update (#2)

- update model (0bee88ade3883f1ccae50d60e8f847eb7b66147e)

config.json

@@ -26,7 +26,7 @@
   "num_key_value_heads": 4,
   "output_router_logits": false,
   "quantization_config": {
-    "algo_config": null,
+    "algo_config": [],
     "exclude": [
       "model.layers.0.mlp.gate",
       "model.layers.1.mlp.gate",
@@ -126,7 +126,7 @@
     "quant_method": "quark",
     "quant_mode": "eager_mode",
     "softmax_quant_spec": null,
-    "version": "0.10"
+    "version": "0.10+b8ad5c1d29"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
@@ -134,7 +134,7 @@
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.56.2",
+  "transformers_version": "4.57.1",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "4.56.2"
+  "transformers_version": "4.57.1"
 }

special_tokens_map.json

@@ -14,18 +14,6 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:9417dfa2470f086897a0fa5acf4c11e1b05646717bdd7f9d4dc119332c65d421
+size 11422919

tokenizer_config.json

@@ -228,11 +228,12 @@
   ],
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 1010000,
   "pad_token": "<|endoftext|>",
+  "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null