Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,175 @@
+---
+license: apache-2.0
+tags:
+- LLMs
+- mistral
+- math
+- Intel
+- llama-cpp
+- gguf-my-repo
+base_model: Intel/neural-chat-7b-v3-1
+model-index:
+- name: neural-chat-7b-v3-3
+  results:
+  - task:
+      type: Large Language Model
+      name: Large Language Model
+    dataset:
+      name: meta-math/MetaMathQA
+      type: meta-math/MetaMathQA
+    metrics:
+    - type: ARC (25-shot)
+      value: 66.89
+      name: ARC (25-shot)
+      verified: true
+    - type: HellaSwag (10-shot)
+      value: 85.26
+      name: HellaSwag (10-shot)
+      verified: true
+    - type: MMLU (5-shot)
+      value: 63.07
+      name: MMLU (5-shot)
+      verified: true
+    - type: TruthfulQA (0-shot)
+      value: 63.01
+      name: TruthfulQA (0-shot)
+      verified: true
+    - type: Winogrande (5-shot)
+      value: 79.64
+      name: Winogrande (5-shot)
+      verified: true
+    - type: GSM8K (5-shot)
+      value: 61.11
+      name: GSM8K (5-shot)
+      verified: true
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 66.89
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 85.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 63.01
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 79.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 61.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
+      name: Open LLM Leaderboard
+---
+
+# newsletter/neural-chat-7b-v3-3-Q6_K-GGUF
+This model was converted to GGUF format from [`Intel/neural-chat-7b-v3-3`](https://huggingface.co/Intel/neural-chat-7b-v3-3) 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/Intel/neural-chat-7b-v3-3) for more details on the model.
+## Use with llama.cpp
+
+Install llama.cpp through brew.
+
+```bash
+brew install ggerganov/ggerganov/llama.cpp
+```
+Invoke the llama.cpp server or the CLI.
+
+CLI:
+
+```bash
+llama-cli --hf-repo newsletter/neural-chat-7b-v3-3-Q6_K-GGUF --model neural-chat-7b-v3-3.Q6_K.gguf -p "The meaning to life and the universe is"
+```
+
+Server:
+
+```bash
+llama-server --hf-repo newsletter/neural-chat-7b-v3-3-Q6_K-GGUF --model neural-chat-7b-v3-3.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.
+
+```
+git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m neural-chat-7b-v3-3.Q6_K.gguf -n 128
+```