fix

Fixes these issues:
```
`rope_scaling`'s beta_fast field must be a float, got 32

`rope_scaling`'s beta_slow field must be a float, got 1

ValueError: GenerationConfig is invalid:
- `temperature`: `do_sample` is set to `False`. However, `temperature` is set to `0.6` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
- `top_p`: `do_sample` is set to `False`. However, `top_p` is set to `0.95` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.
If you're using a pretrained model, note that some of these attributes may be set through the model's `generation_config.json` file.
```

config.json

@@ -53,8 +53,8 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "attention_factor": 1.2079441541679836,
-    "beta_fast": 32,
-    "beta_slow": 1,
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
     "factor": 8.0,
     "original_max_position_embeddings": 8192,
     "rope_type": "yarn"

generation_config.json

@@ -1,5 +1,6 @@
 {
   "_from_model_config": true,
+  "do_sample": true,
   "eos_token_id": [
     100265,
     100257