroot/Llama-3-LongStory-LORA
• Hastagaras/Halu-8B-Llama3-v0.3 + Blackroot/Llama-3-8B-Abomination-LORA

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Hastagaras/Halu-8B-Llama3-v0.3+Blackroot/Llama-3-LongStory-LORA
  - model: Hastagaras/Halu-8B-Llama3-v0.3+Blackroot/Llama-3-8B-Abomination-LORA
mergemethod: modelstock
base_model: Hastagaras/Halu-8B-Llama3-v0.3
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.78
AI2 Reasoning Challenge (25-Shot)	63.82
HellaSwag (10-Shot)	84.55
MMLU (5-Shot)	67.04
TruthfulQA (0-shot)	53.28
Winogrande (5-shot)	79.48
GSM8k (5-shot)	70.51