初始化项目，由ModelHub XC社区提供模型

Model: tiiuae/Falcon3-10B-Base-1.58bit-prequantized
Source: Original Platform

.gitattributes

@@ -0,0 +1,50 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,135 @@
+
+---
+library_name: transformers
+tags:
+- bitnet
+- falcon3
+base_model: tiiuae/Falcon3-10B-Base
+license: other 
+license_name: falcon-llm-license 
+license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
+---
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62441d1d9fdefb55a0b7d12c/c-tosr0FvMlKuKQTojx_6.png)
+
+
+#  Table of Contents
+
+0. [TL;DR](#TL;DR)
+1. [Model Details](#model-details)
+2. [Training Details](#training-details)
+3. [Usage](#usage)
+4. [Evaluation](#evaluation)
+5. [Citation](#citation)
+
+
+# TL;DR
+
+# Model Details
+
+This is a 'hacked' version of `tiiuae/Falcon3-10B-Base-1.58bit` where model weight scales have been injected into ternary model weights in order to make the model compatible with fine-tuning
+
+## Model Description
+
+- **Developed by:** [https://www.tii.ae](https://www.tii.ae)
+- **Model type:** Causal decoder-only
+- **Architecture:** Pure-transformer - 1.58bit version
+- **Language(s) (NLP):** Mainly English
+- **License:** TII Falcon License 2.0
+
+# Training details
+
+The model has been trained following the training strategies from the recent [1-bit LLM HF blogpost](https://huggingface.co/blog/1_58_llm_extreme_quantization) and [1-bit LLM paper](https://huggingface.co/papers/2402.17764).
+For more details about the training protocol of this model, please refer to the Falcon-3 technical report, section *Compression*.
+
+
+# Usage
+
+Currently to use this model you can either rely on Hugging Face transformers library or [BitNet](https://github.com/microsoft/BitNet) library. You can also play with the model using the [falcon-1.58bit playground](https://huggingface.co/spaces/tiiuae/falcon3-1.58bit-playground) (only for the 7B instruct version).
+
+## 🤗 transformers
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "tiiuae/Falcon3-10B-Base-1.58bit"
+
+model = AutoModelForCausalLM.from_pretrained(
+  model_id,
+  torch_dtype=torch.bfloat16,
+).to("cuda")
+
+# Perform text generation
+```
+
+## BitNet
+
+```
+git clone https://github.com/microsoft/BitNet && cd BitNet
+pip install -r requirements.txt
+python setup_env.py --hf-repo tiiuae/Falcon3-10B-Base-1.58bit -q i2_s
+python run_inference.py -m models/Falcon3-10B-1.58bit/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv
+```
+
+# Evaluation
+We report in the following table our internal pipeline benchmarks:
+
+**Note evaluation results are normalized score from v2 leaderboard tasks - reported results of original models in the blogpost are raw scores**
+
+<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
+    <colgroup>
+        <col style="width: 10%;">
+        <col style="width: 10%;">
+        <col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
+    </colgroup>
+    <thead>
+        <tr>
+            <th>Benchmark</th>
+            <th>Llama3-8B-1.58-100B-tokens</th>
+            <th>Falcon3-10B-Base-1.58bit</th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td>IFEval</td>
+            <td>17.91</td>
+            <td><b>24.89</b></td>
+        </tr>      
+        <tr>
+            <td>MUSR</td>
+            <td><b>4.87</b></td>
+            <td>4.6</td>
+        </tr>
+        <tr>
+            <td>GPQA</td>
+            <td>1.83</td>
+            <td>1.83</td>
+        </tr>
+        <tr>
+            <td>BBH</td>
+            <td><b>5.36</b></td>
+            <td>4.44</td>
+        </tr>
+        <tr>
+            <td>MMLU-PRO</td>
+            <td><b>2.78</b></td>
+            <td>1.36</td>
+        </tr>      
+        <tr>
+            <td>MATH</td>
+            <td>0.26</td>
+            <td><b>0.48</b></td>
+        </tr>
+        <tr>
+            <td>Average</td>
+            <td>5.5</td>
+            <td><b>6.27</b></td>
+        </tr>          
+    </tbody>
+</table>
+
+# Citation
+
+Coming soon ..

