初始化项目，由ModelHub XC社区提供模型

Model: svc-nai-cci/nanollama-public
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,112 @@
+---
+library_name: transformers
+tags:
+- llama
+- causal-lm
+- text-generation
+- nanollama
+license: apache-2.0
+---
+
+# NanoLlama (Public)
+
+A compact Llama-based language model optimized for efficient inference and deployment. This is the **public** version with open access.
+
+## Model Details
+
+### Model Description
+
+NanoLlama is a small-scale language model based on the Llama architecture, designed for lightweight applications and resource-constrained environments. This model provides a good balance between performance and computational efficiency.
+
+- **Developed by:** svc-nai-cci
+- **Model type:** Causal Language Model
+- **Language(s):** English
+- **License:** Apache 2.0
+- **Finetuned from:** Llama architecture
+- **Access:** Public (Open Access)
+
+### Model Architecture
+
+- **Architecture:** LlamaForCausalLM
+- **Hidden Size:** 4096
+- **Number of Layers:** 4
+- **Number of Attention Heads:** 4
+- **Number of Key-Value Heads:** 2
+- **Vocabulary Size:** 32000
+- **Max Position Embeddings:** 4096
+- **Hidden Activation:** SiLU
+
+## Uses
+
+### Direct Use
+
+This model can be used for:
+- Text generation
+- Conversational AI
+- Code completion
+- Creative writing
+- Question answering
+
+### Downstream Use
+
+The model can be fine-tuned for specific tasks such as:
+- Domain-specific text generation
+- Task-specific instruction following
+- Specialized conversational agents
+
+## How to Get Started with the Model
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load the model and tokenizer
+model_name = "svc-nai-cci/nanollama-public"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Generate text
+input_text = "Hello, how are you?"
+inputs = tokenizer(input_text, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=100, temperature=0.7)
+generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(generated_text)
+```
+
+## Technical Specifications
+
+### Model Architecture and Objective
+
+The model uses the standard Llama architecture with:
+- RMSNorm for layer normalization
+- RoPE (Rotary Position Embedding) for positional encoding
+- SwiGLU activation function
+- Grouped Query Attention (GQA)
+
+### Performance Characteristics
+
+- **Model Size:** Compact design for efficient deployment
+- **Memory Requirements:** Optimized for low-memory environments
+- **Inference Speed:** Fast inference suitable for real-time applications
+
+## Limitations
+
+- Limited context length (4096 tokens)
+- May not perform as well as larger models on complex reasoning tasks
+- Primarily trained/fine-tuned for English text
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{nanollama2024,
+  title={NanoLlama: A Compact Llama-based Language Model},
+  author={svc-nai-cci},
+  year={2024},
+  url={https://huggingface.co/svc-nai-cci/nanollama-public}
+}
+```
+
+## Contact
+
+For questions or issues, please contact: svc-nai-cci

chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% 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 = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.56.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d5026d9952394f3b93230977e09f63674787ee603f29f8d51d97c50a34bd16
+size 1174556976

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}