Upload README.md with huggingface_hub

README.md

@@ -1,36 +1,146 @@
----
-license: apache-2.0
-tags:
-- llama-cpp
-- gguf-my-repo
----
+---
+license: apache-2.0
+tags:
+- llama-cpp
+- gguf-my-repo
+base_model: newsbang/Homer-v1.0-Qwen2.5-7B
+model-index:
+- name: Homer-v1.0-Qwen2.5-7B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 63.93
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 37.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 30.36
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.62
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 11.88
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 39.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-7B
+      name: Open LLM Leaderboard
+---
 
 # Aashraf995/Homer-v1.0-Qwen2.5-7B-Q6_K-GGUF
 This model was converted to GGUF format from [`newsbang/Homer-v1.0-Qwen2.5-7B`](https://huggingface.co/newsbang/Homer-v1.0-Qwen2.5-7B) 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/newsbang/Homer-v1.0-Qwen2.5-7B) for more details on the model.
-## Use with llama.cpp
 
-Install llama.cpp through brew.
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
 
 ```bash
-brew install ggerganov/ggerganov/llama.cpp
+brew install llama.cpp
+
 ```
 Invoke the llama.cpp server or the CLI.
 
-CLI:
-
+### CLI:
 ```bash
-llama-cli --hf-repo Aashraf995/Homer-v1.0-Qwen2.5-7B-Q6_K-GGUF --model homer-v1.0-qwen2.5-7b.Q6_K.gguf -p "The meaning to life and the universe is"
+llama-cli --hf-repo Aashraf995/Homer-v1.0-Qwen2.5-7B-Q6_K-GGUF --hf-file homer-v1.0-qwen2.5-7b-q6_k.gguf -p "The meaning to life and the universe is"
 ```
 
-Server:
-
+### Server:
 ```bash
-llama-server --hf-repo Aashraf995/Homer-v1.0-Qwen2.5-7B-Q6_K-GGUF --model homer-v1.0-qwen2.5-7b.Q6_K.gguf -c 2048
+llama-server --hf-repo Aashraf995/Homer-v1.0-Qwen2.5-7B-Q6_K-GGUF --hf-file homer-v1.0-qwen2.5-7b-q6_k.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 Aashraf995/Homer-v1.0-Qwen2.5-7B-Q6_K-GGUF --hf-file homer-v1.0-qwen2.5-7b-q6_k.gguf -p "The meaning to life and the universe is"
+```
+or 
 ```
-git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m homer-v1.0-qwen2.5-7b.Q6_K.gguf -n 128
+./llama-server --hf-repo Aashraf995/Homer-v1.0-Qwen2.5-7B-Q6_K-GGUF --hf-file homer-v1.0-qwen2.5-7b-q6_k.gguf -c 2048
 ```