Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,158 @@
+---
+base_model: ibm-granite/granite-3b-code-base-128k
+datasets:
+- codeparrot/github-code-clean
+- bigcode/starcoderdata
+- open-web-math/open-web-math
+- math-ai/StackMathQA
+library_name: transformers
+license: apache-2.0
+metrics:
+- code_eval
+pipeline_tag: text-generation
+tags:
+- code
+- granite
+- llama-cpp
+- gguf-my-repo
+inference: false
+model-index:
+- name: granite-3b-code-base-128k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis (Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 36.0
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 30.5
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 22.4
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 19.9
+      name: pass@1
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: RepoQA (Python@16K)
+      type: repoqa
+    metrics:
+    - type: pass@1 (thresh=0.5)
+      value: 40.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 36.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 37.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 27.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 29.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: LCC (Balanced)
+      type: lcc
+    metrics:
+    - type: Exact Match@4K
+      value: 54.6
+      name: Exact Match@4K
+      verified: false
+    - type: Exact Match@8K
+      value: 56.8
+      name: Exact Match@8K
+      verified: false
+    - type: Exact Match@16K
+      value: 52.2
+      name: Exact Match@16K
+      verified: false
+    - type: Exact Match@32K
+      value: 57.8
+      name: Exact Match@32K
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: RepoBench-P (Balanced)
+      type: repobench
+    metrics:
+    - type: Exact Match@4K
+      value: 39.8
+      name: Exact Match@4K
+      verified: false
+    - type: Exact Match@8K
+      value: 46.8
+      name: Exact Match@8K
+      verified: false
+    - type: Exact Match@16K
+      value: 43.1
+      name: Exact Match@16K
+      verified: false
+    - type: Exact Match@32K
+      value: 45.3
+      name: Exact Match@32K
+      verified: false
+---
+
+# ijohn07/granite-3b-code-base-128k-Q8_0-GGUF
+This model was converted to GGUF format from [`ibm-granite/granite-3b-code-base-128k`](https://huggingface.co/ibm-granite/granite-3b-code-base-128k) 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/ibm-granite/granite-3b-code-base-128k) 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 ijohn07/granite-3b-code-base-128k-Q8_0-GGUF --hf-file granite-3b-code-base-128k-q8_0.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo ijohn07/granite-3b-code-base-128k-Q8_0-GGUF --hf-file granite-3b-code-base-128k-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 ijohn07/granite-3b-code-base-128k-Q8_0-GGUF --hf-file granite-3b-code-base-128k-q8_0.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo ijohn07/granite-3b-code-base-128k-Q8_0-GGUF --hf-file granite-3b-code-base-128k-q8_0.gguf -c 2048
+```