mwitiderrick commited on
Commit
360bf72
1 Parent(s): 4437aa5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -53
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
- base_model: openlm-research/open_llama_3b
3
  datasets:
4
  - mwitiderrick/AlpacaCode
5
  inference: true
6
  model_type: llama
7
  prompt_template: |
8
- ### Instruction:\n
9
  {prompt}
10
- ### Response:
11
  created_by: mwitiderrick
12
  tags:
13
  - transformers
@@ -28,7 +28,7 @@ model-index:
28
  metrics:
29
  - name: hellaswag(0-Shot)
30
  type: hellaswag (0-Shot)
31
- value: 0.6581
32
  - task:
33
  type: text-generation
34
  dataset:
@@ -37,7 +37,7 @@ model-index:
37
  metrics:
38
  - name: winogrande(0-Shot)
39
  type: winogrande (0-Shot)
40
- value: 0.6267
41
 
42
  - task:
43
  type: text-generation
@@ -47,7 +47,7 @@ model-index:
47
  metrics:
48
  - name: arc_challenge(0-Shot)
49
  type: arc_challenge (0-Shot)
50
- value: 0.3712
51
  source:
52
  name: open_llama_3b_instruct_v_0.2 model card
53
  url: https://huggingface.co/mwitiderrick/open_llama_3b_instruct_v_0.2
@@ -56,69 +56,30 @@ model-index:
56
  ---
57
  # OpenLLaMA Code Instruct: An Open Reproduction of LLaMA
58
 
59
- This is an [OpenLlama model](https://huggingface.co/openlm-research/open_llama_3b) that has been fine-tuned on 1 epoch of the
60
- [AlpacaCode](https://huggingface.co/datasets/mwitiderrick/AlpacaCode) dataset (122K rows).
61
 
62
  ## Prompt Template
63
  ```
64
- ### Instruction:
65
 
66
- {query}
67
-
68
- ### Response:
69
- <Leave new line for model to respond>
70
  ```
71
  ## Usage
72
  ```python
73
  from transformers import AutoTokenizer, AutoModelForCausalLM,pipeline
74
 
75
- tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/open_llama_3b_code_instruct_0.1")
76
- model = AutoModelForCausalLM.from_pretrained("mwitiderrick/open_llama_3b_code_instruct_0.1")
77
  query = "Write a quick sort algorithm in Python"
78
  text_gen = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
79
- output = text_gen(f"### Instruction:\n{query}\n### Response:\n")
80
  print(output[0]['generated_text'])
81
  """
82
- ### Instruction:
83
- write a quick sort algorithm in Python
84
- ### Response:
85
- def quick_sort(arr):
86
- if len(arr) <= 1:
87
- return arr
88
- else:
89
- pivot = arr[len(arr) // 2]
90
- left = [x for x in arr if x < pivot]
91
- middle = [x for x in arr if x == pivot]
92
- right = [x for x in arr if x > pivot]
93
- return quick_sort(left) + middle + quick_sort(right)
94
 
95
- arr = [5,2,4,3,1]
96
- print(quick_sort(arr))
97
- """
98
- [1, 2, 3, 4, 5]
99
  """
100
  ```
101
  ## Metrics
102
- [Detailed metrics](https://huggingface.co/datasets/open-llm-leaderboard/details_mwitiderrick__open_llama_3b_code_instruct_0.1)
103
  ```
104
- | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
105
- |----------|-------|------|-----:|------|-----:|---|-----:|
106
- |winogrande|Yaml |none | 0|acc |0.6267|± |0.0136|
107
- |hellaswag|Yaml |none | 0|acc |0.4962|± |0.0050|
108
- | | |none | 0|acc_norm|0.6581|± |0.0047|
109
- |arc_challenge|Yaml |none | 0|acc |0.3481|± |0.0139|
110
- | | |none | 0|acc_norm|0.3712|± |0.0141|
111
- |truthfulqa|N/A |none | 0|bleu_max | 24.2580|± |0.5985|
112
- | | |none | 0|bleu_acc | 0.2876|± |0.0003|
113
- | | |none | 0|bleu_diff | -8.3685|± |0.6065|
114
- | | |none | 0|rouge1_max | 49.3907|± |0.7350|
115
- | | |none | 0|rouge1_acc | 0.2558|± |0.0002|
116
- | | |none | 0|rouge1_diff|-10.6617|± |0.6450|
117
- | | |none | 0|rouge2_max | 32.4189|± |0.9587|
118
- | | |none | 0|rouge2_acc | 0.2142|± |0.0002|
119
- | | |none | 0|rouge2_diff|-12.9903|± |0.9539|
120
- | | |none | 0|rougeL_max | 46.2337|± |0.7493|
121
- | | |none | 0|rougeL_acc | 0.2424|± |0.0002|
122
- | | |none | 0|rougeL_diff|-11.0285|± |0.6576|
123
- | | |none | 0|acc | 0.3072|± |0.0405|
124
  ```
 
1
  ---
2
+ base_model: mwitiderrick/open_llama_3b_code_instruct_0.1
3
  datasets:
4
  - mwitiderrick/AlpacaCode
5
  inference: true
6
  model_type: llama
7
  prompt_template: |
8
+ <s>[INST]
9
  {prompt}
10
+ [/INST]
11
  created_by: mwitiderrick
12
  tags:
13
  - transformers
 
28
  metrics:
29
  - name: hellaswag(0-Shot)
30
  type: hellaswag (0-Shot)
31
+ value: 0.
32
  - task:
33
  type: text-generation
34
  dataset:
 
37
  metrics:
38
  - name: winogrande(0-Shot)
39
  type: winogrande (0-Shot)
40
+ value: 0.
41
 
42
  - task:
43
  type: text-generation
 
47
  metrics:
48
  - name: arc_challenge(0-Shot)
49
  type: arc_challenge (0-Shot)
50
+ value: 0.
51
  source:
52
  name: open_llama_3b_instruct_v_0.2 model card
53
  url: https://huggingface.co/mwitiderrick/open_llama_3b_instruct_v_0.2
 
56
  ---
57
  # OpenLLaMA Code Instruct: An Open Reproduction of LLaMA
58
 
59
+ This is an [OpenLlama model Code Instruct](https://huggingface.co/mwitiderrick/open_llama_3b_code_instruct_0.1) that has been fine-tuned on 1 epoch of the
60
+ [Glaive Assistsnt](https://huggingface.co/datasets/mwitiderrick/glaive-code-assistant) dataset.
61
 
62
  ## Prompt Template
63
  ```
64
+ <s>[INST] {{ user_msg }} [/INST]
65
 
 
 
 
 
66
  ```
67
  ## Usage
68
  ```python
69
  from transformers import AutoTokenizer, AutoModelForCausalLM,pipeline
70
 
71
+ tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/open_llama_3b_glaive_assistant_v0.1")
72
+ model = AutoModelForCausalLM.from_pretrained("mwitiderrick/open_llama_3b_glaive_assistant_v0.1")
73
  query = "Write a quick sort algorithm in Python"
74
  text_gen = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
75
+ output = text_gen(f<s>[INST]{query}[/INST]")
76
  print(output[0]['generated_text'])
77
  """
 
 
 
 
 
 
 
 
 
 
 
 
78
 
 
 
 
 
79
  """
80
  ```
81
  ## Metrics
82
+
83
  ```
84
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
  ```