初始化项目，由ModelHub XC社区提供模型

Model: qylis/llama3.2-3b-tuned Source: Original Platform
2026-04-13 06:04:56 +08:00
commit 1e92a951d7
8 changed files with 408 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/README.md
+++ 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
+---
+
+<div align="center">
+
+<!-- Qylis Logo / Brand Header -->
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/qylis/llama3.2-3b-tuned/resolve/main/assets/qylis-logo-dark.png">
+  <img alt="Qylis Logo" src="https://huggingface.co/qylis/llama3.2-3b-tuned/resolve/main/assets/qylis-logo.png" width="200"/>
+</picture>
+
+# 🦙 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)
+
+</div>
+
+---
+
+## 📖 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
+
+<div align="center">
+
+**Qylis** is building next-generation AI solutions, from fine-tuned language models to production-ready AI applications.
+
+🌐 [qylis.com](https://qylis.com) &nbsp;|&nbsp; 🤗 [HuggingFace](https://huggingface.co/qylis) &nbsp;|&nbsp; 📧 [Contact Us](mailto:hello@qylis.com)
+
+</div>
+
+---
+
+## 📬 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}}
+}
+```
--- a/chat_template.jinja
+++ 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 %}
--- a/config.json
+++ 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
+}
--- a/generation_config.json
+++ 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"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9527b5d04e7dd14d197fca62ea813f13a97d7a760e3e37973f4371328a75e082
+size 6425529112
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
--- a/tokenizer_config.json
+++ 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"
+}