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

@@ -34,7 +34,7 @@ This adapter runs entirely on CPU — no GPU required.
 pip install trillim
 trillim pull Trillim/BitNet-TRNQ
 trillim pull Trillim/BitNet-GenZ-LoRA-TRNQ
-trillim chat Trillim/BitNet-TRNQ --lora Trillim/BitNet-GenZ-LoRA-TRNQ
+trillim chat Trillim/BitNet-TRNQ Trillim/BitNet-GenZ-LoRA-TRNQ
 ```
 
 This starts an interactive CLI chat.
@@ -44,11 +44,12 @@ This starts an interactive CLI chat.
 | File | Description |
 |---|---|
 | `qmodel.lora` | Ternary-quantized LoRA weights in Trillim format |
-| `lora_tokenizer.json` | Tokenizer |
-| `lora_tokenizer_config.json` | Tokenizer configuration |
-| `lora_chat_template.jinja` | Chat template |
+| `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 +1,43 @@
+{
+  "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": 16,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "o_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 loop_messages = messages %}{% for message in loop_messages %}{% set content = message['role'] | capitalize + ': '+ message['content'] | trim + '<|eot_id|>' %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}

qmodel.lora

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c46b14bf88f89fdb043f4f365120c392214a9db85f99b2a17a67a650ac3794
+oid sha256:5df6e2bff9167fdea4ac3f4d97c1d88f323ac99074fa6a4390a040a64a6c3882
 size 15974634

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961

tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>"
+}

trillim_config.json

@@ -1,13 +1,14 @@
 {
-    "trillim_version": "0.3.0",
-    "format_version": 3,
-    "type": "lora_adapter",
-    "style": "genz-slang",
-    "description": "LoRA adapter that changes the model style to speak in GenZ slang",
-    "quantization": "ternary",
-    "source_model": "microsoft/bitnet-b1.58-2B-4T-bf16",
-    "base_model_dir": "BitNet",
-    "architecture": "bitnet",
-    "platforms": ["x86_64", "aarch64"],
-    "base_model_config_hash": "46c46efcb3b6ca1e0e6ce2f822cdb6d211b165b4d4f6359b3581ced1616b01ba"
+  "trillim_version": "0.6.0",
+  "format_version": 4,
+  "type": "lora_adapter",
+  "quantization": "ternary",
+  "source_model": "microsoft/bitnet-b1.58-2B-4T-bf16",
+  "architecture": "bitnet",
+  "platforms": [
+    "x86_64",
+    "aarch64"
+  ],
+  "base_model_config_hash": "f70d9d651af0fcf2a7c89c2194160b1139bf77638d0d7bf7f730770984bc2623",
+  "remote_code": false
 }