Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+tags:
+- pruned
+- python
+- optimized
+- wanda
+base_model: LiquidAI/LFM2.5-1.2B-Base
+pipeline_tag: text-generation
+---
+
+# LFM2.5-1.2B-Base-python-safe
+
+> 🎯 **PYTHON-optimized** | 📦 **Safe** pruning | ⚡ **1% weights pruned**
+
+This model is a **conservatively pruned** version of [LiquidAI/LFM2.5-1.2B-Base](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base).
+
+## Performance Comparison
+
+| Category | Original | Pruned | Change |
+|----------|----------|--------|--------|
+| **Python** | 0.0% | 0.0% ⭐ | → |
+| Html | 16.7% | 16.7% | → |
+| Trivia | 91.7% | 91.7% | → |
+| Math | 75.0% | 75.0% | → |
+| Reasoning | 41.7% | 41.7% | → |
+| Medical | 66.7% | 66.7% | → |
+| Linux | 16.7% | 16.7% | → |
+| Writing | 33.3% | 33.3% | → |
+
+**Average**: 42.7% → 42.7% (+0.0%)
+
+
+
+![Comparison Graph](comparison_graph.png)
+
+## Quick Start
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("CompactAI/LFM2.5-1.2B-Base-python-safe")
+tokenizer = AutoTokenizer.from_pretrained("CompactAI/LFM2.5-1.2B-Base-python-safe")
+
+inputs = tokenizer("Your prompt here", return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Technical Details
+
+| Property | Value |
+|----------|-------|
+| Base Model | [LiquidAI/LFM2.5-1.2B-Base](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base) |
+| Specialization | Python |
+| Prune Mode | Safe |
+| Weight Reduction | 1% weights pruned |
+
+## License
+
+This model inherits the license from the base model.

chat_template.jinja

@@ -0,0 +1,7 @@
+{{- bos_token -}}{%- set system_prompt = "" -%}{%- set ns = namespace(system_prompt="") -%}{%- if messages[0]["role"] == "system" -%} {%- set ns.system_prompt = messages[0]["content"] -%} {%- set messages = messages[1:] -%}{%- endif -%}{%- if tools -%} {%- set ns.system_prompt = ns.system_prompt + ("
+" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%} {%- for tool in tools -%} {%- if tool is not string -%} {%- set tool = tool | tojson -%} {%- endif -%} {%- set ns.system_prompt = ns.system_prompt + tool -%} {%- if not loop.last -%} {%- set ns.system_prompt = ns.system_prompt + ", " -%} {%- endif -%} {%- endfor -%} {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}{%- endif -%}{%- if ns.system_prompt -%} {{- "<|im_start|>system
+" + ns.system_prompt + "<|im_end|>
+" -}}{%- endif -%}{%- for message in messages -%} {{- "<|im_start|>" + message["role"] + "
+" -}} {%- set content = message["content"] -%} {%- if content is not string -%} {%- set content = content | tojson -%} {%- endif -%} {%- if message["role"] == "tool" -%} {%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%} {%- endif -%} {{- content + "<|im_end|>
+" -}}{%- endfor -%}{%- if add_generation_prompt -%} {{- "<|im_start|>assistant
+" -}}{%- endif -%}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 2048,
+  "block_ff_dim": 12288,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 2048,
+  "conv_use_xavier_init": true,
+  "dtype": "float16",
+  "eos_token_id": 7,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "tie_embedding": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": true,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": false,
+  "eos_token_id": 7,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22826c95201aa6902b38e9d5bb6c6b774eea300bb8addf312c5a35d0b76bd86e
+size 2340697784

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|pad|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}