mudler commited on
Commit
2f50ac3
1 Parent(s): 401e99e

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +52 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - it
4
+ license: apache-2.0
5
+ tags:
6
+ - text-generation-inference
7
+ - transformers
8
+ - mistral
9
+ - trl
10
+ - sft
11
+ - llama-cpp
12
+ - gguf-my-repo
13
+ datasets:
14
+ - mchl-labs/stambecco_data_it
15
+ pipeline_tag: text-generation
16
+ widget:
17
+ - text: "Di seguito è riportata un'istruzione che descrive un'attività, abbinata ad\
18
+ \ un input che fornisce ulteriore informazione. Scrivi una risposta che soddisfi\
19
+ \ adeguatamente la richiesta. \n### Istruzione:\nSuggerisci un'attività serale\
20
+ \ romantica\n\n### Input:\n\n### Risposta:"
21
+ example_title: Example 1
22
+ ---
23
+
24
+ # mudler/Minerva-3B-Instruct-v1.0-Q8_0-GGUF
25
+ This model was converted to GGUF format from [`walid-iguider/Minerva-3B-Instruct-v1.0`](https://huggingface.co/walid-iguider/Minerva-3B-Instruct-v1.0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
26
+ Refer to the [original model card](https://huggingface.co/walid-iguider/Minerva-3B-Instruct-v1.0) for more details on the model.
27
+ ## Use with llama.cpp
28
+
29
+ Install llama.cpp through brew.
30
+
31
+ ```bash
32
+ brew install ggerganov/ggerganov/llama.cpp
33
+ ```
34
+ Invoke the llama.cpp server or the CLI.
35
+
36
+ CLI:
37
+
38
+ ```bash
39
+ llama-cli --hf-repo mudler/Minerva-3B-Instruct-v1.0-Q8_0-GGUF --model minerva-3b-instruct-v1.0.Q8_0.gguf -p "The meaning to life and the universe is"
40
+ ```
41
+
42
+ Server:
43
+
44
+ ```bash
45
+ llama-server --hf-repo mudler/Minerva-3B-Instruct-v1.0-Q8_0-GGUF --model minerva-3b-instruct-v1.0.Q8_0.gguf -c 2048
46
+ ```
47
+
48
+ 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.
49
+
50
+ ```
51
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m minerva-3b-instruct-v1.0.Q8_0.gguf -n 128
52
+ ```