pcuenq HF staff commited on
Commit
2aaef5e
·
verified ·
1 Parent(s): acb9675

Minor fixes to model card

Browse files
Files changed (1) hide show
  1. README.md +22 -22
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  - name: pass@1
22
  type: pass@1
23
  value:
24
- veriefied: false
25
  - task:
26
  type: text-generation
27
  dataset:
@@ -31,7 +31,7 @@ model-index:
31
  - name: pass@1
32
  type: pass@1
33
  value:
34
- veriefied: false
35
  - task:
36
  type: text-generation
37
  dataset:
@@ -41,7 +41,7 @@ model-index:
41
  - name: pass@1
42
  type: pass@1
43
  value:
44
- veriefied: false
45
  - task:
46
  type: text-generation
47
  dataset:
@@ -51,7 +51,7 @@ model-index:
51
  - name: pass@1
52
  type: pass@1
53
  value:
54
- veriefied: false
55
  - task:
56
  type: text-generation
57
  dataset:
@@ -61,7 +61,7 @@ model-index:
61
  - name: pass@1
62
  type: pass@1
63
  value:
64
- veriefied: false
65
  - task:
66
  type: text-generation
67
  dataset:
@@ -71,7 +71,7 @@ model-index:
71
  - name: pass@1
72
  type: pass@1
73
  value:
74
- veriefied: false
75
  - task:
76
  type: text-generation
77
  dataset:
@@ -81,7 +81,7 @@ model-index:
81
  - name: pass@1
82
  type: pass@1
83
  value:
84
- veriefied: false
85
  - task:
86
  type: text-generation
87
  dataset:
@@ -91,7 +91,7 @@ model-index:
91
  - name: pass@1
92
  type: pass@1
93
  value:
94
- veriefied: false
95
  - task:
96
  type: text-generation
97
  dataset:
@@ -101,7 +101,7 @@ model-index:
101
  - name: pass@1
102
  type: pass@1
103
  value:
104
- veriefied: false
105
  - task:
106
  type: text-generation
107
  dataset:
@@ -111,7 +111,7 @@ model-index:
111
  - name: pass@1
112
  type: pass@1
113
  value:
114
- veriefied: false
115
  - task:
116
  type: text-generation
117
  dataset:
@@ -121,7 +121,7 @@ model-index:
121
  - name: pass@1
122
  type: pass@1
123
  value:
124
- veriefied: false
125
  - task:
126
  type: text-generation
127
  dataset:
@@ -131,7 +131,7 @@ model-index:
131
  - name: pass@1
132
  type: pass@1
133
  value:
134
- veriefied: false
135
  - task:
136
  type: text-generation
137
  dataset:
@@ -141,7 +141,7 @@ model-index:
141
  - name: pass@1
142
  type: pass@1
143
  value:
144
- veriefied: false
145
  - task:
146
  type: text-generation
147
  dataset:
@@ -151,7 +151,7 @@ model-index:
151
  - name: pass@1
152
  type: pass@1
153
  value:
154
- veriefied: false
155
  - task:
156
  type: text-generation
157
  dataset:
@@ -161,7 +161,7 @@ model-index:
161
  - name: pass@1
162
  type: pass@1
163
  value:
164
- veriefied: false
165
  - task:
166
  type: text-generation
167
  dataset:
@@ -171,7 +171,7 @@ model-index:
171
  - name: pass@1
172
  type: pass@1
173
  value:
174
- veriefied: false
175
  - task:
176
  type: text-generation
177
  dataset:
@@ -181,7 +181,7 @@ model-index:
181
  - name: pass@1
182
  type: pass@1
183
  value:
184
- veriefied: false
185
  - task:
186
  type: text-generation
187
  dataset:
@@ -191,7 +191,7 @@ model-index:
191
  - name: pass@1
192
  type: pass@1
193
  value:
194
- veriefied: false
195
  - task:
196
  type: text-generation
197
  dataset:
@@ -201,14 +201,14 @@ model-index:
201
  - name: pass@1
202
  type: pass@1
203
  value:
204
- veriefied: false
205
  ---
206
  <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) -->
207
 
208
  # Granite-3.0-1B-A400M-Instruct
209
 
210
  ## Model Summary
211
- **Granite-3.0-1B-A400M-Instruct** is a lightweight and open-source 1B parameter model fine tuned from *Granite-3.0-1B-A400M-Base* on a combination of open-source and proprietary instruction data with a **permissively licensed**. This language model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, funcion-calling, and more.
212
 
