commit 26ded0058cbb55a916ebef7791b5349c085ed1e4 Author: ModelHub XC Date: Wed Jul 15 11:56:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: kd13/Type-o1-mini-instruct Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4088b49 --- /dev/null +++ b/README.md @@ -0,0 +1,116 @@ +--- +license: mit +language: +- en +- hi +base_model: +- meta-llama/Llama-3.2-1B +pipeline_tag: text-generation +library_name: transformers +tags: +- llama +- mini +--- + +# Type-o1-mini-instruct + +A compact general-purpose instruct model designed for everyday assistant use across a wide range of domains — from science and math to writing, coding, language tasks, and tool-style web search workflows. + +The model is intended for lightweight assistant use cases where users need clear, well-structured answers, helpful explanations, and practical support across many subject areas. + +## Capabilities + +This model can help with: + +* General chat and multi-turn conversation +* Biology, chemistry, and physics questions and explanations +* Mathematics and quantitative reasoning +* Engineering concepts and explanations +* Health and medical information (general, non-clinical) +* Python coding assistance and code explanation +* Creative writing (stories, poetry, writing prompts) +* Content generation (marketing copy, social media captions, emails) +* English grammar correction and rewriting +* Advanced NLP tasks: + * Fill-mask + * Table question answering + * Context-based question answering (SQuAD style) + * Summarization (dialogue, news, and scientific papers) +* English ↔ Hindi translation +* School and coursework-level question answering +* Web search tool-call style conversations + +## Chat Format + +The model follows a Harmony-style chat structure. + +Supported interaction flow: + +```text +system -> developer -> user -> tool call -> tool result -> final response +``` + +For normal chat use, you can use a standard chat-template style prompt. + +## Web Search Tool-Call Style + +The model can be used in tool-calling style conversations where the assistant decides when a search is needed, emits a tool call, receives a tool result, and then writes the final answer. + +Example structure: + +```text +system: You are a helpful assistant with access to web search. +user: Find the latest information about a topic. +assistant tool call: web_search(...) +tool result: ... +assistant final: Answer using the search result. +``` + +Actual tool execution depends on your inference framework or application wrapper. + +## Recommended Use Cases + +This model is best suited for: + +* General-purpose lightweight assistants +* Study and homework helpers across science subjects +* Writing and content generation helpers +* Grammar and language correction tools +* English ↔ Hindi translation helpers +* Summarization and document Q&A tools +* Beginner Python learning assistants +* Tool-call research experiments +* Chatbots that need broad domain coverage in a small model + +## Limitations + +This model is not recommended for: + +* Production-critical software generation without review +* Non-Python coding tasks such as C++, Java, Rust, Go, or JavaScript +* Security-sensitive code generation +* Medical, legal, or financial decision-making +* Advanced research-level science or mathematics +* Long multi-file software engineering tasks +* Tasks requiring very long context +* High-stakes factual lookup without verification + +The model may sometimes: + +* Produce incorrect facts or reasoning +* Miss edge cases +* Over-explain simple questions +* Generate code that needs testing +* Struggle with very long context +* Use tool-call format inconsistently depending on the prompt +* Give uneven quality across its many supported domains + +Always verify important outputs and test generated code before using it. + +## License + +Please check the model repository license before commercial or production use. + +## Disclaimer + +This model is an experimental small general-purpose assistant. It should be used as a helpful assistant, not as a guaranteed source of truth. For important tasks, verify outputs with tests, documentation, and human review. \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..5d0e812 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,4 @@ +{% for m in messages %}<|begin_of_text|>{{ m['role'] }} +{{ m['content'] }}<|end_of_text|> +{% endfor %}{% if add_generation_prompt %}<|begin_of_text|>assistant +{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..665517a --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128001, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pad_token_id": 128001, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.6", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..90b2369 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.57.6" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..88c2ed2 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ab2f6a70d8f694cbefdec6d8ecb5f8afd4a7971931d54111c948e71182d4b6c +size 2471645608 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..04829af --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|end_of_text|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..317f802 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "is_local": true, + "local_files_only": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "TokenizersBackend" +}