Corellios commited on
Commit
2338d04
·
verified ·
1 Parent(s): b3744c9

Update config.json

Browse files

Hi, first, thank you for making this model :)

When using LLM Compressor to quantize in FP8, I got the following error when first loading the model:

> model = AutoModelForCausalLM.from_pretrained(MODEL_ID, dtype=torch.bfloat16, low_cpu_mem_usage=True, device_map="cuda", local_files_only=True)
`rope_scaling`'s beta_fast field must be a float, got 32
`rope_scaling`'s beta_slow field must be a float, got 1

It might be my local environment only (my transformers version is "4.57.3"), but just in case you observe the same.

Files changed (1) hide show
  1. config.json +2 -2
config.json CHANGED
@@ -52,8 +52,8 @@
52
  "rms_norm_eps": 1e-06,
53
  "rope_scaling": {
54
  "attention_factor": 1.2079441541679836,
55
- "beta_fast": 32,
56
- "beta_slow": 1,
57
  "factor": 8.0,
58
  "original_max_position_embeddings": 8192,
59
  "rope_type": "yarn"
 
52
  "rms_norm_eps": 1e-06,
53
  "rope_scaling": {
54
  "attention_factor": 1.2079441541679836,
55
+ "beta_fast": 32.0,
56
+ "beta_slow": 1.0,
57
  "factor": 8.0,
58
  "original_max_position_embeddings": 8192,
59
  "rope_type": "yarn"