diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..aa7aacd0134a92c3c1943fdecc75cd8b7420cce6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,5 @@ 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 +model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..2ab98ef068d62829d17c5ade1827b9f013fa2bbf --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,86 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name}{arg-key-1}{arg-value-1}{arg-key-2}{arg-value-2}...{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%} +{{ '' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '' }} +{%- endif -%} +{%- if content.strip() -%} +{{ content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{- '' + tc.name -}} +{% set _args = tc.arguments %}{% for k, v in _args.items() %}{{ k }}{{ v | tojson(ensure_ascii=False) if v is not string else v }}{% endfor %}{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '' }} +{{- m.content }} +{{- '' }} +{%- else -%} +<|observation|>{% for tr in m.content %} +{{ tr.output if tr.output is defined else tr }}{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|>{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..cc9676ded735fbe80534560afa279b0bd83a21f4 --- /dev/null +++ b/config.json @@ -0,0 +1,77 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 3, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 202752, + "model_type": "glm4_moe", + "moe_intermediate_size": 1536, + "n_group": 1, + "n_routed_experts": 160, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 92, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 2.5, + "tie_word_embeddings": false, + "topk_group": 1, + "transformers_version": "4.57.1", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552, + "quantization_config": { + "config_groups": { + "group_0": { + "input_activations": { + "dynamic": false, + "num_bits": 8, + "type": "float" + }, + "weights": { + "dynamic": false, + "num_bits": 8, + "type": "float" + }, + "targets": [ + "Linear" + ] + } + }, + "ignore": [ + "lm_head", + "model.layers.92*" + ], + "quant_algo": "FP8", + "kv_cache_scheme": { + "dynamic": false, + "num_bits": 8, + "type": "float" + }, + "producer": { + "name": "modelopt", + "version": "0.42.0rc1.dev9+ge53ca61b7" + }, + "quant_method": "modelopt" + } +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f51194759eb31dde6fbc75a28e3fb7036f68161a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "temperature": 1.0, + "transformers_version": "4.56.2" +} diff --git a/hf_quant_config.json b/hf_quant_config.json new file mode 100644 index 0000000000000000000000000000000000000000..6abb3b9d16e3f66cda3eb831c7c7f16f4978896e --- /dev/null +++ b/hf_quant_config.json @@ -0,0 +1,14 @@ +{ + "producer": { + "name": "modelopt", + "version": "0.42.0rc1.dev9+ge53ca61b7" + }, + "quantization": { + "quant_algo": "FP8", + "kv_cache_quant_algo": "FP8", + "exclude_modules": [ + "lm_head", + "model.layers.92*" + ] + } +} \ No newline at end of file diff --git a/model-00001-of-00071.safetensors b/model-00001-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..beab01c5bd8cd75de702017f51984d51e4c92cfc --- /dev/null +++ b/model-00001-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a9fe7e2a9f7ae1423b3c67f1038d4484437628a9df0e85091894b1428966cc0 +size 4999379848 diff --git a/model-00002-of-00071.safetensors b/model-00002-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5acd0cdd79948990c260bd76379e1c070ac64518 --- /dev/null +++ b/model-00002-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4399dba86b3ffbcf79f757eabc381ac08525119ebc31cbb733da44542fcdb12 +size 4998372816 diff --git a/model-00003-of-00071.safetensors b/model-00003-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a4a4454774fc23ca7108d59a7d7d45bdf88bf8b --- /dev/null +++ b/model-00003-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4906e51155ec8aeacd93d6bef0eb7b170fd403cb42fbae1b4d907b098083c1a +size 4994814792 diff --git a/model-00004-of-00071.safetensors b/model-00004-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c3143b18091648031ab2d6830426ecfb44ecbc1 --- /dev/null +++ b/model-00004-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea6fcf69bfe7893f2d72f20524b22829ca7a534a02ee9e1c06f5d49134d1791 +size 4998372416 diff --git a/model-00006-of-00071.safetensors