Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,90 @@
+---
+base_model: AI-MO/NuminaMath-7B-TIR
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- alignment-handbook
+- generated_from_trainer
+- llama-cpp
+- gguf-my-repo
+widget:
+- example_title: Math problem
+  messages:
+  - role: user
+    content: For how many values of the constant $k$ will the polynomial $x^{2}+kx+36$
+      have two distinct integer roots?
+  output:
+    text: "### Solution: \n1- For the polynomial \\\\( x^2 + kx + 36 \\\\) to have\
+      \ two distinct integer roots, let's denote these roots by \\\\( r_1 \\\\) and\
+      \ \\\\( r_2 \\\\).\n\n\n2- According to Vieta's formulas, the sum of the roots\
+      \ \\\\( r_1 + r_2 \\\\) is equal to \\\\(-k\\\\), and the product of the roots\
+      \ \\\\( r_1 \\\\cdot r_2 \\\\) is equal to 36.\n\n\n3- To find the distinct\
+      \ integer pairs \\\\((r_1, r_2)\\\\) whose product is 36, we need to determine\
+      \ all pairs of integers \\\\((r_1, r_2)\\\\) such that \\\\( r_1 \\\\cdot r_2\
+      \ = 36 \\\\) and \\\\( r_1 \\\\neq r_2 \\\\).\n\n\n4- From the equation \\\\\
+      ( r_1 + r_2 = -k \\\\), for each valid pair \\\\((r_1, r_2)\\\\), we can compute\
+      \ the corresponding value of \\\\( k \\\\).\n\n\n5- Finally, since we need the\
+      \ polynomial to have two distinct integer roots, we need to ensure that \\\\\
+      ( r_1 \\\\) and \\\\( r_2 \\\\) are distinct.\nLet's start by finding all pairs\
+      \ \\\\((r_1, r_2)\\\\) such that \\\\( r_1 \\\\cdot r_2 = 36 \\\\). We'll then\
+      \ determine the values of \\\\( k \\\\) and ensure the roots are distinct.\n\
+      ```python import itertools\n# Find all pairs (r1, r2) such that r1 * r2 = 36\
+      \ product_36 = 36 factor_pairs = []\nfor i in range(1, product_36 + 1):\n  if\
+      \ product_36 % i == 0:\n    pair = (i, product_36 // i)\n    if pair[0] != pair[1]:\
+      \ # Ensure distinct pairs\n      factor_pairs.append(pair)\n    \n    # Calculate\
+      \ k for each pair and ensure distinct integer roots\n    valid_k_values = set()\n\
+      \    for r1, r2 in factor_pairs:\n      if r1 != r2:\n        k = -(r1 + r2)\n\
+      \        valid_k_values.add(k)\n        \n    print((len(valid_k_values), sorted(valid_k_values)))\n\
+      \ ```\n \n ```output\n (4, [-37, -20, -15,-13])\n ```\n The distinct integer\
+      \ values of \\\\( k \\\\) that make the\npolynomial \\\\( x^2 + kx + 36 \\\\\
+      ) have two distinct integer roots are \\\\(-37, -20, -15, \\\\text{and} -13\\\
+      \\).\nTherefore, the number of such values of \\\\( k \\\\) is:\n[ \\\\boxed{4}\
+      \ \\\\]"
+model-index:
+- name: NuminaMath-7B-TIR
+  results: []
+---
+
+# kawchar85/NuminaMath-7B-TIR-Q8_0-GGUF
+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.
+Refer to the [original model card](https://huggingface.co/AI-MO/NuminaMath-7B-TIR) for more details on the model.
+
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+
+```bash
+brew install llama.cpp
+
+```
+Invoke the llama.cpp server or the CLI.
+
+### CLI:
+```bash
+llama-cli --hf-repo kawchar85/NuminaMath-7B-TIR-Q8_0-GGUF --hf-file numinamath-7b-tir-q8_0.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo kawchar85/NuminaMath-7B-TIR-Q8_0-GGUF --hf-file numinamath-7b-tir-q8_0.gguf -c 2048
+```
+
+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.
+
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+
+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).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo kawchar85/NuminaMath-7B-TIR-Q8_0-GGUF --hf-file numinamath-7b-tir-q8_0.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo kawchar85/NuminaMath-7B-TIR-Q8_0-GGUF --hf-file numinamath-7b-tir-q8_0.gguf -c 2048
+```