diff --git a/.eval_results/aime_2026.yaml b/.eval_results/aime_2026.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d768415b2fc1ff4c930e1e3a38341af03b07d895 --- /dev/null +++ b/.eval_results/aime_2026.yaml @@ -0,0 +1,7 @@ +- dataset: + id: MathArena/aime_2026 + task_id: MathArena/aime_2026 + value: 95.5 + source: + url: https://huggingface.co/thinkingmachines/Inkling-Small + name: Model Card diff --git a/.eval_results/gpqa.yaml b/.eval_results/gpqa.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3b8d60cd89c7b3bf42f88993e65745960c6a2838 --- /dev/null +++ b/.eval_results/gpqa.yaml @@ -0,0 +1,7 @@ +- dataset: + id: Idavidrein/gpqa + task_id: diamond + value: 89.5 + source: + url: https://huggingface.co/thinkingmachines/Inkling-Small + name: Model Card diff --git a/.eval_results/hle.yaml b/.eval_results/hle.yaml new file mode 100644 index 0000000000000000000000000000000000000000..895fe7daf7e79b3f2142001ed964befb715b0b1d --- /dev/null +++ b/.eval_results/hle.yaml @@ -0,0 +1,8 @@ +- dataset: + id: cais/hle + task_id: hle + value: 31.6 + source: + url: https://huggingface.co/thinkingmachines/Inkling-Small + name: Model Card + notes: text only diff --git a/.eval_results/hmmt_feb_2026.yaml b/.eval_results/hmmt_feb_2026.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0c3b3542d03a51a43053e9c7c2c68171b79cbc61 --- /dev/null +++ b/.eval_results/hmmt_feb_2026.yaml @@ -0,0 +1,7 @@ +- dataset: + id: MathArena/hmmt_feb_2026 + task_id: MathArena/hmmt_feb_2026 + value: 90.2 + source: + url: https://huggingface.co/thinkingmachines/Inkling-Small + name: Model Card diff --git a/.eval_results/mmmu_pro.yaml b/.eval_results/mmmu_pro.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b94de7abf228729f8aa95066c423302ce7dc610e --- /dev/null +++ b/.eval_results/mmmu_pro.yaml @@ -0,0 +1,7 @@ +- dataset: + id: MMMU/MMMU_Pro + task_id: mmmu_pro_standard_10_options + value: 74 + source: + url: https://huggingface.co/thinkingmachines/Inkling-Small + name: Model Card diff --git a/.eval_results/swe-bench_pro.yaml b/.eval_results/swe-bench_pro.yaml new file mode 100644 index 0000000000000000000000000000000000000000..baf609fd1bf479e4d862531402d0bf57025a68b2 --- /dev/null +++ b/.eval_results/swe-bench_pro.yaml @@ -0,0 +1,7 @@ +- dataset: + id: ScaleAI/SWE-bench_Pro + task_id: SWE_Bench_Pro + value: 55.9 + source: + url: https://huggingface.co/thinkingmachines/Inkling-Small + name: Model Card diff --git a/.eval_results/swe-bench_verified.yaml b/.eval_results/swe-bench_verified.yaml new file mode 100644 index 0000000000000000000000000000000000000000..37d902266afba550d742eba64a14a33549355639 --- /dev/null +++ b/.eval_results/swe-bench_verified.yaml @@ -0,0 +1,7 @@ +- dataset: + id: SWE-bench/SWE-bench_Verified + task_id: swe_bench_%_resolved + value: 80.2 + source: + url: https://huggingface.co/thinkingmachines/Inkling-Small + name: Model Card diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ 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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..adc0102bda858839cc174cd42bf7d7ae2c75324c --- /dev/null +++ b/README.md @@ -0,0 +1,787 @@ +--- +license: apache-2.0 +license_link: https://www.apache.org/licenses/LICENSE-2.0 +pipeline_tag: image-text-to-text +tags: +- conversational +- image-text-to-text +- audio-text-to-text +- moe +library_name: transformers +--- + +# Inkling + + + +

+ BF16 | + NVFP4 | + Playground | + Tinker Cookbook | + Acceptable Use +

