README.md

---
base_model: AdaptLLM/medicine-chat
datasets:
- EleutherAI/pile
- Open-Orca/OpenOrca
- GAIR/lima
- WizardLM/WizardLM_evol_instruct_V2_196k
language:
- en
license: llama2
metrics:
- accuracy
pipeline_tag: text-generation
tags:
- biology
- medical
- llama-cpp
- gguf-my-repo
model-index:
- name: medicine-chat
  results:
  - 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: 53.75
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/medicine-chat
      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: 76.11
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/medicine-chat
      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: 49.98
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/medicine-chat
      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: 43.46
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/medicine-chat
      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: 75.69
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/medicine-chat
      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: 18.95
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/medicine-chat
      name: Open LLM Leaderboard
---

# hellork/medicine-chat-IQ4_NL-GGUF
This model was converted to GGUF format from [`AdaptLLM/medicine-chat`](https://huggingface.co/AdaptLLM/medicine-chat) 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/AdaptLLM/medicine-chat) 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 hellork/medicine-chat-IQ4_NL-GGUF --hf-file medicine-chat-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo hellork/medicine-chat-IQ4_NL-GGUF --hf-file medicine-chat-iq4_nl-imat.gguf -c 2048
```

### The Ship's Computer:

Interact with this model by speaking to it. Lean, fast, & private, networked speech to text, AI images, multi-modal voice chat, control apps, webcam, and sound with less than 4GiB of VRAM.
[whisper_dictation](https://github.com/themanyone/whisper_dictation)

```bash
git clone -b main --single-branch https://github.com/themanyone/whisper_dictation.git
pip install -r whisper_dictation/requirements.txt

git clone https://github.com/ggerganov/whisper.cpp
cd whisper.cpp
GGML_CUDA=1 make -j # assuming CUDA is available. see docs
ln -s server ~/.local/bin/whisper_cpp_server # (just put it somewhere in $PATH)

# -ngl option assums AI accelerator like CUDA is available
llama-server --hf-repo hellork/medicine-chat-IQ4_NL-GGUF --hf-file medicine-chat-iq4_nl-imat.gguf -c 2048 -ngl 17 --port 8888
whisper_cpp_server -l en -m models/ggml-tiny.en.bin --port 7777
cd whisper_dictation
./whisper_cpp_client.py
```
See [the docs](https://github.com/themanyone/whisper_dictation) for tips on integrating with llama.cpp server, enabling the computer to talk back, draw AI images, carry out voice commands, and other features.

### Install Llama.cpp via git:

Note: You can also try this checkpoint with the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo.

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 hellork/medicine-chat-IQ4_NL-GGUF --hf-file medicine-chat-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo hellork/medicine-chat-IQ4_NL-GGUF --hf-file medicine-chat-iq4_nl-imat.gguf -c 2048
```