commit 1e92a951d7722567009e3d5db09f990a3216c371 Author: ModelHub XC Date: Mon Apr 13 06:04:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: qylis/llama3.2-3b-tuned 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..15af984 --- /dev/null +++ b/README.md @@ -0,0 +1,207 @@ +--- +language: +- en +- hi +- te +license: llama3.2 +license_link: https://www.llama.com/llama3_2/license/ +base_model: meta-llama/Llama-3.2-3B +tags: +- llama +- llama-3.2 +- fine-tuned +- qylis +- text-generation +- instruction-following +- medical +- finance +- insurance +- biology +- claims +- chemistry +pipeline_tag: text-generation +model_name: qylis/llama3.2-3b-tuned +datasets: +- gbharti/finance-alpaca +- medalpaca/medical_meadow_wikidoc +metrics: +- bleu +library_name: transformers +--- + +
+ + + + + Qylis Logo + + +# 🦙 Qylis / Llama-3.2-3B-Tuned + +**A fine-tuned Llama 3.2 3B model by [Qylis](https://qylis.com)** + +[![Model](https://img.shields.io/badge/Model-Llama%203.2%203B-blue?style=flat-square&logo=meta)](https://huggingface.co/meta-llama/Llama-3.2-3B) +[![Fine-tuned by Qylis](https://img.shields.io/badge/Fine--tuned%20by-Qylis-6C3CE1?style=flat-square)](https://qylis.com) +[![License](https://img.shields.io/badge/License-Llama%203.2-orange?style=flat-square)](https://www.llama.com/llama3_2/license/) +[![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-qylis-yellow?style=flat-square)](https://huggingface.co/qylis) + +
+ +--- + +## 📖 Model Overview + +`qylis/llama3.2-3b-tuned` is a fine-tuned version of Meta's [Llama 3.2 3B](https://huggingface.co/meta-llama/Llama-3.2-3B), developed and maintained by **Qylis**. This model has been adapted for enhanced instruction-following and domain-specific performance, leveraging Qylis's proprietary fine-tuning pipeline. + +| Property | Details | +|---|---| +| **Base Model** | meta-llama/Llama-3.2-3B | +| **Model Type** | Causal Language Model (CLM) | +| **Architecture** | LlamaForCausalLM | +| **Parameters** | ~3 Billion | +| **Fine-tuned by** | Qylis | +| **Language** | English | +| **License** | Llama 3.2 Community License | + +--- + +## 🚀 Quick Start + +### Installation + +```bash +pip install transformers torch accelerate +``` + +### Inference + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_id = "qylis/llama3.2-3b-tuned" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +prompt = "Your prompt here" +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) + +with torch.no_grad(): + outputs = model.generate( + **inputs, + max_new_tokens=512, + temperature=0.7, + top_p=0.9, + do_sample=True, + ) + +response = tokenizer.decode(outputs[0], skip_special_tokens=True) +print(response) +``` + +### Pipeline API + +```python +from transformers import pipeline + +pipe = pipeline( + "text-generation", + model="qylis/llama3.2-3b-tuned", + torch_dtype="auto", + device_map="auto" +) + +result = pipe("Your prompt here", max_new_tokens=256) +print(result[0]["generated_text"]) +``` + +--- + +## 🎯 Intended Use + +This model is intended for: + +- **Instruction following** — Responding to natural language instructions +- **Text generation** — Generating coherent and contextually relevant text +- **Domain-specific tasks** — Applications fine-tuned by Qylis for specific use cases +- **Research and development** — Experimentation with fine-tuned LLMs + +### Out-of-Scope Use + +- Generating harmful, abusive, or misleading content +- High-stakes decision making without human oversight +- Use in applications requiring absolute factual accuracy without verification + +--- + +## 🏋️ Training Details + +| Property | Details | +|---|---| +| **Base Model** | meta-llama/Llama-3.2-3B | +| **Fine-tuning Method** | Supervised Fine-Tuning (SFT) | +| **Fine-tuned by** | Qylis | +| **Framework** | HuggingFace Transformers / PEFT | + +> 📝 Additional training details, dataset information, and hyperparameters will be updated as documentation is finalized. + +--- + +## 📊 Evaluation + +> Benchmark results and evaluation metrics will be published here. Stay tuned for updates from the Qylis team. + +--- + +## ⚠️ Limitations & Bias + +Like all large language models, this model may: + +- **Hallucinate** — Generate plausible-sounding but factually incorrect information +- **Reflect training biases** — Exhibit biases present in the training data +- **Struggle with long contexts** — Performance may degrade with very long inputs +- **Lack real-time knowledge** — No access to information beyond the training cutoff + +Always validate outputs in production settings, especially for critical applications. + +--- + +## 📜 License + +This model is based on **Meta's Llama 3.2** and is subject to the [Llama 3.2 Community License Agreement](https://www.llama.com/llama3_2/license/). By using this model, you agree to the terms of that license. + +> ⚠️ **Naming Requirement:** Per the Llama 3.2 Community License, any fine-tuned model distributed publicly must include **"Llama"** at the beginning of its name (e.g., `Llama-Qylis-3.2-3B-Tuned`). Please ensure your model name on HuggingFace complies with this requirement. + +--- + +## 🤝 About Qylis + +
+ +**Qylis** is building next-generation AI solutions, from fine-tuned language models to production-ready AI applications. + +🌐 [qylis.com](https://qylis.com)  |  🤗 [HuggingFace](https://huggingface.co/qylis)  |  📧 [Contact Us](mailto:hello@qylis.com) + +
+ +--- + +## 📬 Citation + +If you use this model in your research or application, please cite: + +```bibtex +@misc{qylis2024llama32tuned, + title = {Qylis Llama-3.2-3B-Tuned}, + author = {Qylis}, + year = {2024}, + publisher = {HuggingFace}, + howpublished = {\url{https://huggingface.co/qylis/llama3.2-3b-tuned}} +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1bad6a0 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,93 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- if strftime_now is defined %} + {%- set date_string = strftime_now("%d %b %Y") %} + {%- else %} + {%- set date_string = "26 Jul 2024" %} + {%- endif %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {{- "<|eot_id|>" }} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..403ac6d --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": null, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": true, + "transformers_version": "5.4.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d11a68c --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.4.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..174ede7 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9527b5d04e7dd14d197fca62ea813f13a97d7a760e3e37973f4371328a75e082 +size 6425529112 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..360d71a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": true, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}