+ +## 1. General Information + +Inkling-Small is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and multimodal tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers. + +**Languages:** English, with general multilingual capabilities across other languages. + +## 2. Getting Started + +Try Inkling-Small on the [Tinker Playground](https://tinker.thinkingmachines.ai/playground) or access via API using the [Tinker Cookbook](https://github.com/thinking-machines-lab/tinker-cookbook). + +Inkling-Small supports local deployment using the following open-source libraries: + +* SGLang ([recipe](https://docs.sglang.io/cookbook/autoregressive/ThinkingMachines/Inkling-Small)) +* vLLM ([recipe](https://recipes.vllm.ai/thinkingmachines/Inkling-Small)) +* TokenSpeed ([recipe](https://lightseek.org/tokenspeed/recipes/models#Inkling)) +* Unsloth ([recipe](https://unsloth.ai/docs/models/inkling)) +* Huggingface ([recipe](https://hf.co/blog/thinkingmachines-inkling)) + +API access is also available through third party inference providers. + +## 3. Model Properties + +### Model type + +Multimodal autoregressive transformer + +### Architecture type + +A 42-layer decoder-only transformer with a sparse Mixture-of-Experts (MoE) feed-forward backbone: each token is routed to 6 of 256 experts, plus 2 shared experts active on every token. Attention is a hybrid of local and global layers. The model is natively multimodal — images are encoded via a hierarchical patch encoder, and audio via discrete token encoding — with all modalities projected into a shared hidden space and processed jointly by the decoder. + +### Parameters + +276B total, 12B active + +### Numerics support + +BF16 and NVFP4 + +### Input modalities + +Inkling-Small accepts text, image, and audio inputs: + +- Text: UTF-8 encoded text +- Image: Any pixel-based image input. For optimal performance, each image dimension should be between 40px to 4096px. +- Audio: WAV format, sampled at 16kHz. For optimal performance, audio length should ideally be under 2 mins. + +### Output modalities + +Inkling-Small generates output as UTF-8 encoded text. + +## 4. Training + +Training data includes a broad variety of content types, including text, images, audio, video. + +Training data for the model was drawn from publicly available sources, acquired from third-parties, or synthetically generated or augmented. Publicly available data includes content from the public internet and publicly accessible repositories. + +The training data curation process includes cleaning, processing, and modifying datasets. These processing steps, which vary by data type, may include deduplication and filtering to remove junk or other low-quality data, or to advance safety or other objectives. + +## 5. Evaluations + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ Open weights + + Closed weights +
+ Inkling-Small + Qwen3.5 397B-A17B + MiMo V2.5 + Minimax M2.7 + DeepSeek V4 Flash + Nemotron 3 Ultra + Inkling + Claude 4.5 Haiku + Gemini 3.5 Flash-Lite + GPT 5.6 Luna
Model Info
+ AA Index (v4.1) + 40.0%34.0%37.0%38.0%40.0%38.0%41.0%30.0%36.0%49.0%
+ Params (B) (activated / total) + 12 / 27617 / 39715 / 31010 / 23013 / 28455 / 55041 / 975–––
Agentic (coding)
+ SWEBench Verified + 80.2%76.4%71.0%79.9%79.0%70.7%77.6%73.3%75.0%93.0%
+ SWEBench Pro (public) + 55.9%50.9%56.1%56.2%52.6%46.4%54.3%39.5%54.2%62.7%
+ Terminal Bench 2.1 (best harness) + 64.7%51.3%63.7%55.4%61.8%56.4%63.8%44.2%54.0%82.5%
+ SciCode + 48.7%42.0%43.1%47.0%44.9%39.9%46.1%43.3%40.9%50.0%
Agentic (general)
+ GDPval-AA v2 + 12699621145115911891164123891111391530
+ MCP Atlas (public / all) + 79.6/79.2%74.2%/––49.4%/–69.0%/–47.4/44.7%78.8/76.0%41.2/40.2%79.8/76.8%77.0/75.0%
+ Tau 3 Banking + 15.5%13.4%6.6%8.9%22.9%13.8%23.7%9.1%16.5%24.3%
+ BrowseComp (with context management) + 77.4%78.6%–76.3%73.2%63.0%77.1%––84.0%
+ Toolathlon Verified + 54.4%40.7%49.1%47.5%50.9%34.3%45.5%26.9%57.1%67.9%
+ AA-Briefcase + 917–––833870839612––
Reasoning (general)
+ GPQA Diamond + 89.5%89.3%84.9%87.4%89.4%86.7%87.2%67.2%83.8%89.5%
+ HLE (text only) + 31.6%27.3%25.2%28.1%32.1%26.6%29.7%9.7%17.5%35.6%
+ HLE (with tools) + 47.8%48.3%40.0%40.3%45.1%37.4%46.0%17.8%42.5%48.9%
+ AIME 2026 + 95.5%93.3%93.6%87.7%95.8%94.2%97.1%85.1%82.2%97.6%
+ HMMT Feb 2026 + 90.2%87.9%82.6%71.2%93.9%78.8%86.3%66.7%63.6%98.5%
+ CritPt + 8.3%1.7%3.7%0.6%7.1%3.1%5.4%0.0%0.0%20.6%
Reasoning (abstract)
