Upload 9 files
Browse files- README.md +126 -0
- config.json +36 -0
- generation_config.json +6 -0
- huggingface-metadata.txt +9 -0
- model.safetensors +3 -0
- quantization_config.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
base_model:
|
| 5 |
+
- Sao10K/MN-12B-Lyra-v1
|
| 6 |
+
datasets:
|
| 7 |
+
- jondurbin/gutenberg-dpo-v0.1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Lyra-Gutenberg-mistral-nemo-12B
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
type: text-generation
|
| 13 |
+
name: Text Generation
|
| 14 |
+
dataset:
|
| 15 |
+
name: IFEval (0-Shot)
|
| 16 |
+
type: HuggingFaceH4/ifeval
|
| 17 |
+
args:
|
| 18 |
+
num_few_shot: 0
|
| 19 |
+
metrics:
|
| 20 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
| 21 |
+
value: 34.95
|
| 22 |
+
name: strict accuracy
|
| 23 |
+
source:
|
| 24 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
|
| 25 |
+
name: Open LLM Leaderboard
|
| 26 |
+
- task:
|
| 27 |
+
type: text-generation
|
| 28 |
+
name: Text Generation
|
| 29 |
+
dataset:
|
| 30 |
+
name: BBH (3-Shot)
|
| 31 |
+
type: BBH
|
| 32 |
+
args:
|
| 33 |
+
num_few_shot: 3
|
| 34 |
+
metrics:
|
| 35 |
+
- type: acc_norm
|
| 36 |
+
value: 36.99
|
| 37 |
+
name: normalized accuracy
|
| 38 |
+
source:
|
| 39 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
|
| 40 |
+
name: Open LLM Leaderboard
|
| 41 |
+
- task:
|
| 42 |
+
type: text-generation
|
| 43 |
+
name: Text Generation
|
| 44 |
+
dataset:
|
| 45 |
+
name: MATH Lvl 5 (4-Shot)
|
| 46 |
+
type: hendrycks/competition_math
|
| 47 |
+
args:
|
| 48 |
+
num_few_shot: 4
|
| 49 |
+
metrics:
|
| 50 |
+
- type: exact_match
|
| 51 |
+
value: 8.31
|
| 52 |
+
name: exact match
|
| 53 |
+
source:
|
| 54 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
|
| 55 |
+
name: Open LLM Leaderboard
|
| 56 |
+
- task:
|
| 57 |
+
type: text-generation
|
| 58 |
+
name: Text Generation
|
| 59 |
+
dataset:
|
| 60 |
+
name: GPQA (0-shot)
|
| 61 |
+
type: Idavidrein/gpqa
|
| 62 |
+
args:
|
| 63 |
+
num_few_shot: 0
|
| 64 |
+
metrics:
|
| 65 |
+
- type: acc_norm
|
| 66 |
+
value: 11.19
|
| 67 |
+
name: acc_norm
|
| 68 |
+
source:
|
| 69 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
|
| 70 |
+
name: Open LLM Leaderboard
|
| 71 |
+
- task:
|
| 72 |
+
type: text-generation
|
| 73 |
+
name: Text Generation
|
| 74 |
+
dataset:
|
| 75 |
+
name: MuSR (0-shot)
|
| 76 |
+
type: TAUR-Lab/MuSR
|
| 77 |
+
args:
|
| 78 |
+
num_few_shot: 0
|
| 79 |
+
metrics:
|
| 80 |
+
- type: acc_norm
|
| 81 |
+
value: 14.76
|
| 82 |
+
name: acc_norm
|
| 83 |
+
source:
|
| 84 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
|
| 85 |
+
name: Open LLM Leaderboard
|
| 86 |
+
- task:
|
| 87 |
+
type: text-generation
|
| 88 |
+
name: Text Generation
|
| 89 |
+
dataset:
|
| 90 |
+
name: MMLU-PRO (5-shot)
|
| 91 |
+
type: TIGER-Lab/MMLU-Pro
|
| 92 |
+
config: main
|
| 93 |
+
split: test
|
| 94 |
+
args:
|
| 95 |
+
num_few_shot: 5
|
| 96 |
+
metrics:
|
| 97 |
+
- type: acc
|
| 98 |
+
value: 29.2
|
| 99 |
+
name: accuracy
|
| 100 |
+
source:
|
| 101 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
|
| 102 |
+
name: Open LLM Leaderboard
|
| 103 |
+
---
|
| 104 |
+
|
| 105 |
+
# Lyra-Gutenberg-12B
|
| 106 |
+
|
| 107 |
+
[Sao10K/MN-12B-Lyra-v1](https://huggingface.co/Sao10K/MN-12B-Lyra-v1) finetuned on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1).
|
| 108 |
+
|
| 109 |
+
### Method
|
| 110 |
+
|
| 111 |
+
Finetuned using an A100 on Google Colab for 3 epochs.
|
| 112 |
+
|
| 113 |
+
[Fine-tune Llama 3 with ORPO](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html)
|
| 114 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
| 115 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nbeerbower__Lyra-Gutenberg-mistral-nemo-12B)
|
| 116 |
+
|
| 117 |
+
| Metric |Value|
|
| 118 |
+
|-------------------|----:|
|
| 119 |
+
|Avg. |22.57|
|
| 120 |
+
|IFEval (0-Shot) |34.95|
|
| 121 |
+
|BBH (3-Shot) |36.99|
|
| 122 |
+
|MATH Lvl 5 (4-Shot)| 8.31|
|
| 123 |
+
|GPQA (0-shot) |11.19|
|
| 124 |
+
|MuSR (0-shot) |14.76|
|
| 125 |
+
|MMLU-PRO (5-shot) |29.20|
|
| 126 |
+
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Sao10K/MN-12B-Lyra-v1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 1024000,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 40,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": null,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.44.2",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 131072,
|
| 27 |
+
"quantization_config": {
|
| 28 |
+
"quant_method": "exl3",
|
| 29 |
+
"version": "0.0.1",
|
| 30 |
+
"bits": 4.0,
|
| 31 |
+
"calibration": {
|
| 32 |
+
"rows": 100,
|
| 33 |
+
"cols": 2048
|
| 34 |
+
}
|
| 35 |
+
}
|
| 36 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.44.2"
|
| 6 |
+
}
|
huggingface-metadata.txt
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
url: https://huggingface.co/nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
|
| 2 |
+
branch: main
|
| 3 |
+
download date: 2025-04-10 17:23:31
|
| 4 |
+
sha256sum:
|
| 5 |
+
1d68d6a81aa65d8d4f7e4fa5fa0e4a8b6872bfeded80a40a54573a4b1f2d4f9b model-00001-of-00005.safetensors
|
| 6 |
+
8adf98d6eb3294de4b926b0fea150326ddfb043cce264814cdaeeada82d7aefe model-00002-of-00005.safetensors
|
| 7 |
+
932b0c7b5babd9a33f08f65af46e77a0e1d663ae63cacd0e4638e86c083c0d0a model-00003-of-00005.safetensors
|
| 8 |
+
417ebae31dc99c6557c2a04e60fe79107efe30fd2a5c86f73280e606bbf86b38 model-00004-of-00005.safetensors
|
| 9 |
+
93832dac9af7ea0cae80423a630fc5452a6b05b3e5e41ef361cd5e8e6bde4dc7 model-00005-of-00005.safetensors
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15e58ebf17034289b9212dbc304d5ea3dda3f828a0d8aea3123dd927bff41d15
|
| 3 |
+
size 7306420360
|
quantization_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|