Upload folder using huggingface_hub

README.md

@@ -0,0 +1,105 @@
+---
+license: apache-2.0
+tags:
+- llm
+- tinyllama
+- function-calling
+- cpu-optimized
+- low-resource
+---
+
+# TinyLlama Function Calling (CPU Optimized)
+
+This is a CPU-optimized version of TinyLlama that has been fine-tuned for function calling capabilities.
+
+## Model Details
+
+- **Base Model**: TinyLlama-1.1B-Chat-v1.0
+- **Parameters**: 1.1 billion
+- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
+- **Training Data**: Function calling examples from Glaive Function Calling v2 dataset
+- **Optimization**: Merged LoRA weights, converted to float32 for CPU deployment
+
+## Key Features
+
+1. **Function Calling Capabilities**: The model can identify when functions should be called and generate appropriate function call syntax
+2. **CPU Optimized**: Ready to run efficiently on low-end hardware without GPUs
+3. **Lightweight**: Only 1.1B parameters, making it suitable for older hardware
+4. **Low Resource Requirements**: Requires only 4-6 GB RAM for loading
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the model
+model = AutoModelForCausalLM.from_pretrained("tinyllama-function-calling-cpu-optimized")
+tokenizer = AutoTokenizer.from_pretrained("tinyllama-function-calling-cpu-optimized")
+
+# Example prompt for function calling
+prompt = """### Instruction:
+Given the available functions and the user query, determine which function(s) to call and with what arguments.
+
+Available functions:
+{
+    "name": "get_exchange_rate",
+    "description": "Get the exchange rate between two currencies",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "base_currency": {
+                "type": "string",
+                "description": "The currency to convert from"
+            },
+            "target_currency": {
+                "type": "string",
+                "description": "The currency to convert to"
+            }
+        },
+        "required": [
+            "base_currency",
+            "target_currency"
+        ]
+    }
+}
+
+User query: What is the exchange rate from USD to EUR?
+
+### Response:"""
+
+# Tokenize and generate response
+inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512)
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=150,
+        do_sample=True,
+        temperature=0.7,
+        top_k=50,
+        top_p=0.95
+    )
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
+
+## Performance on Low-End Hardware
+
+The CPU-optimized model requires approximately:
+- 4-6 GB RAM for loading
+- 2-4 CPU cores for inference
+- No GPU required
+
+This makes it suitable for:
+- Older laptops (2018 and newer)
+- Low-end desktops
+- Edge devices with ARM processors
+
+## Training Process
+
+The model was fine-tuned using LoRA (Low-Rank Adaptation) on the Glaive Function Calling v2 dataset. Only a subset of 50 examples was used for demonstration purposes.
+
+## License
+
+This model is licensed under the Apache 2.0 license.

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c815995697257be7a51dc7b41c6eafc6ffe0a37a9a11ac0d864bee27c07e8c7b
+size 4400216536

optimization_info.txt

@@ -0,0 +1,6 @@
+Model optimized for CPU deployment
+==================================
+- Merged LoRA weights with base model
+- Converted to float32 precision
+- Optimized for CPU inference
+- Ready for function calling tasks

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

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": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}