+ ARC-AGI-1 + 84.0%–––––79.5%47.7%–87.7%
+ ARC-AGI-2 + 40.1%–––––36.5%4.0%–47.6%
Factuality
+ SimpleQA Verified + 20.6%26.0%16.1%13.5%34.1%32.4%43.9%5.9%44.1%41.7%
+ AA Omniscience (index) + -9.0-29.8-9.30.7-22.9-1.02.1-4.26.9-11.6
Chat
+ IFBench + 82.2%78.8%67.1%75.7%79.2%81.4%79.8%54.3%78.6%67.3%
+ Global-MMLU-Lite + 86.7%90.0%83.5%83.9%88.4%85.6%88.7%83.4%89.4%88.7%
Safety
+ StrongREJECT + 98.4%99.4%99.3%99.4%97.4%98.7%98.6%98.6%97.6%98.7%
+ FORTRESS (adversarial) + 71.6%77.3%64.8%86.3%32.0%77.6%78.0%91.3%70.7%83.8%
+ FORTRESS (benign) + 96.9%95.4%94.6%90.1%99.2%90.6%95.9%94.1%95.5%97.8%
Vision
+ MMMU Pro (Standard 10) + 74.0%77.3%75.4%–––73.5%58.6%79.0%78.6%
+ Charxiv RQ (original / with python) + 77.4/81.3%80.8%/–81.0%/––––78.1/82.0%57.4%/–70.0%/–81.4%/–
Audio
+ Audio MC + 54.9%–30.4%–––56.6%–33.6%–
+ MMAU + 77.0%–73.6%–––77.2%–75.2%–
+ VoiceBench + 90.1%–86.4%–––91.4%–85.9%–
+ +- Inkling-Small against open-and closed-weights models across the full eval suite. Activated and total parameters are given for scale; a dash means the score was not available at the time of writing. +- SWEBench Verified: Inkling and Inkling-Small’s numbers are reported using a bash-only harness. We use self-reported numbers for external models. +- Terminal Bench 2.1: Inkling and Inkling-Small’s numbers are reported using an internal coding harness. A small number of solutions were found to be contaminated from web search and were assigned a score of 0. We use self-reported numbers for external models where available. Otherwise, we report performance using our internal harness. +- Audio MC: Other models were evaluated internally since they are not on the official leaderboard. +- VoiceBench: VoiceBench uses rule-based, hard-coded string matching for grading, making the evaluation sensitive to output-formatting differences. We therefore added a system message instructing models to follow the expected answer format. +- HLE with tools: We benchmarked Minimax M2.7, Claude 4.5 Haiku, Gemini 3.5 Flash-Lite, and GPT 5.6 Luna using our internal harness. + +## 6. Safety + +We conducted safety evaluations ahead of release, spanning both everyday human-AI interaction and dangerous-capability testing. Because Inkling-Small is multimodal, we paid attention to whether safety behavior held consistently across text, audio, and image inputs. We applied mitigations to reduce risks before release. + +For everyday interaction, we evaluated sycophancy, harmful manipulation, and psychological-harm patterns like parasocial dependency and validation of delusional reasoning, including through multi-turn, open-ended external red-teaming designed to surface issues that only emerge over longer conversations. We also assessed whether the model refuses genuinely harmful requests without over-refusing benign ones. For CBRN and cyber, we assessed knowledge and procedural uplift through internal evaluations, external testing, and refusal-suppressed variants intended to estimate latent capability with safeguards removed. For loss of control, we evaluated agentic capability, strategic deception, and sabotage potential, benchmarked against public frontier models, and found the model materially below frontier capabilities. + +Across all areas, we concluded that Inkling-Small did not present risk of material uplift beyond what's already available in the open-weight ecosystem. + +The residual risks identified in our evaluations — specifically, Inkling-Small’s occasional tendency to comply with role-play and indirectly framed prompts concerning harmful topics — are consistent with what you would see from any open-weight model, and are best addressed with defense-in-depth rather than relying on the model's refusals alone. Common downstream moderation tools, such as Llama Guard, are compatible with Inkling-Small and can be layered around the model to catch jailbreak attempts, filter unsafe outputs, and enforce