From fa83380d99e761cd2c06940299c935345979db53 Mon Sep 17 00:00:00 2001
From: potassiummmm <54800242+potassiummmm@users.noreply.github.com>
Date: Thu, 19 Dec 2024 18:32:54 +0800
Subject: [PATCH] Update README.md
---
README.md | 103 +++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 98 insertions(+), 5 deletions(-)
diff --git a/README.md b/README.md
index 8b6fce8..95f6096 100644
--- a/README.md
+++ b/README.md
@@ -88,6 +88,104 @@ This project is based on the [llama.cpp](https://github.com/ggerganov/llama.cpp)
| ✔ |
✘ |
+
+ | Falcon3-1B-Instruct-1.58bit |
+ 1.0B |
+ x86 |
+ ✔ |
+ ✘ |
+ ✔ |
+
+
+ | ARM |
+ ✔ |
+ ✔ |
+ ✘ |
+
+
+ | Falcon3-3B-1.58bit |
+ 3.0B |
+ x86 |
+ ✔ |
+ ✘ |
+ ✔ |
+
+
+ | ARM |
+ ✔ |
+ ✔ |
+ ✘ |
+
+
+ | Falcon3-3B-Instruct-1.58bit |
+ 3.0B |
+ x86 |
+ ✔ |
+ ✘ |
+ ✔ |
+
+
+ | ARM |
+ ✔ |
+ ✔ |
+ ✘ |
+
+
+ | Falcon3-7B-1.58bit |
+ 7.0B |
+ x86 |
+ ✔ |
+ ✘ |
+ ✔ |
+
+
+ | ARM |
+ ✔ |
+ ✔ |
+ ✘ |
+
+
+ | Falcon3-7B-Instruct-1.58bit |
+ 7.0B |
+ x86 |
+ ✔ |
+ ✘ |
+ ✔ |
+
+
+ | ARM |
+ ✔ |
+ ✔ |
+ ✘ |
+
+
+ | Falcon3-10B-1.58bit |
+ 10.0B |
+ x86 |
+ ✔ |
+ ✘ |
+ ✔ |
+
+
+ | ARM |
+ ✔ |
+ ✔ |
+ ✘ |
+
+
+ | Falcon3-10B-Instruct-1.58bit |
+ 10.0B |
+ x86 |
+ ✔ |
+ ✘ |
+ ✔ |
+
+
+ | ARM |
+ ✔ |
+ ✔ |
+ ✘ |
+
@@ -160,11 +258,6 @@ optional arguments:
```bash
# Run inference with the quantized model
python run_inference.py -m models/Falcon3-7B-Instruct-1.58bit/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv
-
-# Output:
-# Daniel went back to the the the garden. Mary travelled to the kitchen. Sandra journeyed to the kitchen. Sandra went to the hallway. John went to the bedroom. Mary went back to the garden. Where is Mary?
-# Answer: Mary is in the garden.
-
```
usage: run_inference.py [-h] [-m MODEL] [-n N_PREDICT] -p PROMPT [-t THREADS] [-c CTX_SIZE] [-temp TEMPERATURE] [-cnv]