b/model-00006-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6363211d6613bf68e18738c47d534e9be914c3d1 --- /dev/null +++ b/model-00006-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86ed4fd8fc5777b046e58bdeffa91375547ba3f0e275d58fb8b030ab5e16d420 +size 4998372824 diff --git a/model-00007-of-00071.safetensors b/model-00007-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..172d79add7cd76d8d312726afc85423459fabaa6 --- /dev/null +++ b/model-00007-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c762199b9941a2d014ceb111826b9a66aab16217f04f6d8eee3d3b5fa20abd +size 4994816176 diff --git a/model-00010-of-00071.safetensors b/model-00010-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6735eae8e4d2d38330480e4930465a8d6bf18487 --- /dev/null +++ b/model-00010-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e4162684af6e7d33b55fa66fdced487ed64298a4095df4752953b6d7b54c037 +size 4994816648 diff --git a/model-00011-of-00071.safetensors b/model-00011-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d3591d9c43bd7bd45602766bc3dc9d549936af6 --- /dev/null +++ b/model-00011-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266af5abb658587ca21d23f0b50dc6752471d47ed489cda75b4e68849844adc3 +size 4998374232 diff --git a/model-00012-of-00071.safetensors b/model-00012-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c3aab4d0bfe3cc3dce31204a0c3763174246eb0 --- /dev/null +++ b/model-00012-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:883202738bd8fecb14b45512d1446cb40c00f035e17744aede260e52cce028e6 +size 4998374296 diff --git a/model-00014-of-00071.safetensors b/model-00014-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eba9a731122087fd59f24b95386cddfc3dba3cdd --- /dev/null +++ b/model-00014-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0266602d75db7623b31d9b30b1a36a795ce5992fa59e3a43916fb3711dc278 +size 4994816624 diff --git a/model-00015-of-00071.safetensors b/model-00015-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fbe11b97a3e5e17c97d5483a631de182f4c4d1f2 --- /dev/null +++ b/model-00015-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:216561e9da7eee80b5b3c82d78eb1867bb884508892c7bb308b015848a79b88b +size 4998374296 diff --git a/model-00016-of-00071.safetensors b/model-00016-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28911476da69918481dd7ef1557471da38408367 --- /dev/null +++ b/model-00016-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3012980b56037e8e12fed54950a2eb7292ba3a2781eeb8c145e55b4fd634761 +size 4998374352 diff --git a/model-00018-of-00071.safetensors b/model-00018-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82af3acb96347f1edc8853c3e98ed6b6575083a6 --- /dev/null +++ b/model-00018-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29db1d88854a27bc49c66d9c9291d12d34bc0940d9f56c32dd974452ed6a835a +size 4994816584 diff --git a/model-00019-of-00071.safetensors b/model-00019-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7be9aa068e251520881d8ca400e26fa918a8d76 --- /dev/null +++ b/model-00019-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3acb093da248844c1b9c9e7eec982b736bd4e1257ecdf629896dc69aaa0cf2cc +size 4998374296 diff --git a/model-00021-of-00071.safetensors b/model-00021-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..798a1796b988dbea8362d116e5066b55026e9095 --- /dev/null +++ b/model-00021-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf87add52cb1541dffd20ff3344fdd99bf82148afd83487648e189738c3d659 +size 4997437536 diff --git a/model-00022-of-00071.safetensors b/model-00022-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d49d85afb922e49aacb4ab0e27ea924b755a26bc --- /dev/null +++ b/model-00022-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d08374366e5c697acb051012afa496cc9ba94ac1c1537cb2e9ea0a187ca005 +size 4995753328 diff --git a/model-00023-of-00071.safetensors b/model-00023-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8edb7585b27bdd33a010c6c934d7a2f4ea099e3b --- /dev/null +++ b/model-00023-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4473d5c2515c242b9c8de85761e1f5d812e762b00c7453c32d3eb874b2b12412 +size 4998374296 diff --git a/model-00026-of-00071.safetensors b/model-00026-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0971b283b3170fe7ebb63a71c8cd8a5b33e9ad0b --- /dev/null +++ b/model-00026-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7bf1bc4d39100c765a6d0c1d9f9ce98ad48687a37ef448d0710c484e8aaf2e4 +size 4998374296 diff --git a/model-00027-of-00071.safetensors b/model-00027-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c255176bb7416d1061368b037fdc31b547197b3 --- /dev/null +++ b/model-00027-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae074a7acf90cd8c9dc35854f48739c0d740be9f441927926904abe49f72e999 +size 4998374296 diff --git a/model-00028-of-00071.safetensors b/model-00028-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..551b33344ded3d495fcc900c27759e8f04823de8 --- /dev/null +++ b/model-00028-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fceaecdfa64394c356c50647a85b0c8f798ecbc8c014651cbcf658e421c149c7 +size 4998374704 diff --git a/model-00029-of-00071.safetensors b/model-00029-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eed4de23069d4cf384bb0379d2b824e28dfb9633 --- /dev/null +++ b/model-00029-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d64e3e16181650d3f1a46eea53128afd47d0182a88e6e5a79c7500402ed67c1 +size 4994816640 diff --git a/model-00031-of-00071.safetensors b/model-00031-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a8792e95a0dd3f85bb1a42fbb6d0089c198cdb6 --- /dev/null +++ b/model-00031-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c860a25818818aefc4257636bcaaf9692180d378a76216417722edc4185f98c0 +size 4998374416 diff --git a/model-00032-of-00071.safetensors b/model-00032-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23228bb59cb585109461a960e0f9bda3e9c2aa05 --- /dev/null +++ b/model-00032-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cafb9af43f6c4ada1d7c2ee60ca3b605c4813824a679ccf8c55aa972465852f0 +size 4998374704 diff --git a/model-00036-of-00071.safetensors b/model-00036-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..074bac349ea50aedb2b4be15c9831e85aa080b98 --- /dev/null +++ b/model-00036-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a427937253b67463803fd8b30ac7495e6e1c30b371497bdcc8a39bed28628a3e +size 4994816640 diff --git a/model-00038-of-00071.safetensors b/model-00038-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad325ce4fec0b3bfff762aa7241bd01d674a4546 --- /dev/null +++ b/model-00038-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b5402bbdef41082d482f1c7732405960cd439912971e748e2c13bb28ff2fd44 +size 4998374296 diff --git a/model-00039-of-00071.safetensors b/model-00039-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80da221ac1fd4e348285d7a2ffb0dc6210099233 --- /dev/null +++ b/model-00039-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f3ebebbff23b22b6917add391de145f487f2d7dc586e4561119f27b0b20bf8 +size 4998374648 diff --git a/model-00040-of-00071.safetensors b/model-00040-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..168bff72023d11924c6c3233bbebda70d9ce9fc3 --- /dev/null +++ b/model-00040-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae146b2d626da2845b00f9d5f000c01d4696ffccfbec2d76d29a0a9da02641cb +size 4994816624 diff --git a/model-00044-of-00071.safetensors b/model-00044-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acd9db326d97ff2f78c12a5435b3ad35baf6bca8 --- /dev/null +++ b/model-00044-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:002012b1650bbbf60d4fe4751cfa99df40eb4e1a1cbf85517bd0007608d16d87 +size 4994816576 diff --git a/model-00046-of-00071.safetensors b/model-00046-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b355081c2c671870555eca00560de056b4990ae6 --- /dev/null +++ b/model-00046-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e35484cb15b5113f7ff0d5e04fd322b0f0faa525e6f61058d49229020fd463b +size 4998374480 diff --git a/model-00047-of-00071.safetensors b/model-00047-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16ca41fb80353fa9130802adc68d3fdcb89edff0 --- /dev/null +++ b/model-00047-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a97c1f908a8c00eab808d9d0dd09a41939038c67945f360b6d8905f2b06d9f +size 4979088880 diff --git a/model-00048-of-00071.safetensors b/model-00048-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3979f4814be1508f64a15e0e0acbe22ebb258938 --- /dev/null +++ b/model-00048-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe37928357d318e71754917de561c15a0c72dcb1dd9dface0b6f571535b5dc1 +size 4998372632 diff --git a/model-00049-of-00071.safetensors b/model-00049-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a9a13f4233f102d2e543e36bfb5f64b6338cf99d --- /dev/null +++ b/model-00049-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42bd5f042706ad310d6e4526526f89b51f27528538927465247be0bd813caabb +size 4998374296 diff --git a/model-00051-of-00071.safetensors b/model-00051-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1d93819e3cf9d73598e4b51ec6fc4c5f6311884 --- /dev/null +++ b/model-00051-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7169513b1dbb516f8ef2b4bc6c232000f40be01299bc83d8538af21b9b9fb3 +size 4994816600 diff --git a/model-00052-of-00071.safetensors b/model-00052-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f57a4d4d7def269b9ce9d86788e78338fd2af7ac --- /dev/null +++ b/model-00052-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907a3ebf2e569e5a8683a883bd1ac9b158632acfbdad61c4023787d7c6eebe51 +size 4998374296 diff --git a/model-00054-of-00071.safetensors b/model-00054-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e42d3dd413410f0d8f926b7cbde79fbb620f0068 --- /dev/null +++ b/model-00054-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4abeb456d790a1475ea5686a45f2d561e07dabc6c4b1675b089ad7e0128420 +size 4998374704 diff --git a/model-00056-of-00071.safetensors b/model-00056-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0372490b6e6ccde523b9b04cd02c96125d32bc90 --- /dev/null +++ b/model-00056-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22bd5ad18875cde1ca6a121b21841f73ec8fff1bd55e346500065e95089d4fd4 +size 4998374296 diff --git a/model-00059-of-00071.safetensors b/model-00059-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..caa06b652e4a9729585443ff3788e7abf1bf68f7 --- /dev/null +++ b/model-00059-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c8fb4a3d47a93ce939c17c7390a5eb63c6d3e5a5a2a3387509856540aa217c +size 4994816552 diff --git a/model-00062-of-00071.safetensors b/model-00062-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b4c62d95ef1f8911151fe57d0ee64d2c89d5f3a --- /dev/null +++ b/model-00062-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2997a08af88d306c48cf920873b6433f024d22405896db70ca5909e4ce041e57 +size 4994816640 diff --git a/model-00064-of-00071.safetensors b/model-00064-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f523f1fd6cec29b6d6fd3dde691127b563efb88 --- /dev/null +++ b/model-00064-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed2ab2adb49308624499a80f277d544db4a94453de97b1b773ec737b68a78fda +size 4998374296 diff --git a/model-00067-of-00071.safetensors b/model-00067-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18d2f9d765df4001e4591d4090bb3c4141c1bf12 --- /dev/null +++ b/model-00067-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaeaacb52dc313f87381a2a6f32d81d010d0cfd3474bd372fef4ca4216c5b9be +size 4998374296 diff --git a/model-00069-of-00071.safetensors b/model-00069-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d9974e4c5a731c1898ca15056d2dba911817b74 --- /dev/null +++ b/model-00069-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8393832ef0dd10d3b3b84073efb418ae04a0c449a063ba2e0c2b821a8fd4b01e +size 4998374704 diff --git a/model-00071-of-00071.safetensors b/model-00071-of-00071.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aab0e723b86f1bd2eaa71a07268a13630c396ced --- /dev/null +++ b/model-00071-of-00071.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9609ec3031885825c96641830314c5212c6310a55f2f11e63125a6c55d82f5d7 +size 4636515144 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..a9b2c0bd02a89dd20783d92f9ac23b80b5692596 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:067adab1d9864371e6693f328183cd792d07aac46b07731d2aa8d2fcc8e8615f +size 12337281 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..7645faed5973c324a314e6c1157a946a960f284c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|endoftext|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ed3c66baf1ec4de61840b0abf02142687bfed8 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba +size 19970700 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..75e11cfb2e0cc09f19391ec2278b4825a4c3fae9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,325 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizerFast" +}