diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..7fbce576022c6971a7e73030b1f32d59a374153f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text + +*.index.json filter=lfs diff=lfs merge=lfs -text +*.index.json filter=lfs diff=lfs merge=lfs -text diff --git a/5daab62106b72a49/gpqa:diamond|0/e4d6395c589ea279/GENERATIVE.parquet b/5daab62106b72a49/gpqa:diamond|0/e4d6395c589ea279/GENERATIVE.parquet new file mode 100644 index 0000000000000000000000000000000000000000..2b1556ccd4720994594aa4b7633022fde13ce64e --- /dev/null +++ b/5daab62106b72a49/gpqa:diamond|0/e4d6395c589ea279/GENERATIVE.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f44667fce2968c4b3295cccc8c043be1033594801b8c82d011fd1c3392ed4f2 +size 5582871 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..41478957aca7a04b7321022e7d1f73de5badd995 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,103 @@ +[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) }} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- 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 loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + 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 %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{%- 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|>{{- '\n' 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..55ad03e64d372d59edae377780930377345697b2 --- /dev/null +++ b/config.json @@ -0,0 +1,89 @@ +{ + "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, + "quantization_config": { + "config_groups": { + "group_0": { + "format": "nvfp4-pack-quantized", + "input_activations": { + "actorder": null, + "block_structure": null, + "dynamic": "local", + "group_size": 16, + "num_bits": 4, + "observer": "static_minmax", + "observer_kwargs": {}, + "strategy": "tensor_group", + "symmetric": true, + "type": "float" + }, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "actorder": null, + "block_structure": null, + "dynamic": false, + "group_size": 16, + "num_bits": 4, + "observer": "memoryless_minmax", + "observer_kwargs": {}, + "strategy": "tensor_group", + "symmetric": true, + "type": "float" + } + } + }, + "format": "nvfp4-pack-quantized", + "global_compression_ratio": null, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed", + "sparsity_config": {}, + "transform_config": {}, + "version": "0.12.3.dev31+gb019b89" + }, + "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": "4.57.3", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a7958b7d81d1338ae40db2fd0d9d030effc9e41d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "transformers_version": "4.57.3" +} diff --git a/model-00001-of-00041.safetensors b/model-00001-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19474bbf5fe5eebc1ee6c15a4179fa45d95b438d --- /dev/null +++ b/model-00001-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb0c08db2d0122a5298bf7b90551f985f08f99c32b13f6613098d5515904ad0 +size 4998659536 diff --git a/model-00002-of-00041.safetensors b/model-00002-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ea80bba0734001edf3907fb79e6ecc8059d8132 --- /dev/null +++ b/model-00002-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350f7920e6a114c7e5a1ba6f0cde26bc3a33b3625367bdc5115a17a1c5b322be +size 4996788968 diff --git a/model-00003-of-00041.safetensors b/model-00003-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7bc46dc8f6df7750d641456aa52252121e9a63b4 --- /dev/null +++ b/model-00003-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5b6e5b7fcdd74c008d8810ce1286ff1ac0c58c6240fb7ba8dca64643f992f66 +size 4996789328 diff --git a/model-00004-of-00041.safetensors b/model-00004-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f178f24e248f6f76f5055907a2cfc45453be0cc --- /dev/null +++ b/model-00004-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b8a83ebaed2a50a4f0cb852eb28ec51da8b3e64a07d55b855ccea925b89da1 +size 4999948944 diff --git a/model-00005-of-00041.safetensors b/model-00005-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b63c9db83179f7359ea2544bedb6a0809a764cf --- /dev/null +++ b/model-00005-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dbb15f6f5f332b4fd5ef70540812dc03380b7a534ed4ad45a6d075e7d2858cd +size 4996793352 diff --git a/model-00006-of-00041.safetensors b/model-00006-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..243cf19394ba0122b7fddc5163fcd2ee2817c37e --- /dev/null +++ b/model-00006-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a85c6ffe0bf8bc05e7a9793896375c326d547333d351cbd346ea6cb271d4dd4a +size 4996793392 diff --git a/model-00007-of-00041.safetensors b/model-00007-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57c4689f8dbc1d73faa1d671b71c1b4044c3fcd3 --- /dev/null +++ b/model-00007-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e3e9d1ac7b05e0b3dcdce69ff25eb142fb255b4b42d7f79863fec030156062 +size 4996793800 diff --git a/model-00008-of-00041.safetensors b/model-00008-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07a24f82bdee3b617a5ba93f2decf528b15ef2ac --- /dev/null +++ b/model-00008-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cbe0c5ae5f2b9f999272a711263b71ecfcd1b6c4dbf5045ea936d017cad7b95 +size 4999951528 diff --git a/model-00009-of-00041.safetensors b/model-00009-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2daf1d2de846ab806b6065eab5b25c54224d7a94 --- /dev/null +++ b/model-00009-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2debb3311a0d4d2dbd5706c851773d3d1488bf8f046c2a84b40d1c6ff608ded +size 4996793384 diff --git a/model-00010-of-00041.safetensors b/model-00010-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b748f1aaae27b0b412c9a07bc1076cf5829c9d6 --- /dev/null +++ b/model-00010-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:529bbef410d198aba89498c6be5edb32c78c01913e90d5309e3818621ad84098 +size 4996793392 diff --git a/model-00011-of-00041.safetensors b/model-00011-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd0ba1bdbddb2fd0fcc73956b94adbfee7c6ac1b --- /dev/null +++ b/model-00011-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf8c7b8fec1b12819752bc69a44c3231a59a9f75f7023fe862699fa3df43edc0 +size 4996793848 diff --git a/model-00012-of-00041.safetensors b/model-00012-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9395f3e731177d7546afca2a4d1e1aaf1294b47 --- /dev/null +++ b/model-00012-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896b2a5785ab03f046ba3f3cc7991f63a38330a5088b0ccafdf6ba89433f3f6e +size 4999951576 diff --git a/model-00013-of-00041.safetensors b/model-00013-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21ebf4a2a9bb4869569259dc5ae7fe10c5d0976f --- /dev/null +++ b/model-00013-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d557ccb9d987370de1d1020ef171f7cb51599f4a02f2b67a95093c16b6fc4d6 +size 4996793384 diff --git a/model-00014-of-00041.safetensors b/model-00014-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e303cec9ae4f58493b8fd7f903070261bdecda5e --- /dev/null +++ b/model-00014-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfe96b2d69a9143cabe0cad5aaa3e1b111d625a148c5d1f67527cb49db9c24c4 +size 4996793392 diff --git a/model-00015-of-00041.safetensors b/model-00015-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3aca297a372e6ff2868ec43452d6a7c507954bc7 --- /dev/null +++ b/model-00015-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f57eaa30eeaddaa577bb9fe194e56e31b701afd6d04a03ef75169cd26dc278 +size 4996793896 diff --git a/model-00016-of-00041.safetensors b/model-00016-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d5b7f4d5f86d3c327a3786965d1284c3bc928712 --- /dev/null +++ b/model-00016-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4426e0d7f7404d77d25fe9f3567c46cc79c667326e36e8ac96dda4aa732c0f +size 4999951624 diff --git a/model-00017-of-00041.safetensors b/model-00017-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c889f4377a4cad495e33d10ad8bac601de72a2c --- /dev/null +++ b/model-00017-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2cd10de536ab3b957f38108b9b3c3ab3b1d84e96eed4c0c9eba54edc9399ccd +size 4996793384 diff --git a/model-00018-of-00041.safetensors b/model-00018-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d67ebac4e87f7616dfd63463c315417a4453f4c --- /dev/null +++ b/model-00018-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bec4b90eff6649948c9a9e30b5964448ab93a11f60d6916849fe7494b8f6d53 +size 4996793440 diff --git a/model-00019-of-00041.safetensors b/model-00019-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c33e393c731abf41bf39faceb1dd4a6b96ba54a --- /dev/null +++ b/model-00019-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da04f0f290cb0de5226b37e1d87761007a4e9faac6678a1ce31ce25b3352abd2 +size 4996793896 diff --git a/model-00020-of-00041.safetensors b/model-00020-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d614039390ac7a9de3023ef1d6930d3b34cea9bb --- /dev/null +++ b/model-00020-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d8512a9741b5e75b607f99dbf44fd4c8538d4c665f0bcfd983c2e93ab47e2ae +size 4999951648 diff --git a/model-00021-of-00041.safetensors b/model-00021-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b6dc39ede34740969f06a540e583e1e5f38540a8 --- /dev/null +++ b/model-00021-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316eff11e6baf0a892bda206b8a1581a1bc1ce522cd7e576df721aa297638e2d +size 4996793384 diff --git a/model-00022-of-00041.safetensors b/model-00022-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90fa0b71564224e13a8b4d05a57c552fdcebb3ba --- /dev/null +++ b/model-00022-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8108c30af26d40950294733f9f47dd3d00e87e12afd10f9dd763bbcbd501d5 +size 4996793488 diff --git a/model-00023-of-00041.safetensors b/model-00023-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7970d631c9188b19bb474dcd58351767f3696b5b --- /dev/null +++ b/model-00023-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a81f4de602af3091a8bfd3c8b5b5d5fd8fa3fa291f3b1ec5e6f9150230eb12d9 +size 4996793896 diff --git a/model-00024-of-00041.safetensors b/model-00024-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50be95b7a3ec5362197ca4a6270780b2d9a8ac16 --- /dev/null +++ b/model-00024-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93854280e37ffe1254d5f8183d3e1cb0ca3b0a09f419dfb49bd3aadad4a1082 +size 4999951600 diff --git a/model-00025-of-00041.safetensors b/model-00025-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10265cf39c800673b085a08992e07ef0b4f481ff --- /dev/null +++ b/model-00025-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:866f86fd8f907ebc3673f315389f4e58150b5dab47299738e15fc5c1527cbaef +size 4996793384 diff --git a/model-00026-of-00041.safetensors b/model-00026-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90bf9130eb803faebf591fadeffabef8510c73dd --- /dev/null +++ b/model-00026-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7761a4ced316547dc48c925ee055dfecfcfb1893e0134b0bb3773211ff0a784e +size 4996793536 diff --git a/model-00027-of-00041.safetensors b/model-00027-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a88b8585eee1c2f3586b4f02c25391732ca7afd --- /dev/null +++ b/model-00027-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaae89a80ea3723ffb936d14485ead1769d06df19967cc64de469e7e9d885f9a +size 4996793896 diff --git a/model-00028-of-00041.safetensors b/model-00028-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..38aa3ef1fb5c26e69162441d7639f8239d1957f0 --- /dev/null +++ b/model-00028-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02eb68abc986dca9024c73fdade120bd2d5af4e54bbbb8d934aeca01d343b71 +size 4999951552 diff --git a/model-00029-of-00041.safetensors b/model-00029-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..982d03a99ab75898bbb15bad603ac112dbb16262 --- /dev/null +++ b/model-00029-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff953ad380e7ff2fb2d6404d694192b1d38bd0b4a987a18edb743aaca47e9031 +size 4996793384 diff --git a/model-00030-of-00041.safetensors b/model-00030-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2789b628b447759fd17f82cceddcb6a4ef8e2f6 --- /dev/null +++ b/model-00030-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f08fb7e4fc69800fdc81d8b69c4ebc56a1355b8069485904752e36b0049e811d +size 4996793584 diff --git a/model-00031-of-00041.safetensors b/model-00031-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78ec937c63c59d1364f1c7d32334eecc9ad9c34b --- /dev/null +++ b/model-00031-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a64749f01f8407a1cdfda67374bcf020d079ca9982a91b00541ea28943a8c2 +size 4996793896 diff --git a/model-00032-of-00041.safetensors b/model-00032-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..114fff460eae3d9670d84836034535dbbc1611d0 --- /dev/null +++ b/model-00032-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45d0961684160708ccbe0d29572071708792f3a70287e04a029eb5cf920a8e8 +size 4999951536 diff --git a/model-00033-of-00041.safetensors b/model-00033-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b11e5342fcedd4608564a8ab74f7350d0aa56d3c --- /dev/null +++ b/model-00033-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd69c40ff9097240e9a2339dbba8a1c75bd70819a7b3e6210c150cf62ce9057 +size 4996793384 diff --git a/model-00034-of-00041.safetensors b/model-00034-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc9b77610782bbeddb50a5a4e79f493694c3681a --- /dev/null +++ b/model-00034-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c351d8c9e624f017cc57e4907f71e7c6602c423c9c578a58053e7fe24cd45854 +size 4996793632 diff --git a/model-00035-of-00041.safetensors b/model-00035-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..302c199e7bd1c3c02011433c78037b73804f013f --- /dev/null +++ b/model-00035-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ea62f4f760212b2fbedfa141e1c9d173aa27df56e2ca5e68373614a3b0924e +size 4971908776 diff --git a/model-00036-of-00041.safetensors b/model-00036-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8169ae80012006104cf6c7e036c757b349e2bb72 --- /dev/null +++ b/model-00036-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd0e788c2de07d5fabb0e70663dd0b17267cd34b92c0a3cc79667401d0320e28 +size 4998290840 diff --git a/model-00037-of-00041.safetensors b/model-00037-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f631812c9409091bda6ed61d9e7c6a07b1ff226a --- /dev/null +++ b/model-00037-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d50f6455b2061d3cc5e53ea7118175a5b2cbb9065d283bd12ee71d58000afdd1 +size 4996793384 diff --git a/model-00038-of-00041.safetensors b/model-00038-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..517107067a079eb93ee40d478156c76c09ea41cf --- /dev/null +++ b/model-00038-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef8441df081153d56c515cceb6063e662faed94ff93a7d2abd4c1cacc6d5599 +size 4996793656 diff --git a/model-00039-of-00041.safetensors b/model-00039-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28b4a4d67d478aaa88f5c4d50ec556347244c489 --- /dev/null +++ b/model-00039-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b475cfe731a269df654ecbb86e82b683d82f2961704a2f2c78dcae1bfbd12bba +size 4986681784 diff --git a/model-00040-of-00041.safetensors b/model-00040-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..136daf7dc85450cdfc8d98edfbed502db38e7a33 --- /dev/null +++ b/model-00040-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51dd1f4d5ee35272a106a8422f4ccb6af9f134b4d52bd07018dbfa0839c1915a +size 4389190152 diff --git a/model-00041-of-00041.safetensors b/model-00041-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..898ac7fae2f21ce370168e6a67b83112a19b0ce7 --- /dev/null +++ b/model-00041-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ed732a1f52d39814adc6a0b127bad1c816b89d7055fa07b029cba98deba7bf +size 1551892608 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..1fd4ef00163eaa87adfbc27b46e94f7452f1c41a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23836899c31df72cd7283ede47c3930bae0c21649cd1c177d9fceadd7052ffb +size 17418078 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000000000000000000000000000000000000..63021273045d31f35237d83016e28884b1df680f --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,6 @@ +default_stage: + default_modifiers: + QuantizationModifier: + targets: [Linear] + ignore: [lm_head, 're:.*\.mlp\.gate$'] + scheme: NVFP4 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..9028cf84013844f17d7616bdec1d88e977924434 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,40 @@ +{ + "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": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} 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" +}