chat_template.jinja

@@ -0,0 +1,90 @@
+{# ================= SYSTEM PROMPT ================= #}
+{%- if messages and messages[0]['role'] == 'system' %}
+    {%- set system_msg = messages[0]['content'] %}
+    {%- set remaining_messages = messages[1:] %}
+{%- elif messages and messages[0]['role'] == 'developer' %}
+    {%- set system_msg = messages[0]['content'] %}
+    {%- set remaining_messages = messages[1:] %}
+{%- else %}
+    {%- set system_msg = "You are Falcon, a helpful AI assistant created by Technology Innovation Institute (TII)." %}
+    {%- set remaining_messages = messages %}
+{%- endif %}
+{%- if tools %}
+<|im_start|>system
+{{ system_msg }}
+# Tools
+You may call one or more functions to assist with the user query.
+<tools>
+{%- for tool in tools %}
+{{ tool | tojson }}
+{%- endfor %}
+</tools>
+<|im_end|>
+{%- else %}
+<|im_start|>system
+{{ system_msg }}
+<|im_end|>
+{%- endif %}
+{# ================= FIND LAST USER QUERY ================= #}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=remaining_messages|length - 1) %}
+{%- for message in remaining_messages %}
+    {%- if message.role == "user" %}
+        {%- set ns.last_query_index = loop.index0 %}
+    {%- endif %}
+{%- endfor %}
+{# ================= RENDER MESSAGES ================= #}
+{%- for message in remaining_messages %}
+    {# ---- Normalize content to string ---- #}
+    {%- set content = message.get('content', '') %}
+    {%- set reasoning_content = message.get('reasoning_content', none) %}
+    {%- if content is string %}
+        {%- set content_str = content %}
+    {%- elif content is not none %}
+        {%- set ns_content = namespace(text='') %}
+        {%- for item in content if item.type == 'text' %}
+            {%- set ns_content.text = ns_content.text ~ item.text %}
+        {%- endfor %}
+        {%- set content_str = ns_content.text %}
+    {%- endif %}
+    {# ================= USER ================= #}
+    {%- if message.role in ['user', 'human'] %}
+
+<|im_start|>user
+{{ content_str }}<|im_end|>
+    {%- elif message.role in ['assistant', 'gpt', 'function_call'] %}
+
+<|im_start|>assistant
+{%- if reasoning_content is string %}
+{{  "\n<think>" ~ reasoning_content ~ "</think>" }}
+{%- endif %}
+
+{{ content_str }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+
+<tool_call>
+{"name": "{{ tool_call.name }}", "arguments": {{ tool_call.arguments if tool_call.arguments is string else (tool_call.arguments | tojson) }}}
+</tool_call>
+            {%- endfor %}
+        {%- endif %}
+<|im_end|>
+    {%- elif message.role == 'tool' %}
+
+<|im_start|>user
+<tool_response>
+{{ content_str }}
+</tool_response><|im_end|>
+    {%- endif %}
+{%- endfor %}
+{# ================= GENERATION PROMPT ================= #}
+{%- if add_generation_prompt %}
+
+<|im_start|>assistant
+{%- if enable_thinking is defined and enable_thinking is false %}
+    {{- "\n<think></think>" }}
+{%- endif %}
+
+{%- endif %}

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 11,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "is_bitnet_config": true,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000042,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.5.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc5e0d178f149b5e4ee0209eb2f627af1f93f2ea8cddb087729371f548cdc89
+size 20611350200

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aba27c4298f23f82157a1ab646db95bec23f6aebcb4056ee323229064fc5591
+size 9781129

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend"
+}