Hugging Face's logo

haykgrigorian
/
v2mini-eval2

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
Model card Files
xet
Community
haykgrigorian commited on
Commit
93b6729
·
verified ·
1 Parent(s): b3e44dc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -5
README.md CHANGED
@@ -1,13 +1,14 @@
 
1
  license: mit
 
 
2
  language:
3
  - en
4
  pipeline_tag: text-generation
5
- datasets:
6
- - haykgrigorian/TimeCapsuleLLM-London-1800-1875-v2-15GB
7
- library_name: transformers
8
  ---
9
 
10
- # haykgrigorian/v2mini-eval1: Llama-Architecture 318M Model
 
11
 
12
  ## Model Overview
13
 
@@ -16,7 +17,7 @@ library_name: transformers
16
  | Detail | Value |
17
  | :--- | :--- |
18
  | **Model Architecture** | LlamaForCausalLM (Decoder-Only Transformer) |
19
- | **Parameter Count** | **~215 Million (318M)** |
20
  | **Training Type** | Trained **from Scratch** (10,000 steps) |
21
  | **Tokenizer** | Custom BPE, Vocab Size 32,003 |
22
  | **Sequence Length** | 4096 tokens (4x increase from eval1) |
 
1
+ ---
2
  license: mit
3
+ datasets:
4
+ - haykgrigorian/TimeCapsuleLLM-London-1800-1875-v2-15GB
5
  language:
6
  - en
7
  pipeline_tag: text-generation
 
 
 
8
  ---
9
 
10
+
11
+ # haykgrigorian/v2mini-eval1: Llama-Architecture 215M Model
12
 
13
  ## Model Overview
14
 
 
17
  | Detail | Value |
18
  | :--- | :--- |
19
  | **Model Architecture** | LlamaForCausalLM (Decoder-Only Transformer) |
20
+ | **Parameter Count** | **~215 Million (214.8M)** |
21
  | **Training Type** | Trained **from Scratch** (10,000 steps) |
22
  | **Tokenizer** | Custom BPE, Vocab Size 32,003 |
23
  | **Sequence Length** | 4096 tokens (4x increase from eval1) |