Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 lora_tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qmodel.lora filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.trillim-quantize-complete

@@ -0,0 +1 @@
+ready

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+tags:
+  - bitnet
+  - lora
+  - ternary
+  - trillim
+  - cpu-inference
+base_model: microsoft/bitnet-b1.58-2B-4T-bf16
+---
+
+# BitNet-Search-LoRA-TRNQ
+
+Ternary-quantized LoRA adapter for [Trillim/BitNet-TRNQ](https://huggingface.co/Trillim/BitNet-TRNQ) that teaches the model to search. Generates search queries in <search>...</search> XML tags. Need to use Trillim (https://trillim.com) with a search harness to respond to the model's search calls and improve results.
+
+This adapter runs entirely on CPU — no GPU required.
+
+## Adapter Details
+
+| | |
+|---|---|
+| **Type** | LoRA adapter |
+| **Style** | Search tool call |
+| **Architecture** | BitNet (BitNetForCausalLM) |
+| **Quantization** | Ternary ({-1, 0, 1}) |
+| **Platforms** | x86_64, aarch64 |
+| **Base model** | [Trillim/BitNet-TRNQ](https://huggingface.co/Trillim/BitNet-TRNQ) |
+| **Source model** | [microsoft/bitnet-b1.58-2B-4T-bf16](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T-bf16) |
+| **License** | MIT |
+
+## Usage
+
+```bash
+pip install trillim
+trillim pull Trillim/BitNet-TRNQ
+trillim pull Trillim/BitNet-Search-LoRA-TRNQ
+trillim chat Trillim/BitNet-TRNQ Trillim/BitNet-GenZ-LoRA-TRNQ
+```
+
+This starts an interactive CLI chat.
+
+## What's in this repo
+
+| File | Description |
+|---|---|
+| `qmodel.lora` | Ternary-quantized LoRA weights in Trillim format |
+| `tokenizer.json` | Tokenizer |
+| `tokenizer_config.json` | Tokenizer configuration |
+| `chat_template.jinja` | Chat template |
+| `trillim_config.json` | Trillim metadata |
+
+## License
+
+This adapter is released under the [MIT License](https://opensource.org/licenses/MIT), following the license of the source model.
+

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/bitnet-b1.58-2B-4T-bf16",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% set has_system = messages | selectattr('role', 'equalto', 'system') | list | length > 0 %}{% if not has_system %}System: You have access to a search tool. To search the web, write <search>your query</search> and you will receive results. Use search for questions about current events, specific people, places, or facts you are unsure about. Answer directly for math, reasoning, coding, or general knowledge you are confident about.<|eot_id|>{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}System: {{ message['content'] | trim }}<|eot_id|>{% elif message['role'] == 'user' %}User: {{ message['content'] | trim }}<|eot_id|>{% elif message['role'] == 'assistant' %}Assistant: {{ message['content'] | trim }}<|eot_id|>{% elif message['role'] == 'search' %}Search: {{ message['content'] | trim }}<|eot_id|>{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}

qmodel.lora

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc60bb99ae8475d5e3e50b0e5e6ef39d3367750963dfa79c3367f51c1b589557
+oid sha256:9b8afda40ec5631ab6ef56e6d62f700e33a1dfe05488f9afb9c9560be8f01329
 size 86507754

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc5ed64d17c57f61c0ef996ac8b3a8918e7d406866cc4a0292d362a31a217e4
+size 17210125

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>"
+}

trillim_config.json

@@ -1,6 +1,6 @@
 {
-  "trillim_version": "0.3.0",
-  "format_version": 3,
+  "trillim_version": "0.6.0",
+  "format_version": 4,
   "type": "lora_adapter",
   "quantization": "ternary",
   "source_model": "microsoft/bitnet-b1.58-2B-4T-bf16",
@@ -9,5 +9,6 @@
     "x86_64",
     "aarch64"
   ],
-  "base_model_config_hash": "46c46efcb3b6ca1e0e6ce2f822cdb6d211b165b4d4f6359b3581ced1616b01ba"
+  "base_model_config_hash": "f70d9d651af0fcf2a7c89c2194160b1139bf77638d0d7bf7f730770984bc2623",
+  "remote_code": false
 }