GGUF
English
llama-cpp
gguf-my-repo
Theta-Lev commited on
Commit
fbfd55c
·
verified ·
1 Parent(s): 0fc652c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +212 -0
README.md ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: togethercomputer/RedPajama-INCITE-Instruct-3B-v1
3
+ datasets:
4
+ - togethercomputer/RedPajama-Data-1T
5
+ - Muennighoff/P3
6
+ - Muennighoff/natural-instructions
7
+ language:
8
+ - en
9
+ license: apache-2.0
10
+ tags:
11
+ - llama-cpp
12
+ - gguf-my-repo
13
+ widget:
14
+ - text: "Label the tweets as either 'positive', 'negative', 'mixed', or 'neutral':\
15
+ \ \n\nTweet: I can say that there isn't anything I would change.\nLabel: positive\n\
16
+ \nTweet: I'm not sure about this.\nLabel: neutral\n\nTweet: I liked some parts\
17
+ \ but I didn't like other parts.\nLabel: mixed\n\nTweet: I think the background\
18
+ \ image could have been better.\nLabel: negative\n\nTweet: I really like it.\n\
19
+ Label:"
20
+ example_title: Sentiment Analysis
21
+ - text: 'Please answer the following question:
22
+
23
+
24
+ Question: What is the capital of Canada?
25
+
26
+ Answer: Ottawa
27
+
28
+
29
+ Question: What is the currency of Switzerland?
30
+
31
+ Answer: Swiss franc
32
+
33
+
34
+ Question: In which country is Wisconsin located?
35
+
36
+ Answer:'
37
+ example_title: Question Answering
38
+ - text: 'Given a news article, classify its topic.
39
+
40
+ Possible labels: 1. World 2. Sports 3. Business 4. Sci/Tech
41
+
42
+
43
+ Article: A nearby star thought to harbor comets and asteroids now appears to be
44
+ home to planets, too.
45
+
46
+ Label: Sci/Tech
47
+
48
+
49
+ Article: Soaring crude prices plus worries about the economy and the outlook for
50
+ earnings are expected to hang over the stock market next week during the depth
51
+ of the summer doldrums.
52
+
53
+ Label: Business
54
+
55
+
56
+ Article: Murtagh a stickler for success Northeastern field hockey coach Cheryl
57
+ Murtagh doesn''t want the glare of the spotlight that shines on her to detract
58
+ from a team that has been the America East champion for the past three years and
59
+ has been to the NCAA tournament 13 times.
60
+
61
+ Label::'
62
+ example_title: Topic Classification
63
+ - text: 'Paraphrase the given sentence into a different sentence.
64
+
65
+
66
+ Input: Can you recommend some upscale restaurants in New York?
67
+
68
+ Output: What upscale restaurants do you recommend in New York?
69
+
70
+
71
+ Input: What are the famous places we should not miss in Paris?
72
+
73
+ Output: Recommend some of the best places to visit in Paris?
74
+
75
+
76
+ Input: Could you recommend some hotels that have cheap price in Zurich?
77
+
78
+ Output:'
79
+ example_title: Paraphrasing
80
+ - text: 'Given a review from Amazon''s food products, the task is to generate a short
81
+ summary of the given review in the input.
82
+
83
+
84
+ Input: I have bought several of the Vitality canned dog food products and have
85
+ found them all to be of good quality. The product looks more like a stew than
86
+ a processed meat and it smells better. My Labrador is finicky and she appreciates
87
+ this product better than most.
88
+
89
+ Output: Good Quality Dog Food
90
+
91
+
92
+ Input: Product arrived labeled as Jumbo Salted Peanuts...the peanuts were actually
93
+ small sized unsalted. Not sure if this was an error or if the vendor intended
94
+ to represent the product as ''Jumbo''.
95
+
96
+ Output: Not as Advertised
97
+
98
+
99
+ Input: My toddler loves this game to a point where he asks for it. That''s a big
100
+ thing for me. Secondly, no glitching unlike one of their competitors (PlayShifu).
101
+ Any tech I don’t have to reach out to support for help is a good tech for me.
