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/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..546a9778d126baf4db24ce51d0d8dcedb1de7ef6 --- /dev/null +++ b/README.md @@ -0,0 +1,141 @@ +--- +datasets: +- abisee/cnn_dailymail +- nvidia/Nemotron-Post-Training-Dataset-v2 +base_model: +- zai-org/GLM-4.7 +base_model_relation: quantized +license: mit +pipeline_tag: text-generation +--- +# GLM-4.7-NVFP4 + +**Format:** NVFP4 — optimal partial quantization of weights & activations to NVFP4. +**Base model:** `zai-org/GLM-4.7` +**How it was made:** [AutoQuantized](https://nvidia.github.io/Model-Optimizer/guides/_pytorch_quantization.html#optimal-partial-quantization-using-auto-quantize) with [NVIDIA Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer/) (NVFP4) with x8 RTX PRO 6000s, using the default calibration mix. ([cnn_dailymail](https://huggingface.co/datasets/abisee/cnn_dailymail) and [nemotron-post-training-dataset-v2](https://huggingface.co/datasets/nvidia/Nemotron-Post-Training-Dataset-v2)) + +Check the [original model card](https://huggingface.co/zai-org/GLM-4.7) for information about this model. + +--- + +### **MMLU Benchmark Results: Salyut1/GLM-4.7-NVFP4** +#### **Summary Table** +| Groups | Version | Metric | Value | Stderr | +| --- | --- | --- | --- | --- | +| **MMLU (Total)** | 2 | acc ↑ | **0.8348** | ± 0.0030 | +| **Social Sciences** | 2 | acc ↑ | **0.9051** | ± 0.0052 | +| **Other** | 2 | acc ↑ | **0.8684** | ± 0.0058 | +| **STEM** | 2 | acc ↑ | **0.8351** | ± 0.0064 | +| **Humanities** | 2 | acc ↑ | **0.7664** | ± 0.0059 | +#### **STEM** +| Tasks | n-shot | Metric | Value | Stderr | +| --- | --- | --- | --- | --- | +| High School Biology | 0 | acc ↑ | 0.9516 | ± 0.0122 | +| College Biology | 0 | acc ↑ | 0.9514 | ± 0.0180 | +| Astronomy | 0 | acc ↑ | 0.9474 | ± 0.0182 | +| High School Computer Science | 0 | acc ↑ | 0.9300 | ± 0.0256 | +| Conceptual Physics | 0 | acc ↑ | 0.9064 | ± 0.0190 | +| Elementary Mathematics | 0 | acc ↑ | 0.8862 | ± 0.0164 | +| Electrical Engineering | 0 | acc ↑ | 0.8690 | ± 0.0281 | +| High School Statistics | 0 | acc ↑ | 0.8565 | ± 0.0239 | +| College Computer Science | 0 | acc ↑ | 0.8400 | ± 0.0368 | +| Anatomy | 0 | acc ↑ | 0.8296 | ± 0.0325 | +| High School Physics | 0 | acc ↑ | 0.7947 | ± 0.0330 | +| High School Chemistry | 0 | acc ↑ | 0.7882 | ± 0.0287 | +| Machine Learning | 0 | acc ↑ | 0.7679 | ± 0.0401 | +| College Physics | 0 | acc ↑ | 0.7647 | ± 0.0422 | +| Abstract Algebra | 0 | acc ↑ | 0.6800 | ± 0.0469 | +| College Chemistry | 0 | acc ↑ | 0.6800 | ± 0.0469 | +| College Mathematics | 0 | acc ↑ | 0.6800 | ± 0.0469 | +| High School Mathematics | 0 | acc ↑ | 0.6481 | ± 0.0291 | +#### **Social Sciences** +| Tasks | n-shot | Metric | Value | Stderr | +| --- | --- | --- | --- | --- | +| High School Government/Politics | 0 | acc ↑ | 0.9793 | ± 0.0103 | +| High School Microeconomics | 0 | acc ↑ | 0.9706 | ± 0.0110 | +| High School Psychology | 0 | acc ↑ | 0.9523 | ± 0.0091 | +| Human Sexuality | 0 | acc ↑ | 0.9313 | ± 0.0222 | +| Sociology | 0 | acc ↑ | 0.9204 | ± 0.0191 | +| High School Geography | 0 | acc ↑ | 0.9192 | ± 0.0194 | +| High School Macroeconomics | 0 | acc ↑ | 0.9000 | ± 0.0152 | +| US Foreign Policy | 0 | acc ↑ | 0.9000 | ± 0.0302 | +| Professional Psychology | 0 | acc ↑ | 0.8725 | ± 0.0135 | +| Security Studies | 0 | acc ↑ | 0.8653 | ± 0.0219 | +| Public Relations | 0 | acc ↑ | 0.7636 | ± 0.0407 | +| Econometrics | 0 | acc ↑ | 0.7544 | ± 0.0405 | +#### **Humanities** +| Tasks | n-shot | Metric | Value | Stderr | +| --- | --- | --- | --- | --- | +| High School US History | 0 | acc ↑ | 0.9461 | ± 0.0159 | +| High School World History | 0 | acc ↑ | 0.9367 | ± 0.0158 | +| World Religions | 0 | acc ↑ | 0.9064 | ± 0.0223 | +| Prehistory | 0 | acc ↑ | 0.8981 | ± 0.0168 | +| International Law | 0 | acc ↑ | 0.8926 | ± 0.0283 | +| Jurisprudence | 0 | acc ↑ | 0.8889 | ± 0.0304 | +| Logical Fallacies | 0 | acc ↑ | 0.8834 | ± 0.0252 | +| High School European History | 0 | acc ↑ | 0.8788 | ± 0.0255 | +| Moral Disputes | 0 | acc ↑ | 0.8699 | ± 0.0181 | +| Philosophy | 0 | acc ↑ | 0.8617 | ± 0.0196 | +| Formal Logic | 0 | acc ↑ | 0.7460 | ± 0.0389 | +| Professional Law | 0 | acc ↑ | 0.6610 | ± 