Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* 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
+dd_metastate_Llm_Token_MatMulNBits_2_0.fconst filter=lfs diff=lfs merge=lfs -text
+dd_metastate_Llm_Token_MatMulNBits_2_0.state filter=lfs diff=lfs merge=lfs -text
+fusion.onnx.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+language:
+- zh
+- en
+tags:
+- glm
+- chatglm
+- thudm
+- ryzenai-npu
+base_model: THUDM/chatglm3-6b
+---
+
+# chatglm3-6b
+- ## Introduction
+  This model was created using Quark Quantization, followed by OGA Model Builder, and finalized with post-processing for NPU deployment.
+- ## Quantization Strategy
+  - AWQ / Group 128 / Asymmetric / BF16 activations / UINT4 weights
+    
+- ## Quick Start
+For quickstart, refer to [Ryzen AI doucmentation](https://ryzenai.docs.amd.com/en/latest/npu_oga.html)
+
+#### Evaluation scores
+The perplexity measurement is run on the wikitext-2-raw-v1 (raw data) dataset provided by Hugging Face. Perplexity score measured for prompt length 2k is 29.81679.
+
+
+
+#### License
+Modifications copyright(c) 2024 Advanced Micro Devices,Inc. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

config.json

@@ -0,0 +1 @@
+{}

dd_metastate_Llm_Token_MatMulNBits_2_0.fconst

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79da7d11205afab207e5a7b12605a10af20feda24d9cc1bb894ee35dfeb09b39
+size 3581932544

dd_metastate_Llm_Token_MatMulNBits_2_0.state

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246c528c0054f87aac805720c64bf39d6e3a93d1190f3ae1f31d654ed891e835
+size 10772385

fusion.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb25f7360f37cf50f4ae3f0c05a20793c13a59ad5091b6b1931c6a4de23e8cf
+size 1529017

fusion.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bde971b3d4e191ef13cc36bd6afd6b426858899473311420ce45a6b333a2ed3
+size 263725056

genai_config.json

@@ -0,0 +1,59 @@
+{
+    "model": {
+        "bos_token_id": 1,
+        "context_length": 4096,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "custom_ops_library": "onnx_custom_ops.dll",
+                "custom_allocator": "ryzen_mm",
+                "external_data_file": "prefill.pb.bin",
+                "config_entries": {
+                    "hybrid_opt_token_backend": "npu",
+                    "max_length_for_kv_cache": "4096",
+                    "hybrid_opt_gpu_jit": "5",
+                    "hybrid_opt_max_seq_length": "4096"
+                },
+                "provider_options": []
+            },
+            "filename": "fusion.onnx",
+            "head_size": 128,
+            "hidden_size": 4096,
+            "inputs": {
+                "input_ids": "input_ids",
+                "attention_mask": "attention_mask",
+                "position_ids": "position_ids",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 32,
+            "num_hidden_layers": 32,
+            "num_key_value_heads": 32
+        },
+        "eos_token_id": 2,
+        "pad_token_id": 0,
+        "type": "llama",
+        "vocab_size": 32000
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": true,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 4096,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": true,
+        "repetition_penalty": 1.0,
+        "temperature": 0.6,
+        "top_k": 50,
+        "top_p": 0.9
+    }
+}

prefill.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1a4a83c1d65da8b0ed1ec8d52032a70440688f3c9237ad4dd9bdc86200ebd6
+size 3604657152

prefill.pb.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6772a01edf1e5551462098378e8c7b75af0088e17b8ebb76eec8ce17fdff5f72
+size 8259

rai_config.json

@@ -0,0 +1,11 @@
+{
+    "max_prompt_length": {
+        "1.3.1": 2048,
+        "1.4.0": 2048,
+        "1.4.1": 2048,
+        "1.5.0": 2048,
+        "1.5.1" : 2048,
+        "1.6.0": 4096
+    }
+
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}