KronQ g128

README.md

@@ -0,0 +1,47 @@
+---
+base_model: meta-llama/Llama-2-13b-hf
+license: llama2
+tags:
+  - kronq
+  - quantization
+  - group-quantization
+  - fake-quant
+  - fp16
+language:
+  - en
+pipeline_tag: text-generation
+---
+# Llama-2-13b — KronQ W3A16 g128 (fake-quant fp16)
+
+> ⚠️ **Fake-quant fp16 checkpoint.** 3-bit group-128 weights stored in **fp16** (KronQ does not pack int3) — **same size as bf16**, for PPL/accuracy reproduction. For deployable low-bit see the W4A16-g128 / W2A16-g128 (packed) repos.
+
+[Llama-2-13b](https://huggingface.co/meta-llama/Llama-2-13b-hf) quantized to 3-bit weights (group 128) with **KronQ**, exported as a standard fp16 model.
+
+## Results (WikiText-2, seqlen 2048)
+
+**Perplexity:** **5.135**
+
+**Zero-shot accuracy:**
+
+| PIQA | HellaSwag | ARC-E | ARC-C | WinoGrande | BoolQ | Average |
+|---|---|---|---|---|---|---|
+| 79.22 | 77.53 | 76.30 | 48.72 | 72.14 | 81.62 | **72.59** |
+
+(lm-evaluation-harness 0-shot.)
+
+## Usage
+
+Loads as a **standard fp16 model** (no KronQ code):
+
+```python
+from transformers import AutoModelForCausalLM
+m = AutoModelForCausalLM.from_pretrained("donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake", torch_dtype="float16", device_map="auto")
+```
+
+## Recipe
+
+Group-128 asymmetric W3, weight-only, `--alpha 0.25`, `--act_order`, BiIP, raw H_G.
+
+## License
+
+Derivative of Llama-2-13b — [llama2 license](https://ai.meta.com/llama/license/).

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cb92e244888cb24f9f961dec774d33c6f6f21b6d094b9522d212abd5adf366
+size 26031771000

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}