use-case-specific policies. We would encourage treating this kind of input/output classification as a part of your deployment stack, especially for consumer-facing or high-traffic applications where adversarial prompting is more likely. + +## 7. Bias, risks and limitations + +Inkling-Small may exhibit general limitations common to foundation models, including hallucination (generating plausible but factually incorrect or unsupported content), occasional failures to follow instructions precisely, and degraded performance in long multi-turn conversations. As with other large-scale models trained on web-derived and synthetic data, Inkling-Small may reflect biases present in its training data, including demographic, cultural, or linguistic biases, and may perform unevenly across languages, dialects, or subject domains that were less represented during training. + +Inkling-Small's knowledge is limited to information available as of its training cutoff, and it may not reflect events, developments, or changes that occurred afterward. + +We recommend that downstream developers and deployers apply appropriate human oversight and review for outputs used in high-stakes or safety-critical contexts, rather than relying on Inkling-Small's outputs without verification. + +- Conduct their own evaluation of Inkling-Small's performance, safety, and fairness for their specific use case, language, and population prior to deployment, particularly for applications involving vulnerable groups. +- Implement additional safeguards – such as content filtering, rate limiting, and monitoring – at the application layer, especially for open deployment contexts where Inkling-Small's built-in mitigations may not be sufficient on their own. +- Avoid deploying Inkling-Small in domains such as medical, legal, or safety-critical decision-making without additional fine-tuning, domain-specific validation, and human oversight + +## 8. Legal + +[Training Data Documentation](https://thinkingmachines.ai/training-data-documentation/) \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..04c53c7d1f9832f8cce2dab9cbde247a1c66b680 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,129 @@ +{%- set effort_map = {"none": 0.0, "minimal": 0.1, "low": 0.2, "medium": 0.7, "high": 0.9, "max": 0.99} -%} +{%- set role_token = {"user": "<|message_user|>", "assistant": "<|message_model|>", "system": "<|message_system|>", "tool": "<|message_tool|>"} -%} + +{%- macro emit_thinking_effort() -%} + {%- set eff = reasoning_effort if reasoning_effort is defined and reasoning_effort is not none else 0.9 -%} + {%- if eff is string -%} + {%- set key = eff | trim -%} + {%- if key not in effort_map -%} + {{- raise_exception("Unknown reasoning_effort: " ~ eff) -}} + {%- endif -%} + {%- set num = effort_map[key] -%} + {%- else -%} + {%- set num = eff | float -%} + {%- endif -%} + {%- if num < 0.0 or num > 0.99 -%} + {{- raise_exception("reasoning_effort must be in [0.0, 0.99]") -}} + {%- endif -%} + {{- "<|message_system|><|content_text|>Thinking effort level: " -}} + {%- if num == 0.0 -%}0{%- else -%}{{ num }}{%- endif -%} + {{- "<|end_message|>" -}} +{%- endmacro -%} + +{%- if tools -%} + {%- set tool_state = namespace(specs=[]) -%} + {%- for tool in tools -%} + {%- set fn = tool.function if tool.function is defined else tool -%} + {%- set spec = { + "description": (fn.description if fn.description is defined and fn.description else ""), + "name": fn.name, + "parameters": (fn.parameters if fn.parameters is defined and fn.parameters else {}), + "type": (tool.type if tool.type is defined and tool.type else "function"), + } -%} + {%- set tool_state.specs = tool_state.specs + [spec] -%} + {%- endfor -%} + {{- "<|message_system|>tool_declare<|content_xml|>" -}} + {{- tool_state.specs | tojson(sort_keys=true, separators=(",", ":")) -}} + {{- "<|end_message|>" -}} +{%- endif -%} + +{%- set state = namespace(effort_emitted=false) -%} +{%- for