|
--- |
|
language: |
|
- en |
|
license: cc-by-nc-4.0 |
|
model_name: Octopus-V4-GGUF |
|
base_model: NexaAIDev/Octopus-v4 |
|
inference: false |
|
model_creator: NexaAIDev |
|
quantized_by: Nexa AI, Inc. |
|
tags: |
|
- function calling |
|
- on-device language model |
|
- gguf |
|
- llama cpp |
|
--- |
|
# Octopus V4-GGUF: Graph of language models |
|
|
|
|
|
<p align="center"> |
|
- <a href="https://huggingface.co/NexaAIDev/Octopus-v4" target="_blank">Original Model</a> |
|
- <a href="https://www.nexa4ai.com/" target="_blank">Nexa AI Website</a> |
|
- <a href="https://github.com/NexaAI/octopus-v4" target="_blank">Octopus-v4 Github</a> |
|
- <a href="https://arxiv.org/abs/2404.19296" target="_blank">ArXiv</a> |
|
- <a href="https://huggingface.co/spaces/NexaAIDev/domain_llm_leaderboard" target="_blank">Domain LLM Leaderbaord</a> |
|
</p> |
|
|
|
<p align="center" width="100%"> |
|
<a><img src="octopus-v4-logo.png" alt="nexa-octopus" style="width: 40%; min-width: 300px; display: block; margin: auto;"></a> |
|
</p> |
|
|
|
**Acknowledgement**: |
|
We sincerely thank our community members, [Mingyuan](https://huggingface.co/ThunderBeee) and [Zoey](https://huggingface.co/ZY6), for their extraordinary contributions to this quantization effort. Please explore [Octopus-v4](https://huggingface.co/NexaAIDev/Octopus-v4) for our original huggingface model. |
|
|
|
## (Recommended) Run with [llama.cpp](https://github.com/ggerganov/llama.cpp) |
|
|
|
1. **Clone and compile:** |
|
|
|
```bash |
|
git clone https://github.com/ggerganov/llama.cpp |
|
cd llama.cpp |
|
# Compile the source code: |
|
make |
|
``` |
|
|
|
2. **Prepare the Input Prompt File:** |
|
|
|
Navigate to the `prompt` folder inside the `llama.cpp`, and create a new file named `chat-with-octopus.txt`. |
|
|
|
`chat-with-octopus.txt`: |
|
|
|
```bash |
|
User: |
|
``` |
|
|
|
3. **Execute the Model:** |
|
|
|
Run the following command in the terminal: |
|
|
|
```bash |
|
./main -m ./path/to/octopus-v4-Q4_K_M.gguf -c 512 -b 2048 -n 256 -t 1 --repeat_penalty 1.0 --top_k 0 --top_p 1.0 --color -i -r "User:" -f prompts/chat-with-octopus.txt |
|
``` |
|
|
|
Example prompt to interact |
|
```bash |
|
<|system|>You are a router. Below is the query from the users, please call the correct function and generate the parameters to call the function.<|end|><|user|>Tell me the result of derivative of x^3 when x is 2?<|end|><|assistant|> |
|
``` |
|
|
|
## Run with [Ollama](https://github.com/ollama/ollama) |
|
1. Create a `Modelfile` in your directory and include a `FROM` statement with the path to your local model: |
|
```bash |
|
FROM ./path/to/octopus-v4-Q4_K_M.gguf |
|
``` |
|
|
|
2. Use the following command to add the model to Ollama: |
|
```bash |
|
ollama create octopus-v4-Q4_K_M -f Modelfile |
|
PARAMETER temperature 0 |
|
PARAMETER num_ctx 1024 |
|
PARAMETER stop <nexa_end> |
|
``` |
|
|
|
3. Verify that the model has been successfully imported: |
|
```bash |
|
ollama ls |
|
``` |
|
|
|
### Run the model |
|
```bash |
|
ollama run octopus-v4-Q4_K_M "<|system|>You are a router. Below is the query from the users, please call the correct function and generate the parameters to call the function.<|end|><|user|>Tell me the result of derivative of x^3 when x is 2?<|end|><|assistant|>" |
|
``` |
|
|
|
### Dataset and Benchmark |
|
|
|
* Utilized questions from [MMLU](https://github.com/hendrycks/test) to evaluate the performances. |
|
* Evaluated with the Ollama [llm-benchmark](https://github.com/MinhNgyuen/llm-benchmark) method. |
|
|
|
|
|
## Quantized GGUF Models |
|
|
|
| Name | Quant method | Bits | Size | Respons (token/second) | Use Cases | |
|
| ---------------------- | ------------ | ---- | ------- | ---------------------- | ----------------------------------------- | |
|
| Octopus-v4.gguf | | | 7.64 GB | 27.64 | extremely large | |
|
| Octopus-v4-Q2_K.gguf | Q2_K | 2 | 1.42 GB | 54.20 | extremely not recommended, high loss | |
|
| Octopus-v4-Q3_K.gguf | Q3_K | 3 | 1.96 GB | 51.22 | not recommended | |
|
| Octopus-v4-Q3_K_S.gguf | Q3_K_S | 3 | 1.68 GB | 51.78 | not very recommended | |
|
| Octopus-v4-Q3_K_M.gguf | Q3_K_M | 3 | 1.96 GB | 50.86 | not very recommended | |
|
| Octopus-v4-Q3_K_L.gguf | Q3_K_L | 3 | 2.09 GB | 50.05 | not very recommended | |
|
| Octopus-v4-Q4_0.gguf | Q4_0 | 4 | 2.18 GB | 65.76 | good quality, recommended | |
|
| Octopus-v4-Q4_1.gguf | Q4_1 | 4 | 2.41 GB | 69.01 | slow, good quality, recommended | |
|
| Octopus-v4-Q4_K.gguf | Q4_K | 4 | 2.39 GB | 55.76 | slow, good quality, recommended | |
|
| Octopus-v4-Q4_K_S.gguf | Q4_K_S | 4 | 2.19 GB | 53.98 | high quality, recommended | |
|
| Octopus-v4-Q4_K_M.gguf | Q4_K_M | 4 | 2.39 GB | 58.39 | some functions loss, not very recommended | |
|
| Octopus-v4-Q5_0.gguf | Q5_0 | 5 | 2.64 GB | 61.98 | slow, good quality | |
|
| Octopus-v4-Q5_1.gguf | Q5_1 | 5 | 2.87 GB | 63.44 | slow, good quality | |
|
| Octopus-v4-Q5_K.gguf | Q5_K | 5 | 2.82 GB | 58.28 | moderate speed, recommended | |
|
| Octopus-v4-Q5_K_S.gguf | Q5_K_S | 5 | 2.64 GB | 59.95 | moderate speed, recommended | |
|
| Octopus-v4-Q5_K_M.gguf | Q5_K_M | 5 | 2.82 GB | 53.31 | fast, good quality, recommended | |
|
| Octopus-v4-Q6_K.gguf | Q6_K | 6 | 3.14 GB | 52.15 | large, not very recommended | |
|
| Octopus-v4-Q8_0.gguf | Q8_0 | 8 | 4.06 GB | 50.10 | very large, good quality | |
|
| Octopus-v4-f16.gguf | f16 | 16 | 7.64 GB | 30.61 | extremely large | |
|
|
|
_Quantized with llama.cpp_ |
