初始化项目，由ModelHub XC社区提供模型

Model: alexsobolev/IcaroLM
Source: Original Platform

.gitattributes

@@ -0,0 +1,55 @@
+*.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
+icaro-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+icaro-f16.gguf filter=lfs diff=lfs merge=lfs -text
+icaro-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+icaro-Q8_K.gguf filter=lfs diff=lfs merge=lfs -text
+icaro-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+icaro-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+assets/icaro.png filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q2_K_IMAT.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q3_K_M_IMAT.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q4_K_M_IMAT.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro.imatrix filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-IQ2_M_IMAT.gguf filter=lfs diff=lfs merge=lfs -text
+GGUF/icaro-IQ3_M_IMAT.gguf filter=lfs diff=lfs merge=lfs -text

GGUF/icaro-IQ2_M_IMAT.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c56b9ce7755fa62a57a6858e2c7652062c5f34a953060930779a5a5752942a3
+size 601052096

GGUF/icaro-IQ3_M_IMAT.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68be85d363cb677177069ce6847a9beafdaa710a0130296a0968631da7051887
+size 776661440

GGUF/icaro-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db014e095ec939e2215d67dc2b66fbc79e37152dc2275cdce622558c27b963c1
+size 676301984

GGUF/icaro-Q2_K_IMAT.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42edbc9ea128abdc29d914020f4b018bf1d7d5058c5d30b725ee32f907fbe93
+size 676302272

GGUF/icaro-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ecbc3577c8df57778aec2cdbded2e287ae8013602e23ce695ff997a026a76e3
+size 880159904

GGUF/icaro-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ad54182828c1841f52142f9ce5bb7cb7dfdc5e1bbf7398f69bb1cdb0609881
+size 824175776

GGUF/icaro-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49b76e84d44bfdb62d6be702cd53d1dfebd76f9759b6136c2d54189cb21b4e5
+size 760941728

GGUF/icaro-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78e95ae5d9e0c1f88e95ab4c6079c32ce00332e93247490dab052a0353c69a3
+size 986045600

GGUF/icaro-Q4_K_M_IMAT.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4381933d84ffb7721478077639f5062c23a9753ed8f14bd0fbbd6059dfc649b
+size 986045888

GGUF/icaro-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5af010382fb357cd84fedbe6c748c0098bc04ad33b9743e1aa113a3f505dddd
+size 940309664

GGUF/icaro-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2ada4abc0f05d92826856dc5cdd941d280430c03bc33058130b7425e555c50
+size 1125047456

GGUF/icaro-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb22b473e2cae853f97b120978c2fbbdb66a64b1545b7a608f8c415980a71184
+size 1098726560

GGUF/icaro-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a33585d016a231452464093d3cffca8a36b05a287f9da5bcc9e75252b7c1ee8
+size 1272736928

GGUF/icaro-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef6a0ff81cf47a790706095514980bd26a4e69ce085da0c3d1bcef6de3e7198
+size 1646570144

GGUF/icaro-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3b84fe8be75a0230fed40545fcfec7c4465d12975351d898dc0e33a7d192f3
+size 3093666464

GGUF/icaro.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c8aa56ed04a664b1fa0437ef7910f13f1bd07aa6c540e8e9462d10cc7563c1
+size 2042232

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+---
+![icaro](https://huggingface.co/alexsobolev/IcaroLM/resolve/main/assets/icaro.jpg)
+
+# IcaroLM
+
+IcaroLM is a fine-tuned and quantized version of Qwen2 1.5B, designed specifically for on-device mobile applications. By leveraging a 1.5B parameter architecture and quantization, the model is approximately **600MB** in size, making it practical for local deployment on smartphones and edge devices without requiring cloud connectivity.
+
+IcaroLM has been fine-tuned for two primary objectives: maintaining emotionally intelligent conversations and executing reliable function calls within a chat flow.
+
+## Key Features
+
+- **Mobile-Ready Footprint:** The quantized model is roughly 600MB, allowing for efficient storage and inference on consumer mobile hardware.
+- **Function Calling:** Explicitly fine-tuned to understand and execute function calls, enabling local task automation and tool use.
+- **Empathetic Chat:** Trained on datasets curated for emotional intelligence, allowing for more natural and supportive interactions compared to base models.
+
+## Use Cases
+
+- **Mobile Assistants:** Local chatbots that can perform actions on the device (via function calling) without sending data to the server.
+- **Emotional Support Apps:** Companion applications requiring a more empathetic and nuanced conversational tone.
+- **Edge Automation:** Task-oriented agents that need to run locally with low latency.
+
+## Prompt format
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+## Function calling example
+```
+<|im_start|>system  
+You are a helpful assistant with access to the following functions. Use them if required -[{ 
+   "name":"get_news", 
+   "description":"Get the latest news.", 
+   "parameters":{ 
+      "type":"object", 
+      "properties":{ 
+         "location":{ 
+            "type":"string", 
+            "description":"The location for which to fetch news" 
+         } 
+      }, 
+      "required":[ 
+         "location" 
+      ] 
+   } 
+}, 
+{ 
+  "name": "get_current_weather", 
+  "description": "Get the current weather", 
+  "parameters": { 
+      "type": "object", 
+      "properties": { 
+          "location": { 
+              "type": "string", 
+              "description": "The city and state, e.g. San Francisco, CA" 
+          }, 
+      }, 
+      "required": ["location"], 
+  }, 
+}]<|im_end|>  
+<|im_start|>user  
+What's the latest news in Samara?<|im_end|>  
+<|im_start|>assistant
+```
+Result:
+```
+<|im_start|>assistant
+<functioncall> {"name": "get_news", "arguments": '{"location": "Samara"}'}  <|im_end|>
+```
+

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|PAD_TOKEN|>": 151646,
+  "<|endoftext|>": 151645,
+  "<|im_end|>": 151643,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "unsloth/Qwen2-1.5b-bnb-4bit",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151646,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "unsloth_version": "2024.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.41.2"
+}

lora/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2-1.5b-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {
+    "loftq_bits": 4,
+    "loftq_iter": 1
+  },
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ce618b74fb93a321f505c284c9d204c83dfd50be440d03d30991d44400cd1f
+size 147770496

lora/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|PAD_TOKEN|>": 151646,
+  "<|endoftext|>": 151645,
+  "<|im_end|>": 151643,
+  "<|im_start|>": 151644
+}

lora/special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

lora/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|PAD_TOKEN|>",
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480320bef779942282a841420690aad346a5548254cdc13f50aafa7974a4f042
+size 3087467144

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|PAD_TOKEN|>",
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}