reach-vb HF staff commited on
Commit
d615857
1 Parent(s): 961c560

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: AI-MO/NuminaMath-7B-TIR
3
+ license: apache-2.0
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - alignment-handbook
7
+ - generated_from_trainer
8
+ - llama-cpp
9
+ - gguf-my-repo
10
+ widget:
11
+ - example_title: Math problem
12
+ messages:
13
+ - role: user
14
+ content: For how many values of the constant $k$ will the polynomial $x^{2}+kx+36$
15
+ have two distinct integer roots?
16
+ output:
17
+ text: "### Solution: \n1- For the polynomial \\\\( x^2 + kx + 36 \\\\) to have\
18
+ \ two distinct integer roots, let's denote these roots by \\\\( r_1 \\\\) and\
19
+ \ \\\\( r_2 \\\\).\n\n\n2- According to Vieta's formulas, the sum of the roots\
20
+ \ \\\\( r_1 + r_2 \\\\) is equal to \\\\(-k\\\\), and the product of the roots\
21
+ \ \\\\( r_1 \\\\cdot r_2 \\\\) is equal to 36.\n\n\n3- To find the distinct\
22
+ \ integer pairs \\\\((r_1, r_2)\\\\) whose product is 36, we need to determine\
23
+ \ all pairs of integers \\\\((r_1, r_2)\\\\) such that \\\\( r_1 \\\\cdot r_2\
24
+ \ = 36 \\\\) and \\\\( r_1 \\\\neq r_2 \\\\).\n\n\n4- From the equation \\\\\
25
+ ( r_1 + r_2 = -k \\\\), for each valid pair \\\\((r_1, r_2)\\\\), we can compute\
26
+ \ the corresponding value of \\\\( k \\\\).\n\n\n5- Finally, since we need the\
27
+ \ polynomial to have two distinct integer roots, we need to ensure that \\\\\
28
+ ( r_1 \\\\) and \\\\( r_2 \\\\) are distinct.\nLet's start by finding all pairs\
29
+ \ \\\\((r_1, r_2)\\\\) such that \\\\( r_1 \\\\cdot r_2 = 36 \\\\). We'll then\
30
+ \ determine the values of \\\\( k \\\\) and ensure the roots are distinct.\n\
31
+ ```python import itertools\n# Find all pairs (r1, r2) such that r1 * r2 = 36\
32
+ \ product_36 = 36 factor_pairs = []\nfor i in range(1, product_36 + 1):\n if\
33
+ \ product_36 % i == 0:\n pair = (i, product_36 // i)\n if pair[0] != pair[1]:\
34
+ \ # Ensure distinct pairs\n factor_pairs.append(pair)\n \n # Calculate\
35
+ \ k for each pair and ensure distinct integer roots\n valid_k_values = set()\n\
36
+ \ for r1, r2 in factor_pairs:\n if r1 != r2:\n k = -(r1 + r2)\n\
37
+ \ valid_k_values.add(k)\n \n print((len(valid_k_values), sorted(valid_k_values)))\n\
38
+ \ ```\n \n ```output\n (4, [-37, -20, -15,-13])\n ```\n The distinct integer\
39
+ \ values of \\\\( k \\\\) that make the\npolynomial \\\\( x^2 + kx + 36 \\\\\
40
+ ) have two distinct integer roots are \\\\(-37, -20, -15, \\\\text{and} -13\\\
41
+ \\).\nTherefore, the number of such values of \\\\( k \\\\) is:\n[ \\\\boxed{4}\
42
+ \ \\\\]"
43
+ model-index:
44
+ - name: NuminaMath-7B-TIR
45
+ results: []
46
+ ---
47
+
48
+ # reach-vb/NuminaMath-7B-TIR-Q8_0-GGUF
49
+ This model was converted to GGUF format from [`AI-MO/NuminaMath-7B-TIR`](https://huggingface.co/AI-MO/NuminaMath-7B-TIR) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
50
+ Refer to the [original model card](https://huggingface.co/AI-MO/NuminaMath-7B-TIR) for more details on the model.
51
+
52
+ ## Use with llama.cpp
53
+ Install llama.cpp through brew (works on Mac and Linux)
54
+
55
+ ```bash
56
+ brew install llama.cpp
57
+
58
+ ```
59
+ Invoke the llama.cpp server or the CLI.
60
+
61
+ ### CLI:
62
+ ```bash
63
+ llama-cli --hf-repo reach-vb/NuminaMath-7B-TIR-Q8_0-GGUF --hf-file numinamath-7b-tir-q8_0.gguf -p "The meaning to life and the universe is"
64
+ ```
65
+
66
+ ### Server:
67
+ ```bash
68
+ llama-server --hf-repo reach-vb/NuminaMath-7B-TIR-Q8_0-GGUF --hf-file numinamath-7b-tir-q8_0.gguf -c 2048
69
+ ```
70
+
71
+ 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.
72
+
73
+ Step 1: Clone llama.cpp from GitHub.
74
+ ```
75
+ git clone https://github.com/ggerganov/llama.cpp
76
+ ```
77
+
78
+ 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).
79
+ ```
80
+ cd llama.cpp && LLAMA_CURL=1 make
81
+ ```
82
+
83
+ Step 3: Run inference through the main binary.
84
+ ```
85
+ ./llama-cli --hf-repo reach-vb/NuminaMath-7B-TIR-Q8_0-GGUF --hf-file numinamath-7b-tir-q8_0.gguf -p "The meaning to life and the universe is"
86
+ ```
87
+ or
88
+ ```
89
+ ./llama-server --hf-repo reach-vb/NuminaMath-7B-TIR-Q8_0-GGUF --hf-file numinamath-7b-tir-q8_0.gguf -c 2048
90
+ ```