Hugging Face's logo

nurcunal
/
BEDAI-2.4B

Safetensors
mistral
Model card Files
xet
Community
nurcunal commited on
Commit
5707f35
·
verified ·
1 Parent(s): 073286f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -6,7 +6,7 @@ Fine-tuned Turkish instruct model (law domain) based on `nurcunal/BEDAI-2B`, mer
6
  ```python
7
  from transformers import AutoTokenizer, AutoModelForCausalLM
8
  import torch
9
- m = "nurcunal/BEDAI-2B-Hak"
10
  tok = AutoTokenizer.from_pretrained(m, use_fast=True, trust_remote_code=True)
11
  mdl = AutoModelForCausalLM.from_pretrained(m, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
12
  if tok.pad_token_id is None and tok.eos_token_id is not None:
@@ -180,4 +180,4 @@ model-index:
180
 
181
  > **Notes**
182
  > • QA = mean F1 over **TQuAD (TR)** and **XQuAD (TR)** for this run.
183
- > • Your Hak numbers are from a **quick run (limit=50)**; full CETVEL may differ slightly.
 
6
  ```python
7
  from transformers import AutoTokenizer, AutoModelForCausalLM
8
  import torch
9
+ m = "nurcunal/BEDAI-2.4B"
10
  tok = AutoTokenizer.from_pretrained(m, use_fast=True, trust_remote_code=True)
11
  mdl = AutoModelForCausalLM.from_pretrained(m, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
12
  if tok.pad_token_id is None and tok.eos_token_id is not None:
 
180
 
181
  > **Notes**
182
  > • QA = mean F1 over **TQuAD (TR)** and **XQuAD (TR)** for this run.
183
+