Add weights

README.md

@@ -1,3 +1,11 @@
 ---
+language:
+- en
 license: mit
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+base_model_relation: quantized
+library_name: mlc-llm
+pipeline_tag: text-generation
 ---
+
+4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) for inference with the [Private LLM](http://privatellm.app) app.

config.json

@@ -0,0 +1,5 @@
+{
+  "quantization_config": {
+        "bits": 4
+    }
+}

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60bad787360d8b80306ba4d6f78398d5737bf1b9b3b843270bc2268a15f5f9e
+size 116686848

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52352b924e3eacc1e8ddf01236ccb90fbea9c2668a835fe6d2a234edafed4edd
+size 116686848

params_shard_10.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ddd78963ddda4f0f900669c5997656882566ed0490694f8ea2c0c39b95ee950
+size 24137728

params_shard_11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98972f8b318330e2956d5a69185bb2668dbe661ab0239be6fca9366d5340a599
+size 24137728

params_shard_12.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea186173c89142c24c32a3ace9bd5c55eb8f1d1f9ffc16dff972dfdb0365c98
+size 24137728

params_shard_13.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f415097b83921aaf26f429026e1b0ebba520eceb3bc591b4d63904db0e81aae5
+size 24137728

params_shard_14.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3f8ff3c21d66fa57e4ced81ebdc9c3469096cb78f9a5a9b46f99f7c26d05bf
+size 24137728

params_shard_15.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3dff0dbb0e45f0bab78f1fb27c3083c07b1734fc73d3c8f9ab94be7c831a67
+size 24137728

params_shard_16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d97a9ead5baa8791337ebf492b43eee2c7e879d18a59e025422d41efce91e41
+size 24137728

params_shard_17.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec70ed8cef7aef68f847ac4263cf788d3d56a96406b5fdbafc93fcda34dc206
+size 24137728

params_shard_18.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ee2815ab3bcbefcc82af77cdd115bbc14fb4ed1221da968c0346bb82f1df36
+size 24137728

params_shard_19.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7ee7977605d261447b45958f56cd99816b34919c07c2b4b04721dd1238e2c9
+size 24137728

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad7a9a4504510810a2563f14963d220fa8c8ddcb091c32851b12479a6aa144d
+size 31433728

params_shard_20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1942307f5577f60f12698577e276c1787f86e0748c18718e70bf8eee6401e383
+size 24137728

params_shard_21.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4811ec0f90fb20162f126dda4ef9bfbdd4f39be958a041b2abbc54c4e322a4c
+size 24137728

params_shard_22.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452bfd3df249085983f981d7f16001c0b8640d22eed651ab93301a94ae73cbef
+size 24137728

params_shard_23.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e742c3dc08d1629420721248e914bd6c67da735427a957463f29cf68c90594
+size 24137728

params_shard_24.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ee26477fcdcae6ffbe1c3c0bc6427e6c35637ead7378f6c28ad65b50ee6b9c
+size 24137728

params_shard_25.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e465a8c446b594c817ef22b4b098d1121b21c00ab38295a47341ddd541d7828e
+size 24137728

params_shard_26.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c401df0bc9ff022a028bc8272de1bc6c0cbf86774a4e6ba8c5f4b965b6cea25
+size 24137728

params_shard_27.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e6a1e2daaa762cbd61ec823d82fa2c266fb69c796c03d676c058fd8da31aeb
+size 24137728

params_shard_28.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221a13a69815402c2ee244e629d5a7d9ca69947b7c6bfe7ca40d5979eb21bd0b
+size 24137728

params_shard_29.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a854b7ea016d3a8918eceea50eaef8aa8e1c28902126e0fd7f549352ce2b6bd0
+size 17041408

params_shard_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b74982a14f684d051e1796d3fd658d8eca99fbff67cd16369bd09d107ebd6eb
+size 31234048

params_shard_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d40ba07eb14ea983ac7ca38d206787fbf812b2be7bbcf6878653bc34c3c3982
+size 24137728

params_shard_5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b9cc40d4c43bbcc0ef2a59bd01b695cc2cf3937809a1520acf821333440a2f
+size 24137728

params_shard_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cbb05346d4cd73e4fec49faa56583d474d9f15422a5bde7f05d439eae68792
+size 24137728

params_shard_7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d960800014ceb8bdb63b787b84d2079c5241d4727867a989ddb10809e420a1
+size 24137728

params_shard_8.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c69ff52531c46533d45ae896ddb6bb6eb9f3bd24b69ff52604b05d6509ec6d
+size 24137728

params_shard_9.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c9086d063f764faea83951fe83a24707d143f34da56888e23ebebec1f17412
+size 24137728

private-llm-config.json

@@ -0,0 +1,45 @@
+{
+  "model_type": "qwen2",
+  "quantization": "GPTQ-Int4",
+  "model_config": {
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 8960,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000,
+    "vocab_size": 151936,
+    "tie_word_embeddings": false,
+    "context_window_size": 8192,
+    "prefill_chunk_size": 128,
+    "tensor_parallel_shards": 1,
+    "head_dim": 128,
+    "dtype": "float32",
+    "max_batch_size": 80
+  },
+  "vocab_size": 151936,
+  "context_window_size": 8192,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 128,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "mean_gen_len": 512,
+  "max_gen_len": 4096,
+  "shift_fill_factor": 0.3,
+  "temperature": 0.7,
+  "presence_penalty": 0.0,
+  "frequency_penalty": 0.0,
+  "repetition_penalty": 1.2,
+  "top_p": 0.95,
+  "conv_template": "deepseek-r1-qwen",
+  "pad_token_id": 0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "tokenizer_files": [
+    "tokenizer.json",
+    "tokenizer_config.json"
+  ],
+  "version": "0.1.0"
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}"
+}