初始化项目，由ModelHub XC社区提供模型

Model: axolotl-ai-co/Falcon-E-1.2-3B-Exp-prequantized
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 +1,68 @@
+---
+library_name: transformers
+tags:
+- axolotl
+- edge
+- bitnet
+license: apache-2.0
+---
+
+# Falcon-E-1.2-3B-Exp-prequantized
+
+This is the model card of `Falcon-E-1.2-3B-Exp`, a ternary (1.58bits) language model trained on SFT agentic, and STEM data using [`axolotl`](https://github.com/axolotl-ai-cloud/axolotl) framework combined with [`onebitllm`](https://github.com/tiiuae/onebitllms) library.
+
+The model has been trained starting from [`tiiuae/Falcon-E-3B-Base-prequantized`](https://huggingface.co/tiiuae/Falcon-E-3B-Base-prequantized) checkpoint using full-finetuning for 3 epochs. Below are the hyper-parameters used for fine-tuning:
+
+This model is the prequantized version of [`axolotl-ai-co/Falcon-E-1.2-3B-Exp`](https://huggingface.co/axolotl-ai-co/Falcon-E-1.2-3B-Exp) that can be used for further fine-tuning.
+
+```yaml
+micro_batch_size: 1
+num_epochs: 3
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 8.0e-4
+# adamw hyperparams
+adam_beta1: 0.9
+adam_beta2: 0.95
+warmup_steps: 128
+```
+
+And we used a context parallel size of `8`.
+
+## Usage
+
+The model uses `think` mode by default, this can be disabled and switched to non-thiking mode. You can use the model with different frameworks such as HF `transformers`, `llama.cpp` or `mlx-lm`
+
+### transformers 
+
+```bash
+transformers chat axolotl-ai-co/Falcon-E-1.2-3B-Exp
+```
+
+### llama.cpp
+
+```bash
+# thinking mode
+llama-cli -m axolotl-ai-co/Falcon-E-1.2-3B-Exp-GGUF:TQ2_0 --reasoning-format auto --temp 0.2 -cnv
+
+# non thinking mode
+llama-cli -m axolotl-ai-co/Falcon-E-1.2-3B-Exp-GGUF:TQ2_0 --reasoning-format auto --temp 0.2 -cnv --reasoning-budget 0.0
+```
+
+### mlx-lm
+
+```bash
+mlx_lm.chat axolotl-ai-co/Falcon-E-1.2-3B-Exp --temperature 0.2
+```
+
+## Further fine-tuning the model
+
+You can further fine-tune this model, or the base model using their prequantized version. Refer to the [`axolotl` config](https://github.com/axolotl-ai-cloud/axolotl-ai-co/tree/main/examples/falcon-e/falcon-e-3b-ft.yaml) to get started on fine-tuning these models:
+
+- [Base prequantized model](https://huggingface.co/tiiuae/Falcon-E-3B-Base-prequantized)
+- [`Falcon-E-1.2-3B-Exp` base model](https://huggingface.co/axolotl-ai/Falcon-E-1.2-3B-Exp-prequantized)
+- [`DPO fine-tuning config`](https://github.com/axolotl-ai-cloud/axolotl-ai-co/tree/main/examples/falcon-e/falcon-e-3b-dpo.yaml)
+
+## Aknowledgement
+
+Falcon-E-3B-Chat-Exp models are built using Falcon LLM technology from the [Technology Innovation Institute](https://huggingface.co/tiiuae).

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 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 11,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 13312,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 2,
+  "pad_token_id": 11,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    11
+  ],
+  "pad_token_id": 11,
+  "transformers_version": "5.5.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134cd1320c7cb80e355715f5baf7fb3c6e2172b1936e7654fc6f3b5d4a336c7e
+size 6107206592

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}