初始化项目，由ModelHub XC社区提供模型
Model: second-state/Falcon3-7B-Instruct-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
90
README.md
Normal file
90
README.md
Normal file
@@ -0,0 +1,90 @@
|
||||
---
|
||||
base_model: tiiuae/Falcon3-7B-Instruct
|
||||
license: other
|
||||
license_name: falcon-llm-license
|
||||
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
|
||||
model_creator: tiiuae
|
||||
model_name: Falcon3-7B-Instruct
|
||||
quantized_by: Second State Inc.
|
||||
language:
|
||||
- en
|
||||
- fr
|
||||
- es
|
||||
- pt
|
||||
library_name: transformers
|
||||
tags:
|
||||
- falcon3
|
||||
---
|
||||
|
||||
<!-- 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 -->
|
||||
|
||||
# Falcon3-7B-Instruct-GGUF
|
||||
|
||||
## Original Model
|
||||
|
||||
[tiiuae/Falcon3-7B-Instruct](https://huggingface.co/tiiuae/Falcon3-7B-Instruct)
|
||||
|
||||
## Run with LlamaEdge
|
||||
|
||||
- LlamaEdge version: [v0.16.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.0) and above
|
||||
|
||||
- Prompt template
|
||||
|
||||
- Prompt type: `falcon3`
|
||||
|
||||
- Prompt string
|
||||
|
||||
```text
|
||||
<|system|>
|
||||
You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible.
|
||||
<|user|>
|
||||
{user_message}
|
||||
<|assistant|>
|
||||
```
|
||||
|
||||
- Context size: `32000`
|
||||
|
||||
- Run as LlamaEdge service
|
||||
|
||||
```bash
|
||||
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-7B-Instruct-Q5_K_M.gguf \
|
||||
llama-api-server.wasm \
|
||||
--model-name Falcon3-7B-Instruct \
|
||||
--prompt-template falcon3 \
|
||||
--ctx-size 32000
|
||||
```
|
||||
|
||||
- Run as LlamaEdge command app
|
||||
|
||||
```bash
|
||||
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-7B-Instruct-Q5_K_M.gguf \
|
||||
llama-chat.wasm \
|
||||
--prompt-template falcon3 \
|
||||
--ctx-size 32000
|
||||
```
|
||||
|
||||
## Quantized GGUF Models
|
||||
|
||||
| Name | Quant method | Bits | Size | Use case |
|
||||
| ---- | ---- | ---- | ---- | ----- |
|
||||
| [Falcon3-7B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q2_K.gguf) | Q2_K | 2 | 2.89 GB| smallest, significant quality loss - not recommended for most purposes |
|
||||
| [Falcon3-7B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 3.97 GB| small, substantial quality loss |
|
||||
| [Falcon3-7B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 3.69 GB| very small, high quality loss |
|
||||
| [Falcon3-7B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.37 GB| very small, high quality loss |
|
||||
| [Falcon3-7B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 4.30 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
||||
| [Falcon3-7B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.57 GB| medium, balanced quality - recommended |
|
||||
| [Falcon3-7B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.33 GB| small, greater quality loss |
|
||||
| [Falcon3-7B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 5.18 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
||||
| [Falcon3-7B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.32 GB| large, very low quality loss - recommended |
|
||||
| [Falcon3-7B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.18 GB| large, low quality loss - recommended |
|
||||
| [Falcon3-7B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q6_K.gguf) | Q6_K | 6 | 6.12 GB| very large, extremely low quality loss |
|
||||
| [Falcon3-7B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 7.93 GB| very large, extremely low quality loss - not recommended |
|
||||
| [Falcon3-7B-Instruct-f16.gguf](https://huggingface.co/second-state/Falcon3-7B-Instruct-GGUF/blob/main/Falcon3-7B-Instruct-f16.gguf) | f16 | 16 | 14.9 GB| |
|
||||
|
||||
*Quantized with llama.cpp b4381*
|
||||
Reference in New Issue
Block a user