judotens commited on
Commit
83e4786
·
verified ·
1 Parent(s): f99ed92

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -6,7 +6,7 @@ library_name: flatbuild
6
  tags:
7
  - language-model
8
  - conversational
9
- - transformer
10
  - flatbuild
11
  - flatrun
12
  - trained-from-scratch
@@ -19,9 +19,9 @@ pipeline_tag: text-generation
19
 
20
  # Flatbot-micro-4M
21
 
22
- Flatbot-micro-4M is the flagship demonstration model for **Flatbuild**.
23
 
24
- It is a compact conversational language model trained entirely from scratch using the Flatbuild framework. The goal is not to compete with large language models, but to demonstrate the complete workflow of building a modern transformer—from dataset generation and tokenizer training to model training, checkpoint export, and inference.
25
 
26
  Everything in this repository is produced by Flatbuild without relying on pretrained weights.
27
 
@@ -106,16 +106,16 @@ flatbuild export output/demo_chat/*/checkpoint/final --format gguf --output flat
106
  ```
107
 
108
 
109
- ### Flatrun
110
 
111
  ```bash
112
- pip install flatbuild
113
  flatrun chat --model flatbot-micro-4M.gguf --prompt "Hello!"
114
  ```
115
 
116
  ## Purpose
117
 
118
- Flatbot-4M exists as an end-to-end demonstration of the Flatbuild ecosystem.
119
 
120
  It showcases every stage of training a conversational transformer:
121
 
@@ -131,4 +131,4 @@ The complete pipeline is reproducible on consumer hardware and is intended for l
131
 
132
  ## Limitations
133
 
134
- Flatbot-4M is a small conversational language model trained on a relatively small dataset. It has limited factual knowledge and reasoning ability compared to larger models, and is intended as a demonstration of the complete Flatbuild workflow rather than a production-grade assistant.
 
6
  tags:
7
  - language-model
8
  - conversational
9
+ - flatseek
10
  - flatbuild
11
  - flatrun
12
  - trained-from-scratch
 
19
 
20
  # Flatbot-micro-4M
21
 
22
+ Flatbot-micro-4M is the flagship demonstration model for **Flatseek**.
23
 
24
+ It is a compact conversational language model trained entirely from scratch using the Flatseek framework. The goal is not to compete with large language models, but to demonstrate the complete workflow of building a modern transformer—from dataset generation and tokenizer training to model training, checkpoint export, and inference.
25
 
26
  Everything in this repository is produced by Flatbuild without relying on pretrained weights.
27
 
 
106
  ```
107
 
108
 
109
+ ### Flatrun Inference
110
 
111
  ```bash
112
+ pip install flatrun
113
  flatrun chat --model flatbot-micro-4M.gguf --prompt "Hello!"
114
  ```
115
 
116
  ## Purpose
117
 
118
+ Flatbot-4M exists as an end-to-end demonstration of the Flatseek ecosystem.
119
 
120
  It showcases every stage of training a conversational transformer:
121
 
 
131
 
132
  ## Limitations
133
 
134
+ Flatbot-4M is a small conversational language model trained on a relatively small dataset. It has limited factual knowledge and reasoning ability compared to larger models, and is intended as a demonstration of the complete Flatseek workflow rather than a production-grade assistant.