115 lines
6.5 KiB
Markdown
115 lines
6.5 KiB
Markdown
---
|
|
base_model: thirdeyeai/Llama-3.2-3B-Instruct-Uncensored
|
|
model_creator: thirdeyeai
|
|
model_name: Llama-3.2-3B-Instruct-Uncensored
|
|
quantized_by: Second State Inc.
|
|
library_name: transformers
|
|
---
|
|
|
|
<!-- header start -->
|
|
<!-- 200823 -->
|
|
<div style="width: auto; margin-left: auto; margin-right: auto">
|
|
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
|
</div>
|
|
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
|
<!-- header end -->
|
|
|
|
# Llama-3.2-3B-Instruct-Uncensored-GGUF
|
|
|
|
## Original Model
|
|
|
|
[thirdeyeai/Llama-3.2-3B-Instruct-Uncensored](https://huggingface.co/thirdeyeai/Llama-3.2-3B-Instruct-Uncensored)
|
|
|
|
## Run with LlamaEdge
|
|
|
|
- LlamaEdge version: [v0.16.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.8) and above
|
|
|
|
- Prompt template
|
|
|
|
- Prompt type for chat: `llama-3-chat`
|
|
|
|
- Prompt string
|
|
|
|
```text
|
|
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
|
|
|
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
|
|
|
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
|
|
|
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
|
|
|
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
|
```
|
|
|
|
- Prompt type for tool use: `llama-3-tool`
|
|
|
|
- Prompt string
|
|
|
|
```text
|
|
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
|
|
|
{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
|
|
|
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
|
|
|
|
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
|
|
|
|
[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]}},"required":["location","unit"]}}}]
|
|
|
|
Question: {user_message}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
|
```
|
|
|
|
- Context size: `128000`
|
|
|
|
- Run as LlamaEdge service
|
|
|
|
- Chat
|
|
|
|
```bash
|
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf \
|
|
llama-api-server.wasm \
|
|
--prompt-template llama-3-chat \
|
|
--ctx-size 128000 \
|
|
--model-name Llama-3.2-3b
|
|
```
|
|
|
|
- Tool use
|
|
|
|
```bash
|
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf \
|
|
llama-api-server.wasm \
|
|
--prompt-template llama-3-tool \
|
|
--ctx-size 128000 \
|
|
--model-name Llama-3.2-3b
|
|
```
|
|
|
|
- Run as LlamaEdge command app
|
|
|
|
```bash
|
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf \
|
|
llama-chat.wasm \
|
|
--prompt-template llama-3-chat \
|
|
--ctx-size 128000
|
|
```
|
|
|
|
## Quantized GGUF Models
|
|
|
|
| Name | Quant method | Bits | Size | Use case |
|
|
| ---- | ---- | ---- | ---- | ----- |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q2_K.gguf) | Q2_K | 2 | 1.49 GB| smallest, significant quality loss - not recommended for most purposes |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q3_K_L.gguf) | Q3_K_L | 3 | 1.98 GB| small, substantial quality loss |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q3_K_M.gguf) | Q3_K_M | 3 | 1.86 GB| very small, high quality loss |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q3_K_S.gguf) | Q3_K_S | 3 | 1.71 GB| very small, high quality loss |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q4_0.gguf) | Q4_0 | 4 | 2.14 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q4_K_M.gguf) | Q4_K_M | 4 | 2.24 GB| medium, balanced quality - recommended |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q4_K_S.gguf) | Q4_K_S | 4 | 2.15 GB| small, greater quality loss |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q5_0.gguf) | Q5_0 | 5 | 2.54 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf) | Q5_K_M | 5 | 2.59 GB| large, very low quality loss - recommended |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q5_K_S.gguf) | Q5_K_S | 5 | 2.54 GB| large, low quality loss - recommended |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q6_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q6_K.gguf) | Q6_K | 6 | 2.97 GB| very large, extremely low quality loss |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-Q8_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q8_0.gguf) | Q8_0 | 8 | 3.84 GB| very large, extremely low quality loss - not recommended |
|
|
| [Llama-3.2-3B-Instruct-Uncensored-f16.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-f16.gguf) | f16 | 16 | 7.22 GB| |
|
|
|
|
*Quantized with llama.cpp b4681*
|