OPEA
/

GGUF
Inference Endpoints
conversational
cicdatopea commited on
Commit
574cfad
·
verified ·
1 Parent(s): c1a45e8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -1
README.md CHANGED
@@ -146,8 +146,22 @@ text="Which number is bigger, 9.11 or 9.8?"
146
 
147
  pip3 install lm-eval==0.4.5
148
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
149
  ```bash
150
- auto-round --model "OPEA/Qwen2.5-7B-Instruct-int4-inc" --eval --eval_bs 16 --tasks leaderboard_ifeval,leaderboard_mmlu_pro,gsm8k,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,cmmlu,ceval-valid
151
  ```
152
 
153
  | Metric | BF16 | INT4 |
 
146
 
147
  pip3 install lm-eval==0.4.5
148
 
149
+ Convert the gguf model to hf model using the command:
150
+ ```python
151
+ from transformers import AutoModelForCausalLM,AutoTokenizer
152
+
153
+ model_id = "OPEA/SmallThinker-3B-Preview-int4-sym-gguf-q4-0-inc"
154
+ filename = "SmallThinker-3B-Preview-3.1B-Q4_0.gguf"
155
+
156
+ tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
157
+ model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)
158
+
159
+ model.save_pretrained("SmallThinker-3B-Preview-w4g32-gguf-q4-0-to-hf")
160
+ tokenizer.save_pretrained("SmallThinker-3B-Preview-w4g32-gguf-q4-0-to-hf")
161
+ ```
162
+
163
  ```bash
164
+ auto-round --model "SmallThinker-3B-Preview-w4g32-gguf-q4-0-to-hf" --eval --eval_bs 16 --tasks leaderboard_ifeval,leaderboard_mmlu_pro,gsm8k,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,cmmlu,mmlu,ceval-valid
165
  ```
166
 
167
  | Metric | BF16 | INT4 |