dtrawins commited on
Commit
b419af4
·
verified ·
1 Parent(s): df51751

It looks like there is incorrect limit on the model context length. The fp16 like the original one have 131072 length. Updating this value resolved errors while processing longer prompts.

Browse files
Files changed (1) hide show
  1. config.json +1 -1
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "intermediate_size": 8192,
21
  "interpolate_factor": 1,
22
  "lm_head_bias": false,
23
- "max_position_embeddings": 4096,
24
  "mlp_bias": false,
25
  "model_type": "phi3",
26
  "num_attention_heads": 24,
 
20
  "intermediate_size": 8192,
21
  "interpolate_factor": 1,
22
  "lm_head_bias": false,
23
+ "max_position_embeddings": 131072,
24
  "mlp_bias": false,
25
  "model_type": "phi3",
26
  "num_attention_heads": 24,