102
+ I even enjoy some of the games and activities in this. Overall, this is a product
103
+ that shows that the developers took their time and made sure people would not
104
+ be asking for refund. I’ve become bias regarding this product and honestly I look
105
+ forward to buying more of this company’s stuff. Please keep up the great work.
106
+
107
+ Output:'
108
+ example_title: Text Summarization
109
+ - text: 'Identify which sense of a word is meant in a given context.
110
+
111
+
112
+ Context: The river overflowed the bank.
113
+
114
+ Word: bank
115
+
116
+ Sense: river bank
117
+
118
+
119
+ Context: A mouse takes much more room than a trackball.
120
+
121
+ Word: mouse
122
+
123
+ Sense: computer mouse
124
+
125
+
126
+ Context: The bank will not be accepting cash on Saturdays.
127
+
128
+ Word: bank
129
+
130
+ Sense: commercial (finance) banks
131
+
132
+
133
+ Context: Bill killed the project
134
+
135
+ Word: kill
136
+
137
+ Sense:'
138
+ example_title: Word Sense Disambiguation
139
+ - text: 'Given a pair of sentences, choose whether the two sentences agree (entailment)/disagree
140
+ (contradiction) with each other.
141
+
142
+ Possible labels: 1. entailment 2. contradiction
143
+
144
+
145
+ Sentence 1: The skier was on the edge of the ramp. Sentence 2: The skier was dressed
146
+ in winter clothes.
147
+
148
+ Label: entailment
149
+
150
+
151
+ Sentence 1: The boy skated down the staircase railing. Sentence 2: The boy is
152
+ a newbie skater.
153
+
154
+ Label: contradiction
155
+
156
+
157
+ Sentence 1: Two middle-aged people stand by a golf hole. Sentence 2: A couple
158
+ riding in a golf cart.
159
+
160
+ Label:'
161
+ example_title: Natural Language Inference
162
+ inference:
163
+ parameters:
164
+ temperature: 0.7
165
+ top_p: 0.7
166
+ top_k: 50
167
+ max_new_tokens: 128
168
+ ---
169
+
170
+ # Theta-Lev/RedPajama-INCITE-Instruct-3B-v1-Q8_0-GGUF
171
+ This model was converted to GGUF format from [`togethercomputer/RedPajama-INCITE-Instruct-3B-v1`](https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
172
+ Refer to the [original model card](https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1) for more details on the model.
173
+
174
+ ## Use with llama.cpp
175
+ Install llama.cpp through brew (works on Mac and Linux)
176
+
177
+ ```bash
178
+ brew install llama.cpp
179
+
180
+ ```
181
+ Invoke the llama.cpp server or the CLI.
182
+
183
+ ### CLI:
184
+ ```bash
185
+ llama-cli --hf-repo Theta-Lev/RedPajama-INCITE-Instruct-3B-v1-Q8_0-GGUF --hf-file redpajama-incite-instruct-3b-v1-q8_0.gguf -p "The meaning to life and the universe is"
186
+ ```
187
+
188
+ ### Server:
189
+ ```bash
190
+ llama-server --hf-repo Theta-Lev/RedPajama-INCITE-Instruct-3B-v1-Q8_0-GGUF --hf-file redpajama-incite-instruct-3b-v1-q8_0.gguf -c 2048
191
+ ```
192
+
193
+ Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
194
+
195
+ Step 1: Clone llama.cpp from GitHub.
196
+ ```
197
+ git clone https://github.com/ggerganov/llama.cpp
198
+ ```
199
+
200
+ Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
201
+ ```
202
+ cd llama.cpp && LLAMA_CURL=1 make
203
+ ```
204
+
205
+ Step 3: Run inference through the main binary.
206
+ ```
207
+ ./llama-cli --hf-repo Theta-Lev/RedPajama-INCITE-Instruct-3B-v1-Q8_0-GGUF --hf-file redpajama-incite-instruct-3b-v1-q8_0.gguf -p "The meaning to life and the universe is"
208
+ ```
209
+ or
210
+ ```
211
+ ./llama-server --hf-repo Theta-Lev/RedPajama-INCITE-Instruct-3B-v1-Q8_0-GGUF --hf-file redpajama-incite-instruct-3b-v1-q8_0.gguf -c 2048
212
+ ```