message in messages -%} + {%- if message.role not in role_token -%} + {{- raise_exception("Unknown message role: " ~ message.role) -}} + {%- endif -%} + {%- if not state.effort_emitted and message.role != "system" -%} + {{- emit_thinking_effort() -}} + {%- set state.effort_emitted = true -%} + {%- endif -%} + + {%- set rtok = role_token[message.role] -%} + + {%- if message.role == "tool" -%} + {%- set tool_name_state = namespace(name="") -%} + {%- if message.name is defined and message.name -%} + {%- set tool_name_state.name = message.name -%} + {%- elif message.tool_call_id is defined and message.tool_call_id -%} + {%- for prev in messages -%} + {%- if prev.role == "assistant" and prev.tool_calls -%} + {%- for tc in prev.tool_calls -%} + {%- if tc.id is defined and tc.id == message.tool_call_id and tc.function.name is defined -%} + {%- set tool_name_state.name = tc.function.name -%} + {%- endif -%} + {%- endfor -%} + {%- endif -%} + {%- endfor -%} + {%- endif -%} + {{- rtok -}} + {%- if tool_name_state.name -%}{{- tool_name_state.name -}}{%- endif -%} + {{- "<|content_text|>" -}} + {%- if message.content is string -%}{{- message.content -}}{%- endif -%} + {{- "<|end_message|>" -}} + + {%- else -%} + {%- if message.role == "assistant" and message.reasoning_content is defined and message.reasoning_content -%} + {{- "<|message_model|><|content_thinking|>" ~ message.reasoning_content ~ "<|end_message|>" -}} + {%- endif -%} + + {%- if message.content is string -%} + {{- rtok ~ "<|content_text|>" ~ message.content ~ "<|end_message|>" -}} + {%- elif message.content -%} + {%- for part in message.content -%} + {%- if part is string -%} + {{- rtok ~ "<|content_text|>" ~ part ~ "<|end_message|>" -}} + {%- elif part.type is not defined or part.type in ("text", "input_text") -%} + {%- set text_part = (part.text if part.text is defined and part.text is string else "") -%} + {{- rtok ~ "<|content_text|>" ~ text_part ~ "<|end_message|>" -}} + {%- elif part.type in ("image", "input_image", "image_url") -%} + {{- rtok ~ "<|content_image|><|unused_200054|><|end_message|>" -}} + {%- elif part.type in ("audio", "input_audio", "audio_url") -%} + {{- rtok ~ "<|content_audio_input|><|unused_200053|><|audio_end|><|end_message|>" -}} + {%- else -%} + {{- raise_exception("Unsupported content part type: " ~ part.type) -}} + {%- endif -%} + {%- endfor -%} + {%- endif -%} + + {%- if message.role == "assistant" and message.tool_calls -%} + {%- for tc in message.tool_calls -%} + {%- set fn = tc.function -%} + {%- if fn.name is not defined or fn.name is not string -%} + {{- raise_exception("tool call function name must be a string") -}} + {%- endif -%} + {%- set args = fn.arguments if fn.arguments is defined and fn.arguments else {} -%} + {%- if args is string -%} + {{- raise_exception("tool call arguments must be a parsed object, not a JSON string; canonicalize upstream") -}} + {%- endif -%} + {%- if args is not mapping -%} + {{- raise_exception("tool call arguments must be an object") -}} + {%- endif -%} + {{- "<|message_model|>" ~ fn.name ~ "<|content_invoke_tool_json|>" -}} + {{- '{"name":' ~ (fn.name | tojson(sort_keys=true, separators=(",", ":"))) ~ ',"args":' -}} + {{- (args | tojson(sort_keys=true, separators=(",", ":"))) -}} + {{- "}<|end_message|>" -}} + {%- endfor -%} + {%- endif -%} + + {%- if message.role == "assistant" -%} + {{- "<|content_model_end_sampling|>" -}} + {%- endif -%} + {%- endif -%} +{%- endfor -%} + +{%- if not state.effort_emitted -%} + {{- emit_thinking_effort() -}} +{%- endif -%} + +{%- if add_generation_prompt -%} + {{- "<|message_model|>" -}} +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..da5ce4d64bb2b9f178a63f34a4aa5b84ab3da00f --- /dev/null +++ b/config.json @@ -0,0 +1,2077 @@ +{ + "architectures": [ + "InklingForConditionalGeneration" + ], + "model_type": "inkling_mm_model", + "eos_token_id": 200006, + "text_config": { + "model_max_length": 