213
  - **Developers:** IBM Research
214
  - **GitHub Repository:** [ibm-granite/granite-language-models](https://github.com/ibm-granite/granite-language-models)
@@ -262,14 +262,14 @@ chat = [
262
  ]
263
  chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
264
  # tokenize the text
265
- input_tokens = tokenizer(chat, return_tensors="pt").to(device)
266
  # generate output tokens
267
  output = model.generate(**input_tokens,
268
  max_new_tokens=100)
269
  # decode output tokens into text
270
  output = tokenizer.batch_decode(output)
271
  # print output
272
- print(output)
273
  ```
274
 
275
  <!-- TO DO: function-calling-example
 
21
  - name: pass@1
22
  type: pass@1
23
  value:
24
+ verified: false
25
  - task:
26
  type: text-generation
27
  dataset:
 
31
  - name: pass@1
32
  type: pass@1
33
  value:
34
+ verified: false
35
  - task:
36
  type: text-generation
37
  dataset:
 
41
  - name: pass@1
42
  type: pass@1
43
  value:
44
+ verified: false
45
  - task:
46
  type: text-generation
47
  dataset:
 
51
  - name: pass@1
52
  type: pass@1
53
  value:
54
+ verified: false
55
  - task:
56
  type: text-generation
57
  dataset:
 
61
  - name: pass@1
62
  type: pass@1
63
  value:
64
+ verified: false
65
  - task:
66
  type: text-generation
67
  dataset:
 
71
  - name: pass@1
72
  type: pass@1
73
  value:
74
+ verified: false
75
  - task:
76
  type: text-generation
77
  dataset:
 
81
  - name: pass@1
82
  type: pass@1
83
  value:
84
+ verified: false
85
  - task:
86
  type: text-generation
87
  dataset:
 
91
  - name: pass@1
92
  type: pass@1
93
  value:
94
+ verified: false
95
  - task:
96
  type: text-generation
97
  dataset:
 
101
  - name: pass@1
102
  type: pass@1
103
  value:
104
+ verified: false
105
  - task:
106
  type: text-generation
107
  dataset:
 
111
  - name: pass@1
112
  type: pass@1
113
  value:
114
+ verified: false
115
  - task:
116
  type: text-generation
117
  dataset:
 
121
  - name: pass@1
122
  type: pass@1
123
  value:
124
+ verified: false
125
  - task:
126
  type: text-generation
127
  dataset:
 
131
  - name: pass@1
132
  type: pass@1
133
  value:
134
+ verified: false
135
  - task:
136
  type: text-generation
137
  dataset:
 
141
  - name: pass@1
142
  type: pass@1
143
  value:
144
+ verified: false
145
  - task:
146
  type: text-generation
147
  dataset:
 
151
  - name: pass@1
152
  type: pass@1
153
  value:
154
+ verified: false
155
  - task:
156
  type: text-generation
157
  dataset:
 
161
  - name: pass@1
162
  type: pass@1
163
  value:
164
+ verified: false
165
  - task:
166
  type: text-generation
167
  dataset:
 
171
  - name: pass@1
172
  type: pass@1
173
  value:
174
+ verified: false
175
  - task:
176
  type: text-generation
177
  dataset:
 
181
  - name: pass@1
182
  type: pass@1
183
  value:
184
+ verified: false
185
  - task:
186
  type: text-generation
187
  dataset:
 
191
  - name: pass@1
192
  type: pass@1
193
  value:
194
+ verified: false
195
  - task:
196
  type: text-generation
197
  dataset:
 
201
  - name: pass@1
202
  type: pass@1
203
  value:
204
+ verified: false
205
  ---
206
  <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) -->
207
 
208
  # Granite-3.0-1B-A400M-Instruct
209
 
210
  ## Model Summary
211
+ **Granite-3.0-1B-A400M-Instruct** is a lightweight and open-source 1B parameter model fine tuned from *Granite-3.0-1B-A400M-Base* on a combination of open-source and proprietary instruction data with a **permissive license**. This language model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, funcion-calling, and more.
212
 
213
  - **Developers:** IBM Research
214
  - **GitHub Repository:** [ibm-granite/granite-language-models](https://github.com/ibm-granite/granite-language-models)
 
262
  ]
263
  chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
264
  # tokenize the text
265
+ input_tokens = tokenizer(chat, return_tensors="pt").to(model.device)
266
  # generate output tokens
267
  output = model.generate(**input_tokens,
268
  max_new_tokens=100)
269
  # decode output tokens into text
270
  output = tokenizer.batch_decode(output)
271
  # print output
272
+ print(output[0])
273
  ```
274
 
275
  <!-- TO DO: function-calling-example