初始化项目，由ModelHub XC社区提供模型
Model: cloudyu/Mixtral_7Bx2_MoE 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
|
||||||
188
README.md
Normal file
188
README.md
Normal file
@@ -0,0 +1,188 @@
|
|||||||
|
---
|
||||||
|
license: cc-by-nc-4.0
|
||||||
|
model-index:
|
||||||
|
- name: Mixtral_7Bx2_MoE
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: AI2 Reasoning Challenge (25-Shot)
|
||||||
|
type: ai2_arc
|
||||||
|
config: ARC-Challenge
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 25
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 71.25
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: HellaSwag (10-Shot)
|
||||||
|
type: hellaswag
|
||||||
|
split: validation
|
||||||
|
args:
|
||||||
|
num_few_shot: 10
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 87.45
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MMLU (5-Shot)
|
||||||
|
type: cais/mmlu
|
||||||
|
config: all
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 64.98
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE
|
||||||
|
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:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: mc2
|
||||||
|
value: 67.23
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: Winogrande (5-shot)
|
||||||
|
type: winogrande
|
||||||
|
config: winogrande_xl
|
||||||
|
split: validation
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 81.22
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: GSM8k (5-shot)
|
||||||
|
type: gsm8k
|
||||||
|
config: main
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 68.46
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
---
|
||||||
|
|
||||||
|
# Mixtral MOE 2x7B
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
MoE of the following models :
|
||||||
|
|
||||||
|
|
||||||
|
* [NurtureAI/neural-chat-7b-v3-16k](https://huggingface.co/NurtureAI/neural-chat-7b-v3-16k)
|
||||||
|
* [mncai/mistral-7b-dpo-v6](https://huggingface.co/mncai/mistral-7b-dpo-v6)
|
||||||
|
|
||||||
|
|
||||||
|
* metrics:
|
||||||
|
Average 73.43
|
||||||
|
ARC 71.25
|
||||||
|
HellaSwag 87.45
|
||||||
|
|
||||||
|
gpu code example
|
||||||
|
|
||||||
|
```
|
||||||
|
import torch
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
import math
|
||||||
|
|
||||||
|
## v2 models
|
||||||
|
model_path = "cloudyu/Mixtral_7Bx2_MoE"
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
|
||||||
|
)
|
||||||
|
print(model)
|
||||||
|
prompt = input("please input prompt:")
|
||||||
|
while len(prompt) > 0:
|
||||||
|
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
|
||||||
|
|
||||||
|
generation_output = model.generate(
|
||||||
|
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
|
||||||
|
)
|
||||||
|
print(tokenizer.decode(generation_output[0]))
|
||||||
|
prompt = input("please input prompt:")
|
||||||
|
```
|
||||||
|
|
||||||
|
CPU example
|
||||||
|
|
||||||
|
```
|
||||||
|
import torch
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
import math
|
||||||
|
|
||||||
|
## v2 models
|
||||||
|
model_path = "cloudyu/Mixtral_7Bx2_MoE"
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False
|
||||||
|
)
|
||||||
|
print(model)
|
||||||
|
prompt = input("please input prompt:")
|
||||||
|
while len(prompt) > 0:
|
||||||
|
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
|
||||||
|
|
||||||
|
generation_output = model.generate(
|
||||||
|
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
|
||||||
|
)
|
||||||
|
print(tokenizer.decode(generation_output[0]))
|
||||||
|
prompt = input("please input prompt:")
|
||||||
|
|
||||||
|
```
|
||||||
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||||
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cloudyu__Mixtral_7Bx2_MoE)
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|---------------------------------|----:|
|
||||||
|
|Avg. |73.43|
|
||||||
|
|AI2 Reasoning Challenge (25-Shot)|71.25|
|
||||||
|
|HellaSwag (10-Shot) |87.45|
|
||||||
|
|MMLU (5-Shot) |64.98|
|
||||||
|
|TruthfulQA (0-shot) |67.23|
|
||||||
|
|Winogrande (5-shot) |81.22|
|
||||||
|
|GSM8k (5-shot) |68.46|
|
||||||
|
|
||||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "NurtureAI/neural-chat-7b-v3-16k",
|
||||||
|
"architectures": [
|
||||||
|
"MixtralForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"model_type": "mixtral",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_experts_per_tok": 2,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"num_local_experts": 2,
|
||||||
|
"output_router_logits": false,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"router_aux_loss_coef": 0.001,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.36.2",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 32000
|
||||||
|
}
|
||||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:44b47e131f64d78a416068317f2f5e20bdd4d09fa77126e4c474426d3859fffd
|
||||||
|
size 9919813560
|
||||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d20621c9015ae54cfc42e5a3e5327acb41b933c78ab0aa7d07e24be4c6549c14
|
||||||
|
size 9982454648
|
||||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ca762bc0fae026b0539b35b84572b4229fd28a5284a8f988f3df3081f4fc151d
|
||||||
|
size 5856060968
|
||||||
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
29
special_tokens_map.json
Normal file
29
special_tokens_map.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<unk>",
|
||||||
|
"<s>",
|
||||||
|
"</s>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": "<s>",
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
91129
tokenizer.json
Normal file
91129
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
48
tokenizer_config.json
Normal file
48
tokenizer_config.json
Normal file
@@ -0,0 +1,48 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"add_eos_token": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"0": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"1": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<unk>",
|
||||||
|
"<s>",
|
||||||
|
"</s>"
|
||||||
|
],
|
||||||
|
"bos_token": "<s>",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "</s>",
|
||||||
|
"legacy": true,
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"pad_token": "<s>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"spaces_between_special_tokens": false,
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"unk_token": "<unk>",
|
||||||
|
"use_default_system_prompt": true
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user