Upload checkpoint

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -1,4 +1,6 @@
-{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
 ' + message['content'] + '<|im_end|>' + '
 '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
 ' }}{% endif %}

config.json

@@ -1,30 +1,53 @@
 {
   "architectures": [
-    "LlamaForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 64,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 576,
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "max_position_embeddings": 4096,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
-  "pad_token_id": 2,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.53.0.dev0",
   "use_cache": false,
-  "vocab_size": 49152
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }

generation_config.json

@@ -1,9 +1,14 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 1,
+  "bos_token_id": 151643,
   "do_sample": true,
-  "eos_token_id": 2,
-  "max_new_tokens": 40,
-  "pad_token_id": 2,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
   "transformers_version": "4.53.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb544af3eb8a10044aab7260fc00b6be00a445ca67ec52f1e987bf42e46f993
-size 325753976
+oid sha256:108254821a16f93440423d7e1f2dd21fe5d0c85063658ee06c6bc916541becf4
+size 1260455072

special_tokens_map.json

@@ -3,13 +3,6 @@
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "bos_token": {
-    "content": "<|im_start|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "eos_token": {
     "content": "<|im_end|>",
     "lstrip": false,
@@ -18,13 +11,6 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<empty_output>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
+    "151643": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
@@ -9,7 +9,7 @@
       "single_word": false,
       "special": true
     },
-    "1": {
+    "151644": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -17,139 +17,27 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "151645": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "3": {
-      "content": "<repo_name>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<reponame>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<file_sep>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "<filename>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": "<gh_stars>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": "<issue_start>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": "<issue_comment>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": "<issue_closed>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<jupyter_start>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "12": {
-      "content": "<jupyter_text>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "13": {
-      "content": "<jupyter_code>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "14": {
-      "content": "<jupyter_output>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "15": {
-      "content": "<jupyter_script>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "16": {
-      "content": "<empty_output>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "bos_token": "<|im_start|>",
+  "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 2048,
-  "pad_token": "<empty_output>",
-  "padding_side": "left",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>",
-  "vocab_size": 49152
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }