basic-jais-13b-arabic-text-summarizer

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: Omaratef3221/qwen-0.5-rbf-mlp
+license: apache-2.0
+base_model: inceptionai/jais-family-590m-chat
 tags:
 - trl
 - sft
@@ -14,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tmp_trainer
 
-This model is a fine-tuned version of [Omaratef3221/qwen-0.5-rbf-mlp](https://huggingface.co/Omaratef3221/qwen-0.5-rbf-mlp) on an unknown dataset.
+This model is a fine-tuned version of [inceptionai/jais-family-590m-chat](https://huggingface.co/inceptionai/jais-family-590m-chat) on the None dataset.
 
 ## Model description
 
@@ -48,6 +49,6 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - Transformers 4.37.2
-- Pytorch 2.3.1+cu121
-- Datasets 2.12.0
+- Pytorch 2.2.0
+- Datasets 2.21.0
 - Tokenizers 0.15.2

config.json

@@ -1,31 +1,43 @@
 {
-  "_name_or_path": "Omaratef3221/qwen-0.5-rbf-mlp",
+  "_name_or_path": "inceptionai/jais-family-590m-chat",
+  "activation_function": "swiglu",
+  "alibi_scaling": null,
   "architectures": [
-    "CustomQwen2ForCausalLM"
+    "JAISLMHeadModel"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
-  "hidden_size": 896,
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "inceptionai/jais-family-590m-chat--configuration_jais.JAISConfig",
+    "AutoModel": "inceptionai/jais-family-590m-chat--modeling_jais.JAISModel",
+    "AutoModelForCausalLM": "inceptionai/jais-family-590m-chat--modeling_jais.JAISLMHeadModel",
+    "AutoModelForQuestionAnswering": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForQuestionAnswering",
+    "AutoModelForSequenceClassification": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForSequenceClassification",
+    "AutoModelForTokenClassification": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForTokenClassification"
+  },
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 0,
   "initializer_range": 0.02,
-  "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,
-  "rbf_norm_function": "euclidean",
-  "rbf_num_kernels": 100,
-  "rbf_radial_function": "gaussian",
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 1000000.0,
-  "sliding_window": 32768,
-  "tie_word_embeddings": true,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "jais",
+  "mup_embeddings_scale": 9.1705785388303,
+  "mup_output_alpha": 1.09518349815769,
+  "mup_scale_qk_dot_by_d": true,
+  "mup_width_scale": 0.16666666666666666,
+  "n_embd": 1536,
+  "n_head": 12,
+  "n_inner": 4096,
+  "n_layer": 18,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "position_embedding_type": "alibi",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_dim": null,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
   "torch_dtype": "float32",
   "transformers_version": "4.37.2",
   "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 84992
 }

generation_config.json

@@ -1,14 +1,7 @@
 {
-  "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,
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
   "transformers_version": "4.37.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e234b977e2f81ba25c3c05748b240988b6c741553c00551570fadf3d146d78e1
-size 724351912
+oid sha256:31c5ec5092be3872df4db8d595bd0be059ad35eaeb1891e376b77892e704033f
+size 2562246784

special_tokens_map.json

@@ -1,10 +1,13 @@
 {
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
@@ -16,5 +19,12 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
   }
 }

tokenizer_config.json

@@ -1,43 +1,20 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "151643": {
+    "0": {
       "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
     }
   },
-  "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,
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:]  %}{% set system_message = '### Instruction: ' + messages[0]['content'] + '\nComplete the conversation below between [|Human|] and [|AI|]:\n### Input:'%}{% else %}{% set loop_messages = messages %}{% set system_message = '### Instruction: Your name is \\'Jais\\', and you are named after Jebel Jais, the highest mountain in UAE. You were made by \\'Inception\\' in the UAE. You are a helpful, respectful, and honest assistant. Always answer as helpfully as possible, while being safe. Complete the conversation below between [|Human|] and [|AI|]:\n### Input:' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = system_message  %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 0 %}{{ content + ' [|Human|] ' + message['content'] }}{% else %}{{ '\n[|Human|] ' + content.strip() }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '\n[|AI|] '  + content.strip() }}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %} {{'\n[|AI|]\n### Response:'}}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
   "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2437373338b57fc0a580fecc19cc6a5fcdfbc9d9f24192dd532af70314c6ff
+oid sha256:c3c279336da0be4b2e329964f1f1c6d8321dc46c0e81ed5a4fc3d0b110ef8065
 size 4920