0.0121 | +| Moral Scenarios | 0 | acc ↑ | 0.6425 | ± 0.0160 | +#### **Other** +| Tasks | n-shot | Metric | Value | Stderr | +| --- | --- | --- | --- | --- | +| Medical Genetics | 0 | acc ↑ | 0.9800 | ± 0.0141 | +| Marketing | 0 | acc ↑ | 0.9530 | ± 0.0139 | +| Miscellaneous | 0 | acc ↑ | 0.9374 | ± 0.0087 | +| Professional Medicine | 0 | acc ↑ | 0.9301 | ± 0.0155 | +| Clinical Knowledge | 0 | acc ↑ | 0.9057 | ± 0.0180 | +| Nutrition | 0 | acc ↑ | 0.9052 | ± 0.0168 | +| Management | 0 | acc ↑ | 0.8932 | ± 0.0306 | +| Business Ethics | 0 | acc ↑ | 0.8600 | ± 0.0349 | +| Computer Security | 0 | acc ↑ | 0.8600 | ± 0.0349 | +| Human Aging | 0 | acc ↑ | 0.8161 | ± 0.0260 | +| College Medicine | 0 | acc ↑ | 0.7977 | ± 0.0306 | +| Professional Accounting | 0 | acc ↑ | 0.7624 | ± 0.0254 | +| Global Facts | 0 | acc ↑ | 0.6500 | ± 0.0479 | +| Virology | 0 | acc ↑ | 0.5723 | ± 0.0385 | + +--- + +vLLM Inference Note: + +I needed to patch `vllm/model_executor/models/glm4_moe.py` to skip specific k_scale and v_scale parameters if they are missing from the checkpoint, rather than crashing. The below script fixed my k_scale and v_scale errors. +```python +import sys +import os +import re + +# Path to the vLLM model file +path = '/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/glm4_moe.py' + +if os.path.exists(path): + with open(path, 'r') as f: + lines = f.readlines() + + target_str = 'param = params_dict[name]' + new_lines = [] + patched = False + + for line in lines: + # We look for the parameter loading line + if target_str in line and 'k_scale' not in line: + whitespace = re.match(r'^(\s*)', line).group(1) + + # Inject logic: If asking for k_scale/v_scale and it's missing, skip + payload = f"{whitespace}if ('k_scale' in name or 'v_scale' in name) and name not in params_dict: continue\n" + + new_lines.append(payload) + new_lines.append(line) + patched = True + else: + new_lines.append(line) + + if patched: + with open(path, 'w') as f: + f.writelines(new_lines) + print(f"Successfully patched {path}") + else: + print("File already patched or target not found.") +``` \ No newline at end of file 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..2e2d3b72580c6b31253a20c6b9460b107cb7516c --- /dev/null +++ b/config.json @@ -0,0 +1,78 @@ +{ + "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": "4.57.3", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552, + "quantization_config": { + "config_groups": { + "group_0": { + "input_activations": { + "dynamic": false, + "num_bits": 4, + "type": "float", + "group_size": 16 + }, + "weights": { + "dynamic": false, + "num_bits": 4, + "type": "float", + "group_size": 16 + }, + "targets": [ + "Linear" + ] + } + }, + "ignore": [ + "lm_head" + ], + "quant_algo": "NVFP4", + "kv_cache_scheme": { + "dynamic": false, + "num_bits": 8, + "type": "float" + }, + "producer": { + "name": "modelopt", + "version": "0.40.0" + }, + "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..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/hf_quant_config.json b/hf_quant_config.json new file mode 100644 index 0000000000000000000000000000000000000000..6fbebce87675e7999652e01993d89d5f271a3ccd --- /dev/null +++ b/hf_quant_config.json @@ -0,0 +1,14 @@ +{ + "producer": { + "name": "modelopt", + "version": "0.40.0" + }, + "quantization": { + "quant_algo": "NVFP4", + "kv_cache_quant_algo": "FP8", + "group_size": 16, + "exclude_modules": [ + "lm_head" + ] + } +} \ No newline at end of file diff --git a/model-00001-of-00041.safetensors b/model-00001-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4718ec38ca599431da67a6e24bed2eea912a6870 --- /dev/null +++ b/model-00001-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecdd1683256b7b40ff3fc6706a8d64679c817954a3f28c6376dd44a8bf2bde02 +size 4998646904 diff --git a/model-00002-of-00041.safetensors b/model-00002-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c84f02cfb8d0a38ff160403f37e1c54aa46c7663 --- /dev/null +++ b/model-00002-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7332ecbba03b1d3e2ed5867cb3feec8512e001801cfffa0ef18c2c2ac31f39e4 +size 4996766232 diff --git a/model-00003-of-00041.safetensors b/model-00003-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae11d31f35449b29df8391675d0fdb863f7b9b08 --- /dev/null +++ b/model-00003-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1378802395eb36a726535689b1cd969a3c32d678312444330b20f05b9c9aceb7 +size 4996766592 diff --git a/model-00004-of-00041.safetensors b/model-00004-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..987f9566942a17501917865c3d626f7680a28f52 --- /dev/null +++ b/model-00004-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6ad22ee2096c223dea8f29962a5f3c19955875d413f1b49b94a80cdaf38b44 +size 4999926688 diff --git a/model-00005-of-00041.safetensors b/model-00005-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5aec113200eee5af2fbc7e907bd2f62e7c42d01 --- /dev/null +++ b/model-00005-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0681ab255b7fc4d7af2a8ceea54a07efa2e222ebdcde964755427f644cf5f987 +size 4996770616 diff --git a/model-00006-of-00041.safetensors b/model-00006-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f228631f15386785d4c0af47c671ae82e19fb3a --- /dev/null +++ b/model-00006-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d1ecb6cda3dbb313048ad88809ddf0e293aead5e4989e2d0db55d870ed347e +size 4996770664 diff --git a/model-00007-of-00041.safetensors b/model-00007-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a619fc75103cd47bf15a7d453975f0e59a3587a2 --- /dev/null +++ b/model-00007-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7c8710d3d2cc45b99cf9c42543cb3801f8a57b85936a78e0da10c12645c182 +size 4996771072 diff --git a/model-00008-of-00041.safetensors b/model-00008-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a928c6ffc11f5eca4a8c69faef309fa083ce8ba --- /dev/null +++ b/model-00008-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca67b7ac1b34fc58f01da2fa9b9c09011ec88a95e616e49c51e29999dac6df5 +size 4999929272 diff --git a/model-00009-of-00041.safetensors b/model-00009-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20cd0720a3852cd886ac502670ea3706cd9b89f2 --- /dev/null +++ b/model-00009-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa844a2f98c79aff09b261e9172ef92f371af0279a38fa7be27b6bf40b0627eb +size 4996770656 diff --git a/model-00010-of-00041.safetensors b/model-00010-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0897cbf4504e4386ce2fd03a0a7bf7279309b9a --- /dev/null +++ b/model-00010-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f5c230500588c7909a88aa9228a0a8105fb259b221d8579e54b70808c3d61cb +size 4996770664 diff --git a/model-00011-of-00041.safetensors b/model-00011-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ad31aa45376fdb75b38b7899b1501ea325dfb88 --- /dev/null +++ b/model-00011-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f55c35142f91600ab2542c8ae431214f88bb3046e3e27f2d74bab287065e974 +size 4996771120 diff --git a/model-00012-of-00041.safetensors b/model-00012-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb0e600b9ce99bdc7db51c133e51abd30433d1ea --- /dev/null +++ b/model-00012-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:360574e4ea8b00ac0fa8f777613f40836eaa58ffed210f8ac10718d3dc132fdb +size 4999929320 diff --git a/model-00013-of-00041.safetensors b/model-00013-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f57fa0a1c233e1e7db85d8cc1d8a2963c83a67af --- /dev/null +++ b/model-00013-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a419a12dade67dc55170911f3467979b65d28263cad5ba7232c75ff12b77046e +size 4996770656 diff --git a/model-00014-of-00041.safetensors b/model-00014-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..70f2b99cda02444018f04b2adbb96a35516b4ad3 --- /dev/null +++ b/model-00014-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1b4f7c7a533dcafbaf08015c34d3e91d3d878b4b64ae4e3fd2cfb257b01aa46 +size 4996770664 diff --git a/model-00015-of-00041.safetensors b/model-00015-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3835cea0fa9ace457ed932f9a89229b1640a10cc --- /dev/null +++ b/model-00015-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6aba2420e1f643385e045972f351563b54091b3c80c07bf8af17a634f30b5d4 +size 4996771168 diff --git a/model-00016-of-00041.safetensors b/model-00016-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93e51cd4decfbcbf654fb6bf4edd1aa2b41fa63c --- /dev/null +++ b/model-00016-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b54246ec30f920d4d26707bb1a3cd06a5d5a0d3ed44c4d0a6ad54aa008ccafe4 +size 4999929368 diff --git a/model-00017-of-00041.safetensors b/model-00017-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e25cb04936b55b1737ba6a34faf9428f554b5e64 --- /dev/null +++ b/model-00017-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbf0decdc2d36fb57929248c2a8dbfab6c76e972f5aea41f2e2ebff7949d1f07 +size 4996770656 diff --git a/model-00018-of-00041.safetensors b/model-00018-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9bf5b0828251be99760f8d37274152ad37465c23 --- /dev/null +++ b/model-00018-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa552fa21947d91ae2988f25993251dfe3843d4b0b81e1e73707b3cd0f0023e0 +size 4996770712 diff --git a/model-00019-of-00041.safetensors b/model-00019-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff787c1d13719df38cc7d170b722d70e82f29533 --- /dev/null +++ b/model-00019-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ccc47a26daf8413c09ae781029d872fe796ea38fee0eb9f464d97e5dd81517f +size 4996771168 diff --git a/model-00020-of-00041.safetensors b/model-00020-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7ca2026f6b6b3f0c02e493b1e62f216785e6da7 --- /dev/null +++ b/model-00020-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81a5dd01c6f29e751162f11286b3202790e2a0167930b21e74d38e23ae0c0e5c +size 4999929392 diff --git a/model-00021-of-00041.safetensors b/model-00021-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8faad44cc0afccd2afb1c0220b2521f89d4bea85 --- /dev/null +++ b/model-00021-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694a1a2dba2e2e4157df4f769f194c20f382e07956456645c0a6db8c9e83afd1 +size 4996770656 diff --git a/model-00022-of-00041.safetensors b/model-00022-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44b43096aa83418f3e2a144e1e9ad30509c1411c --- /dev/null +++ b/model-00022-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e6184d83be6bac104c735aa6d3f5be2b1ba331dfecafc0d87d5e723d1e278f +size 4996770760 diff --git a/model-00023-of-00041.safetensors b/model-00023-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..783d543cc8ff4132196f37bb5ecf007990e23796 --- /dev/null +++ b/model-00023-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef2cf07d0f47987b3a52cb6a990bc66317244ae3b5c53b70a5d37fb0ed5bd48e +size 4996771168 diff --git a/model-00024-of-00041.safetensors b/model-00024-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a1768f6408ecf0fe93449b1bf119eb2bef8fb1f --- /dev/null +++ b/model-00024-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90bc0197e86b4ca3b711ff399cd33442f49d454e5f15c27f1609e150ea68f9cf +size 4999929344 diff --git a/model-00025-of-00041.safetensors b/model-00025-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..238706b2c3fd5dc0212da670dfa6a5b19b12d81f --- /dev/null +++ b/model-00025-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1d4820cbd00513cf03d447300ffa541ea3cad8803b2e0d0a74d7b632b6f0e0 +size 4996770656 diff --git a/model-00026-of-00041.safetensors b/model-00026-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6412befb4c831fba8d552f66ccf14dd95bbb9796 --- /dev/null +++ b/model-00026-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15067f644a73f9f35d5c6caad44c607b4595dffc0bf75fc62a3330450254440b +size 4996770808 diff --git a/model-00027-of-00041.safetensors b/model-00027-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..beebc100be4794dd167e7699fe16d5506ed77b6a --- /dev/null +++ b/model-00027-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212e9ee30b2d5056b6d01232c4bf03b3a4df058d7dd0c7e54c79398090650e32 +size 4996771168 diff --git a/model-00028-of-00041.safetensors b/model-00028-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d1ea7bc3489da956b8fd13aa96ff39159a7fc52 --- /dev/null +++ b/model-00028-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee3ea7ab93c63dd5be663478d0a068e344350c2cadc81548ae267ee7d86c172 +size 4999929296 diff --git a/model-00029-of-00041.safetensors b/model-00029-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91b1c727db15a38962350daa1e5f3566198276ab --- /dev/null +++ b/model-00029-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32ceb322b8e6c17c533efa32fc17af4281f672366ed70df0a2c5c0770a0855c9 +size 4996770656 diff --git a/model-00030-of-00041.safetensors b/model-00030-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26e09add0efedd992dd11152a7a78227a6a989e0 --- /dev/null +++ b/model-00030-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cdf400d6d4d6e4067c6f82fb373a19335142e1c7db4d450a8cfbdcdb821d70e +size 4996770856 diff --git a/model-00031-of-00041.safetensors b/model-00031-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d137e01e3e41cdb62330e236f82d91204b28ab8 --- /dev/null +++ b/model-00031-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb64026cca4492ef0dda5bb71e61d26713a4f16cc0dfecd41940d77cbb16da20 +size 4996771168 diff --git a/model-00032-of-00041.safetensors b/model-00032-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..67b21c09bef008f416d4d41c3ce7101048a204d1 --- /dev/null +++ b/model-00032-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c800bbb840f146c39963c14d43331c4a995e22ef71c7eb6a33b1a574a19e3eff +size 4999929288 diff --git a/model-00033-of-00041.safetensors b/model-00033-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..72452869481cb6a0ee42ae2f0cfaf246fb8859a0 --- /dev/null +++ b/model-00033-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e1c555bf6d05fc4e471cd9b88e38deb15bf92f1341caf2c94fc7691b0df499 +size 4996770656 diff --git a/model-00034-of-00041.safetensors b/model-00034-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1499bbd902523d6268f117266e056fe6711e9e6 --- /dev/null +++ b/model-00034-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44fb917f390670df7db92c945f77564e814e2f7fc6d485065feb205cc0e26e19 +size 4996770904 diff --git a/model-00035-of-00041.safetensors b/model-00035-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d4aeeba6d41daf09121aeda5bb9ab30f154c744 --- /dev/null +++ b/model-00035-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aab7c2ac0ff4079843d4e907ea05f132957454ccb696dbd6e9f232d00739a568 +size 4971886168 diff --git a/model-00036-of-00041.safetensors b/model-00036-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..088aee74edea978ee98245b1b562b5774e2e40d1 --- /dev/null +++ b/model-00036-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b218302bd7a6ece6ea466a8dce72c4a5db1ace94a4a7e389d88e584ab9b38db7 +size 4998268584 diff --git a/model-00037-of-00041.safetensors b/model-00037-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..774b64d23d859589b1ce9515deef580a8de4aafc --- /dev/null +++ b/model-00037-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737aaee5fa92e6d87ce44bf9502fdeeefe721cd2e01a7becec33b35fa9148f0f +size 4996770656 diff --git a/model-00038-of-00041.safetensors b/model-00038-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c276bf94c7822cfd49ca40c76d35079134e8b161 --- /dev/null +++ b/model-00038-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e380e90aa7e65118491fdbb7c005c9a27ca6bd02d48a52ae3d58f961ea02647e +size 4996770928 diff --git a/model-00039-of-00041.safetensors b/model-00039-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a03807e58fbdba0ac27be393c0c8bc3b72b870b3 --- /dev/null +++ b/model-00039-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cbc3b41ebbc6325b22581f09845068852b77f7834349c511cf50a259672c236 +size 4986659240 diff --git a/model-00040-of-00041.safetensors b/model-00040-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8167a471a234fcc011c05c455fd368d0178ee62c --- /dev/null +++ b/model-00040-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76edabce20e8d04d46e8dd3cb0e835b8e59540908624d76d9d6d2570645cb398 +size 4389170168 diff --git a/model-00041-of-00041.safetensors b/model-00041-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a1b17410c8006357309030848cee5f90d90a542 --- /dev/null +++ b/model-00041-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5344ed0a545f40db7029547e1e473c2a306c1cc2084c5f4c97808f7705a74aa +size 1551892608 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..89066c7651e9d7ebb188041f475532931d2b84d7 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c72a8cbe89ba70d649e76ed386882145d24f70cc04e4a8da5a3b5adeb128843 +size 16609598 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" +}