初始化项目，由ModelHub XC社区提供模型
Model: Dampfinchen/Llama-3.1-8B-Ultra-Instruct Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
167
README.md
Normal file
167
README.md
Normal file
@@ -0,0 +1,167 @@
|
||||
---
|
||||
license: llama3
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
base_model:
|
||||
- nbeerbower/llama3.1-gutenberg-8B
|
||||
- akjindal53244/Llama-3.1-Storm-8B
|
||||
- NousResearch/Meta-Llama-3.1-8B
|
||||
- nbeerbower/llama3.1-airoboros3.2-QDT-8B
|
||||
- Sao10K/Llama-3.1-8B-Stheno-v3.4
|
||||
model-index:
|
||||
- name: Llama-3.1-8B-Ultra-Instruct
|
||||
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: 80.81
|
||||
name: strict accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
|
||||
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: 32.49
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
|
||||
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: 14.95
|
||||
name: exact match
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
|
||||
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: 5.59
|
||||
name: acc_norm
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
|
||||
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: 8.61
|
||||
name: acc_norm
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
|
||||
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: 31.4
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
# merge
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
## Merge Details
|
||||
### Merge Method
|
||||
|
||||
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Meta-Llama-3.1-8B](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B) as a base.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [nbeerbower/llama3.1-gutenberg-8B](https://huggingface.co/nbeerbower/llama3.1-gutenberg-8B)
|
||||
* [akjindal53244/Llama-3.1-Storm-8B](https://huggingface.co/akjindal53244/Llama-3.1-Storm-8B)
|
||||
* [nbeerbower/llama3.1-airoboros3.2-QDT-8B](https://huggingface.co/nbeerbower/llama3.1-airoboros3.2-QDT-8B)
|
||||
* [Sao10K/Llama-3.1-8B-Stheno-v3.4](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
models:
|
||||
- model: Sao10K/Llama-3.1-8B-Stheno-v3.4
|
||||
parameters:
|
||||
weight: 0.2
|
||||
density: 0.5
|
||||
- model: akjindal53244/Llama-3.1-Storm-8B
|
||||
parameters:
|
||||
weight: 0.5
|
||||
density: 0.5
|
||||
- model: nbeerbower/llama3.1-gutenberg-8B
|
||||
parameters:
|
||||
weight: 0.3
|
||||
density: 0.5
|
||||
- model: nbeerbower/llama3.1-airoboros3.2-QDT-8B
|
||||
parameters:
|
||||
weight: 0.2
|
||||
density: 0.5
|
||||
merge_method: dare_ties
|
||||
base_model: NousResearch/Meta-Llama-3.1-8B
|
||||
dtype: bfloat16
|
||||
name: Llama-3.1-8B-Ultra-Instruct
|
||||
```
|
||||
|
||||
Use Llama 3 Instruct prompt template. Use with caution, I'm not responsible for what you do with it. All credits and thanks go to the creators of the fine tunes I've merged. In my own tests and on HF Eval it performs very well for a 8B model and I can recommend it. High quality quants by Bartowski: https://huggingface.co/bartowski/Llama-3.1-8B-Ultra-Instruct-GGUF
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Dampfinchen__Llama-3.1-8B-Ultra-Instruct)
|
||||
|
||||
| Metric |Value|
|
||||
|-------------------|----:|
|
||||
|Avg. |28.98|
|
||||
|IFEval (0-Shot) |80.81|
|
||||
|BBH (3-Shot) |32.49|
|
||||
|MATH Lvl 5 (4-Shot)|14.95|
|
||||
|GPQA (0-shot) | 5.59|
|
||||
|MuSR (0-shot) | 8.61|
|
||||
|MMLU-PRO (5-shot) |31.40|
|
||||
|
||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.42.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.42.3"
|
||||
}
|
||||
21
mergekit_config.yml
Normal file
21
mergekit_config.yml
Normal file
@@ -0,0 +1,21 @@
|
||||
models:
|
||||
- model: Sao10K/Llama-3.1-8B-Stheno-v3.4
|
||||
parameters:
|
||||
weight: 0.2
|
||||
density: 0.5
|
||||
- model: akjindal53244/Llama-3.1-Storm-8B
|
||||
parameters:
|
||||
weight: 0.5
|
||||
density: 0.5
|
||||
- model: nbeerbower/llama3.1-gutenberg-8B
|
||||
parameters:
|
||||
weight: 0.3
|
||||
density: 0.5
|
||||
- model: nbeerbower/llama3.1-airoboros3.2-QDT-8B
|
||||
parameters:
|
||||
weight: 0.2
|
||||
density: 0.5
|
||||
merge_method: dare_ties
|
||||
base_model: NousResearch/Meta-Llama-3.1-8B
|
||||
dtype: bfloat16
|
||||
name: Llama-3.1-8B-Ultra-Instruct
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7fedd9bb5c4fd8624f7e8f3c7b751864f98399c54e25d2ade5bd1108728444ea
|
||||
size 4953586384
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78429beb9e407ff1fba9a2f9c71ced1b788d8f90cd7ab38def5de7da5fde5ee2
|
||||
size 4999819336
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2627395f2bdd92b4f5ea1ecf466c942b31a5bc10567a94dfade1e9d09365022f
|
||||
size 4915916144
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:384a22db6ef7f3306d1da78659a23e970df6d68e99210a0281fae0d1969a1a60
|
||||
size 1191234472
|
||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
410563
tokenizer.json
Normal file
410563
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2062
tokenizer_config.json
Normal file
2062
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user