From dbebcf5fd69c6a6db46074838bf029bce6ecb1e8 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 14 Sep 2026 22:00:20 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: reallexi/lexi-rm-agent Source: Original Platform --- .gitattributes | 39 ++++++++++++++++++ NOTICE | 6 +++ README.md | 77 ++++++++++++++++++++++++++++++++++++ chat_template.jinja | 54 +++++++++++++++++++++++++ config.json | 57 ++++++++++++++++++++++++++ generation_config.json | 14 +++++++ model.safetensors | 3 ++ reallexi-job-519-f16.gguf | 3 ++ reallexi-job-519-q4_k_m.gguf | 3 ++ reallexi-job-519-q8_0.gguf | 3 ++ reallexi-model.json | 20 ++++++++++ tokenizer.json | 3 ++ tokenizer_config.json | 36 +++++++++++++++++ 13 files changed, 318 insertions(+) create mode 100644 .gitattributes create mode 100644 NOTICE create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 reallexi-job-519-f16.gguf create mode 100644 reallexi-job-519-q4_k_m.gguf create mode 100644 reallexi-job-519-q8_0.gguf create mode 100644 reallexi-model.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..15fa441 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +reallexi-job-519-f16.gguf filter=lfs diff=lfs merge=lfs -text +reallexi-job-519-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +reallexi-job-519-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/NOTICE b/NOTICE new file mode 100644 index 0000000..04009a6 --- /dev/null +++ b/NOTICE @@ -0,0 +1,6 @@ +Copyright (c) 2026 Reallexi LLC. All rights reserved. + +This standalone model was produced by Reallexi LLC AI Model Builder. +Core backlink: https://llm.reallexi.io + +The upstream base model and training datasets retain their own licenses and terms. diff --git a/README.md b/README.md new file mode 100644 index 0000000..fc8002b --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +license: other +license_name: "inherits-base-model-and-dataset-terms" +base_model: "Qwen/Qwen2.5-0.5B-Instruct" +library_name: transformers +pipeline_tag: "text-generation" +tags: +- "ai-model-builder" +- "fine-tuned" +- reallexi +- slm +- "text-generation" +--- + +# reallexi/lexi-rm-agent + +A standalone model of 495M parameters, derived from [`Qwen/Qwen2.5-0.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct). + +The adapter has been merged into the base weights, so no PEFT adapter is needed at runtime. + + +## Size and requirements + +| | | +|---|---| +| Parameters | 495,114,112 (495M) | +| Weights on disk | 953 MB | +| Trained context length | 512 tokens | +| Base model | `Qwen/Qwen2.5-0.5B-Instruct` | + + +Approximate memory to hold the weights. Add context and runtime overhead on top. + +| Precision | Weights | +|---|---| +| FP16 / BF16 | 944 MB | +| 8-bit (Q8_0) | 472 MB | +| 4-bit (Q4_K_M) | 260 MB | + + +## Training + +| | | +|---|---| +| Strategy | slm | +| Adapter | Auto LoRA | +| LoRA rank / alpha | 8 / 16 | +| Dataset | `bitext/Bitext-customer-support-llm-chatbot-training-dataset` | +| Samples learned | 100,000 (through phase 382 of 382) | +| Training steps | 1,250 | +| Epochs | 5 | + + +## Usage + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained("reallexi/lexi-rm-agent") +tokenizer = AutoTokenizer.from_pretrained("reallexi/lexi-rm-agent") +``` + + +## License and attribution + +The effective terms are inherited from the base model and the training data, which are not necessarily the same as this project's own license. Review both before redistributing. + +- Base model: [`Qwen/Qwen2.5-0.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) + +- Training data: `bitext/Bitext-customer-support-llm-chatbot-training-dataset` + + +Copyright (c) 2026 Reallexi LLC. All rights reserved. + + +Produced by Reallexi LLC AI Model Builder from training job #1272. +Core: https://llm.reallexi.io diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..8d2e5a5 --- /dev/null +++ b/config.json @@ -0,0 +1,57 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "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": 21, + "model_type": "qwen2", + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.3.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2550cef --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "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": "5.3.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..23a7422 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d395133074fbe006fa52039a731acfb421dfd38d9f35ccec8027eb227d6c11ae +size 988097536 diff --git a/reallexi-job-519-f16.gguf b/reallexi-job-519-f16.gguf new file mode 100644 index 0000000..5c3bd2c --- /dev/null +++ b/reallexi-job-519-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01ff9e4b563fd68872ba9a6b48ddb3fddb494add7d343a89c3e8ffc4f1c53d35 +size 994156320 diff --git a/reallexi-job-519-q4_k_m.gguf b/reallexi-job-519-q4_k_m.gguf new file mode 100644 index 0000000..7c78e4c --- /dev/null +++ b/reallexi-job-519-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aed03babf0856b0bef89d3109c84210d07edeb375f8aaf6c1f23e6cdf0abcdf +size 397807392 diff --git a/reallexi-job-519-q8_0.gguf b/reallexi-job-519-q8_0.gguf new file mode 100644 index 0000000..42f7c02 --- /dev/null +++ b/reallexi-job-519-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f5c2e8e5584310d36089d5429451bd246fddc271df2f1222c5a429438154c3 +size 531067680 diff --git a/reallexi-model.json b/reallexi-model.json new file mode 100644 index 0000000..3868227 --- /dev/null +++ b/reallexi-model.json @@ -0,0 +1,20 @@ +{ + "schema_version": 1, + "job_id": 1272, + "model_name": "Lexi Resume", + "artifact_type": "standalone_model", + "standalone": true, + "adapter_applied": true, + "source_artifact_type": "lora_adapter", + "base_model_id": "Qwen/Qwen2.5-0.5B-Instruct", + "custom_adapter": null, + "training_strategy": "slm", + "total_parameters": 495114112, + "weight_size_bytes": 988097536, + "trained_samples": 250, + "training_steps": 1250, + "owner": "Reallexi LLC", + "copyright": "Copyright (c) 2026 Reallexi LLC. All rights reserved.", + "core_backlink": "https://llm.reallexi.io", + "created_at": "2026-07-22T15:04:25+00:00" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..bca3bfc --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68f259dbf73263bd208f9e5473dd5ff813f5221466cae69f2100b8714fae7bd9 +size 11421990 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b96795f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,36 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": true, + "max_length": 2048, + "model_max_length": 131072, + "pad_to_multiple_of": null, + "pad_token": "<|endoftext|>", + "pad_token_type_id": 0, + "padding_side": "right", + "split_special_tokens": false, + "stride": 0, + "tokenizer_class": "Qwen2Tokenizer", + "truncation_side": "right", + "truncation_strategy": "longest_first", + "unk_token": null +}