Downloads · 30 days
31
6% of all-time downloads
nbeerbower_-_Lyra4-Gutenberg2-12B-gguf
RichardErkhov/nbeerbower_-_Lyra4-Gutenberg2-12B-gguf
nbeerbower_-_Lyra4-Gutenberg2-12B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
535
Public
Repo size
138 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf154 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 18, 2024
- Updated
- Oct 18, 2024
- SHA
- 1f0c5c8d
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Lyra4-Gutenberg2-12B - GGUF
- Model creator: https://huggingface.co/nbeerbower/
- Original model: https://huggingface.co/nbeerbower/Lyra4-Gutenberg2-12B/
| Name | Quant method | Size |
|---|---|---|
| Lyra4-Gutenberg2-12B.Q2_K.gguf | Q2_K | 4.46GB |
| Lyra4-Gutenberg2-12B.IQ3_XS.gguf | IQ3_XS | 1.04GB |
| Lyra4-Gutenberg2-12B.IQ3_S.gguf | IQ3_S | 4.46GB |
| Lyra4-Gutenberg2-12B.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| Lyra4-Gutenberg2-12B.IQ3_M.gguf | IQ3_M | 3.0GB |
| Lyra4-Gutenberg2-12B.Q3_K.gguf | Q3_K | 4.36GB |
| Lyra4-Gutenberg2-12B.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| Lyra4-Gutenberg2-12B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Lyra4-Gutenberg2-12B.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| Lyra4-Gutenberg2-12B.Q4_0.gguf | Q4_0 | 6.59GB |
| Lyra4-Gutenberg2-12B.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| Lyra4-Gutenberg2-12B.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| Lyra4-Gutenberg2-12B.Q4_K.gguf | Q4_K | 6.96GB |
| Lyra4-Gutenberg2-12B.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| Lyra4-Gutenberg2-12B.Q4_1.gguf | Q4_1 | 7.26GB |
| Lyra4-Gutenberg2-12B.Q5_0.gguf | Q5_0 | 7.93GB |
| Lyra4-Gutenberg2-12B.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| Lyra4-Gutenberg2-12B.Q5_K.gguf | Q5_K | 8.13GB |
| Lyra4-Gutenberg2-12B.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| Lyra4-Gutenberg2-12B.Q5_1.gguf | Q5_1 | 8.61GB |
| Lyra4-Gutenberg2-12B.Q6_K.gguf | Q6_K | 9.37GB |
| Lyra4-Gutenberg2-12B.Q8_0.gguf | Q8_0 | 12.13GB |
Original model description:
license: cc-by-nc-4.0 library_name: transformers base_model:
- Sao10K/MN-12B-Lyra-v4 datasets:
- jondurbin/gutenberg-dpo-v0.1
- nbeerbower/gutenberg2-dpo model-index:
- name: Lyra4-Gutenberg2-12B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc value: 25.85 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra4-Gutenberg2-12B name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm value: 33.73 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra4-Gutenberg2-12B name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match value: 10.5 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra4-Gutenberg2-12B name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm value: 8.39 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra4-Gutenberg2-12B name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm value: 11.49 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra4-Gutenberg2-12B name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc value: 28.51 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra4-Gutenberg2-12B name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
Lyra4-Gutenberg2-12B
Sao10K/MN-12B-Lyra-v4 finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo.
Features an increased sequence length from Lyra4-Gutenberg-12B.
Method
ORPO Finetuned using 2x RTX 3090 for 3 epochs.
Training data was formatted with ChatML.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.74 |
| IFEval (0-Shot) | 25.85 |
| BBH (3-Shot) | 33.73 |
| MATH Lvl 5 (4-Shot) | 10.50 |
| GPQA (0-shot) | 8.39 |
| MuSR (0-shot) | 11.49 |
| MMLU-PRO (5-shot) | 28.51 |
- Created
- Oct 18, 2024
- Updated
- Oct 18, 2024