Create README.md

README.md

@@ -0,0 +1,182 @@
+---
+license: apache-2.0
+model-index:
+- name: Yi-9Bx2-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 :
+
+
+* [byroneverson/Yi-1.5-9B-Chat-16K-abliterated](https://huggingface.co/byroneverson/Yi-1.5-9B-Chat-16K-abliterated)
+* [BAAI/Infinity-Instruct-3M-0625-Yi-1.5-9B](https://huggingface.co/BAAI/Infinity-Instruct-3M-0625-Yi-1.5-9B)
+
+
+* 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/Yi-9Bx2-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/Yi-9Bx2-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:")
+
+```