初始化项目，由ModelHub XC社区提供模型
Model: mlabonne/ChimeraLlama-3-8B-v3 Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
200
README.md
Normal file
200
README.md
Normal file
@@ -0,0 +1,200 @@
|
||||
---
|
||||
license: other
|
||||
tags:
|
||||
- merge
|
||||
- mergekit
|
||||
- lazymergekit
|
||||
base_model:
|
||||
- NousResearch/Meta-Llama-3-8B-Instruct
|
||||
- mlabonne/OrpoLlama-3-8B
|
||||
- cognitivecomputations/dolphin-2.9-llama3-8b
|
||||
- Danielbrdz/Barcenas-Llama3-8b-ORPO
|
||||
- VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
|
||||
- vicgalle/Configurable-Llama-3-8B-v0.3
|
||||
- MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
|
||||
model-index:
|
||||
- name: ChimeraLlama-3-8B-v3
|
||||
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: 44.08
|
||||
name: strict accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
|
||||
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: 27.65
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
|
||||
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: 7.85
|
||||
name: exact match
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
|
||||
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=mlabonne/ChimeraLlama-3-8B-v3
|
||||
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: 8.38
|
||||
name: acc_norm
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
|
||||
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: 29.65
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
# ChimeraLlama-3-8B-v3
|
||||
|
||||
ChimeraLlama-3-8B-v3 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
||||
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
|
||||
* [mlabonne/OrpoLlama-3-8B](https://huggingface.co/mlabonne/OrpoLlama-3-8B)
|
||||
* [cognitivecomputations/dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b)
|
||||
* [Danielbrdz/Barcenas-Llama3-8b-ORPO](https://huggingface.co/Danielbrdz/Barcenas-Llama3-8b-ORPO)
|
||||
* [VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct](https://huggingface.co/VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct)
|
||||
* [vicgalle/Configurable-Llama-3-8B-v0.3](https://huggingface.co/vicgalle/Configurable-Llama-3-8B-v0.3)
|
||||
* [MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3)
|
||||
|
||||
## 🧩 Configuration
|
||||
|
||||
```yaml
|
||||
models:
|
||||
- model: NousResearch/Meta-Llama-3-8B
|
||||
# No parameters necessary for base model
|
||||
- model: NousResearch/Meta-Llama-3-8B-Instruct
|
||||
parameters:
|
||||
density: 0.6
|
||||
weight: 0.5
|
||||
- model: mlabonne/OrpoLlama-3-8B
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.05
|
||||
- model: cognitivecomputations/dolphin-2.9-llama3-8b
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.05
|
||||
- model: Danielbrdz/Barcenas-Llama3-8b-ORPO
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.2
|
||||
- model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.1
|
||||
- model: vicgalle/Configurable-Llama-3-8B-v0.3
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.05
|
||||
- model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.05
|
||||
merge_method: dare_ties
|
||||
base_model: NousResearch/Meta-Llama-3-8B
|
||||
parameters:
|
||||
int8_mask: true
|
||||
dtype: float16
|
||||
```
|
||||
|
||||
## 💻 Usage
|
||||
|
||||
```python
|
||||
!pip install -qU transformers accelerate
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
import transformers
|
||||
import torch
|
||||
|
||||
model = "mlabonne/ChimeraLlama-3-8B-v3"
|
||||
messages = [{"role": "user", "content": "What is a large language model?"}]
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model)
|
||||
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
pipeline = transformers.pipeline(
|
||||
"text-generation",
|
||||
model=model,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
)
|
||||
|
||||
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
||||
print(outputs[0]["generated_text"])
|
||||
```
|
||||
# [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_mlabonne__ChimeraLlama-3-8B-v3)
|
||||
|
||||
| Metric |Value|
|
||||
|-------------------|----:|
|
||||
|Avg. |20.53|
|
||||
|IFEval (0-Shot) |44.08|
|
||||
|BBH (3-Shot) |27.65|
|
||||
|MATH Lvl 5 (4-Shot)| 7.85|
|
||||
|GPQA (0-shot) | 5.59|
|
||||
|MuSR (0-shot) | 8.38|
|
||||
|MMLU-PRO (5-shot) |29.65|
|
||||
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "NousResearch/Meta-Llama-3-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"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": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.40.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
37
mergekit_config.yml
Normal file
37
mergekit_config.yml
Normal file
@@ -0,0 +1,37 @@
|
||||
|
||||
models:
|
||||
- model: NousResearch/Meta-Llama-3-8B
|
||||
# No parameters necessary for base model
|
||||
- model: NousResearch/Meta-Llama-3-8B-Instruct
|
||||
parameters:
|
||||
density: 0.6
|
||||
weight: 0.5
|
||||
- model: mlabonne/OrpoLlama-3-8B
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.05
|
||||
- model: cognitivecomputations/dolphin-2.9-llama3-8b
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.05
|
||||
- model: Danielbrdz/Barcenas-Llama3-8b-ORPO
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.2
|
||||
- model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.1
|
||||
- model: vicgalle/Configurable-Llama-3-8B-v0.3
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.05
|
||||
- model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
|
||||
parameters:
|
||||
density: 0.55
|
||||
weight: 0.05
|
||||
merge_method: dare_ties
|
||||
base_model: NousResearch/Meta-Llama-3-8B
|
||||
parameters:
|
||||
int8_mask: true
|
||||
dtype: float16
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:604006d84eaeadbf208a88845e851366d68446a94bed3452ec2c967dc44e11f3
|
||||
size 9953405568
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:94ae09b9577853eb2c4d9f5bfa67603d40d2d977d0642d4b03702c8f59d3403c
|
||||
size 6107150504
|
||||
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": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7
|
||||
size 9085698
|
||||
2061
tokenizer_config.json
Normal file
2061
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user