Upload folder using huggingface_hub

chat_template.jinja

@@ -1 +1,15 @@
-{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'assistant' %}{{ '<|bot|>\n' + message['content'] + '<|end|>\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{{ eos_token }}
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

config.json

@@ -5,26 +5,26 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "dtype": "float32",
+  "dtype": "bfloat16",
   "eos_token_id": 2,
-  "head_dim": 128,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 1536,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 2048,
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 12,
-  "num_hidden_layers": 22,
-  "num_key_value_heads": 3,
-  "pad_token_id": 35049,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "transformers_version": "4.57.1",
-  "use_cache": true,
-  "vocab_size": 35054
+  "use_cache": false,
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,9 +1,8 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": [
-    2
-  ],
-  "pad_token_id": 35049,
-  "transformers_version": "4.57.1"
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.57.1",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c707dceda61ef03e5388ff7134711c357b0d210baa4fd73e2414d7fa7478702
-size 2611032480
+oid sha256:ef6ca3e8ffbac339e2a537663a0211d4edcbfc5aa3f53ace6548ef56acf86431
+size 249349768

special_tokens_map.json

@@ -1,27 +1,4 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|bot|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -36,15 +13,8 @@
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "pad_token": {
-    "content": "<pad>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -26,61 +26,15 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "35049": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "35050": {
-      "content": "<mask>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "35051": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "35052": {
-      "content": "<|bot|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "35053": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|user|>",
-    "<|bot|>",
-    "<|end|>"
-  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "legacy": false,
-  "mask_token": "<mask>",
   "model_max_length": 2048,
-  "pad_token": "<pad>",
+  "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",

training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e983df10c34525cce3dc0cf17d479bdd2c05fab074c3bfdd1c30f3e928646f
+size 498770858