omaratef3221/Qwen2-0.5B-Instruct-SQL-generator

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: core42/jais-13b
+base_model: Qwen/Qwen2-0.5B-Instruct
 tags:
 - trl
 - sft
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tmp_trainer
 
-This model is a fine-tuned version of [core42/jais-13b](https://huggingface.co/core42/jais-13b) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
 
 ## Model description
 

added_tokens.json

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

config.json

@@ -1,40 +1,28 @@
 {
-  "_name_or_path": "core42/jais-13b",
-  "activation_function": "swiglu",
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
   "architectures": [
-    "JAISLMHeadModel"
+    "Qwen2ForCausalLM"
   ],
-  "attn_pdrop": 0.0,
-  "auto_map": {
-    "AutoConfig": "core42/jais-13b--configuration_jais.JAISConfig",
-    "AutoModel": "core42/jais-13b--modeling_jais.JAISModel",
-    "AutoModelForCausalLM": "core42/jais-13b--modeling_jais.JAISLMHeadModel",
-    "AutoModelForQuestionAnswering": "core42/jais-13b--modeling_jais.JAISForQuestionAnswering",
-    "AutoModelForSequenceClassification": "core42/jais-13b--modeling_jais.JAISForSequenceClassification",
-    "AutoModelForTokenClassification": "core42/jais-13b--modeling_jais.JAISForTokenClassification"
-  },
-  "bos_token_id": 0,
-  "embd_pdrop": 0.0,
-  "embeddings_scale": 14.6,
-  "eos_token_id": 0,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "jais",
-  "n_embd": 5120,
-  "n_head": 40,
-  "n_inner": 13653,
-  "n_layer": 40,
-  "n_positions": 2048,
-  "pad_token_id": 0,
-  "position_embedding_type": "alibi",
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.0,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "scale_qk_dot_by_d": true,
-  "torch_dtype": "bfloat16",
+  "intermediate_size": 4864,
+  "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_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
   "transformers_version": "4.39.0",
   "use_cache": true,
-  "vocab_size": 84992,
-  "width_scale": 0.11100000000000002
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }

generation_config.json

@@ -1,7 +1,14 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
-  "pad_token_id": 0,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "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": "4.39.0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf351b1833c25c3388842a0775b20a0a9c82d61472e13adaa8746d735cd273d1
+size 1976163472

special_tokens_map.json

@@ -1,6 +1,10 @@
 {
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
@@ -12,12 +16,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
   }
 }

tokenizer_config.json

@@ -1,18 +1,43 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
+    "151643": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 2048,
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<|endoftext|>"
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe57307bfab73f687004dcb7d81157d3c8b1fc061ffc6898a77c6d4f2a407c70
+oid sha256:93dc6cf82224c54f7c029286620bc3dc4f96c3b90fb90be1aaf3aa97913ae4af
 size 5112