1048576, + "torch_dtype": "bfloat16", + "hidden_size": 4096, + "num_hidden_layers": 42, + "vocab_size": 201024, + "num_attention_heads": 32, + "num_key_value_heads": 8, + "head_dim": 128, + "d_rel": 16, + "rel_extent": 1024, + "q_bias": false, + "o_bias": false, + "log_scaling_n_floor": 128000, + "log_scaling_alpha": 0.1, + "rms_norm_eps": 1e-06, + "use_embed_norm": true, + "local_layer_ids": [ + 0, + 1, + 2, + 3, + 4, + 6, + 7, + 8, + 9, + 10, + 12, + 13, + 14, + 15, + 16, + 18, + 19, + 20, + 21, + 22, + 24, + 25, + 26, + 27, + 28, + 30, + 31, + 32, + 33, + 34, + 36, + 37, + 38, + 39, + 40 + ], + "dense_mlp_idx": 2, + "use_sconv": true, + "sconv_kernel_size": 4, + "unpadded_vocab_size": 200058, + "logits_mup_width_multiplier": 16.0, + "final_logit_softcapping": null, + "swa_head_dim": 128, + "swa_num_attention_heads": 32, + "swa_num_key_value_heads": 8, + "sliding_window_size": 512, + "n_routed_experts": 256, + "num_experts_per_tok": 6, + "n_shared_experts": 2, + "shared_expert_sink": true, + "dense_intermediate_size": 16384, + "intermediate_size": 2048, + "route_scale": 8.0, + "use_gate_bias": true, + "gate_activation": "sigmoid", + "norm_after_topk": true, + "use_global_scale": true + }, + "audio_config": { + "decoder_dmodel": 4096, + "n_mel_bins": 80, + "mel_vocab_size": 16, + "bias": false, + "dmel_min_value": -7.0, + "dmel_max_value": 2.0, + "use_audio_norm": true, + "audio_mode": "dmel" + }, + "vision_config": { + "vision_encoder_type": "hmlp", + "decoder_dmodel": 4096, + "patch_size": 40, + "temporal_patch_size": 2, + "n_channels": 3, + "n_layers": 4, + "use_vision_norm": true + }, + "mtp_config": { + "num_nextn_predict_layers": 8, + "chain_hidden_post_norm": false, + "local_layer_ids": [ + 0, + 2, + 4, + 5, + 6, + 7 + ] + }, + "quantization_config": { + "quant_method": "auto-round", + "packing_format": "auto_round:llm_compressor", + "bits": 4, + "group_size": 32, + "sym": true, + "data_type": "mx_fp", + "iters": 0, + "model_free": true, + "autoround_version": "0.15.0", + "enable_quanted_input": false, + "block_name_to_quantize": "model.llm.layers", + "act_bits": 16, + "act_data_type": "fp", + "act_dynamic": true, + "act_group_size": 128, + "act_sym": true, + "extra_config": { + "mlp.experts": { + "act_bits": 4, + "act_group_size": 32, + "act_data_type": "mx_fp" + }, + "model.audio.encoder": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.visual.layers.linear_2": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.visual.layers.linear_1": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.visual.layers.linear_3": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.visual.layers.linear_0": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + } + } + } +} \ No newline at end of file diff --git a/model-00001-of-00033.safetensors b/model-00001-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a23d5d3927cd6b9618f61edde55d05481cbd6a0d --- /dev/null +++ b/model-00001-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220896ff2c157a8f1ab3aab571101b7ad85e8cee98969bdea32e62c935474ad6 +size 5136558332 diff --git a/model-00002-of-00033.safetensors b/model-00002-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b06b4f53eeb7718ffb2bf2df26bc98c35e0865ba --- /dev/null +++ b/model-00002-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d415d1f62c7c3274a1c032f412b2fd9c01f52a189d15d270c12e137c07fffb +size 5281036664 diff --git a/model-00003-of-00033.safetensors b/model-00003-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2bfe78bb606bf3162741b109039999d0d5af60ed --- /dev/null +++ b/model-00003-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce895ebb1f8f01c0feec547fb46f9ec1199a86164f8f3b0d4dd01f8816428a0 +size 6248246264 diff --git a/model-00004-of-00033.safetensors b/model-00004-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f27faf2980f3fd422e3a405b3a134347854eacc --- /dev/null +++ b/model-00004-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9c0ee179e34ff85a7f166e4e22143c9321400822d843faacc6c7ee1fbcc48e +size 5189658660 diff --git a/model-00005-of-00033.safetensors b/model-00005-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a6aa97cb307b2aefb8b4955bad3fdc017c8a028 --- /dev/null +++ b/model-00005-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15981a82efa092ddda33accefe1d6193d23abe03326ed7c5fafe3e66923be6fe +size 3632409948 diff --git a/model-00006-of-00033.safetensors b/model-00006-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d91a2b3553db170517645f9cd31e4480c482039 --- /dev/null +++ b/model-00006-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0def8931f6090b84e557090fece26affd298974c1bacdce89a108a55be3566aa +size 4815146544 diff --git a/model-00007-of-00033.safetensors b/model-00007-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6698537b558b5342c164efbbc91eff918ca00583 --- /dev/null +++ b/model-00007-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26dfa2e1120f054d4040756587b537816b656bfd7e331e0ffaf1b8523366cf9c +size 4972656182 diff --git a/model-00008-of-00033.safetensors b/model-00008-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87a15328932e82ac7e76b1b84b919d041695c511 --- /dev/null +++ b/model-00008-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d9f00ca87295c3ae96e9a69c67439d747a9131ef16e4cda6b58387b6ef3cda +size 4852912548 diff --git a/model-00009-of-00033.safetensors b/model-00009-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6bb9ce213c6623bbe8555cd06cc2c6dc0915ca0 --- /dev/null +++ b/model-00009-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562a015c331c585cd05f10d37bf2cb8968b4356286fcaff2e7906f853f77efb1 +size 5081635456 diff --git a/model-00010-of-00033.safetensors b/model-00010-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d17b18fc8c22a96a76f75facea61d1d35f464fd1 --- /dev/null +++ b/model-00010-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33713271b1ec1c1a057c133e5386a539a396233dbb17a713dc1d117269f79e12 +size 4972678420 diff --git a/model-00011-of-00033.safetensors b/model-00011-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92aa88cdba3bbf8c02ef4e2c024cd8bf55fcf7d2 --- /dev/null +++ b/model-00011-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91fff27e59784cc24f5a6f01293a7511a5fa7b3387269f004be7a7557826c022 +size 4947387284 diff --git a/model-00012-of-00033.safetensors b/model-00012-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d7aa24d2d1c0168a3abd0fb5fdaea264eaeedd4 --- /dev/null +++ b/model-00012-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:191ff934efbd6fd2350aecea7a130e367a7eb6fe0f19b82fc557d222fa0cd6d3 +size 4731326832 diff --git a/model-00013-of-00033.safetensors b/model-00013-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47c2c1f81e06c9149fa66a8837da4e7e37fb280b --- /dev/null +++ b/model-00013-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43fbdffa99bf3f689a6d63aaace4b7de4818b9e43893319f90b43c3e1dc8cff +size 5022781176 diff --git a/model-00014-of-00033.safetensors b/model-00014-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01dc66f63647ff0a76e00ffe77efb47fcc5ff915 --- /dev/null +++ b/model-00014-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add22ccf098179917146b9550212a3dbb6bf2a348700ebd5245e0948b78c0ce6 +size 4913846332 diff --git a/model-00015-of-00033.safetensors b/model-00015-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b01a71d7592a6c20a8c3e6c592f6e3c67bdf43fc --- /dev/null +++ b/model-00015-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34035b5b4edf6303cfd7029d7f8759fdf7c8c28385e00419bc87b2957c0d2b5 +size 3851986884 diff --git a/model-00016-of-00033.safetensors b/model-00016-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b67bb0b44cea2092b2c438517229681068297b76 --- /dev/null +++ b/model-00016-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950b1820b86f0da9d935c4bde10f32657f77b4c9b319d37b52226d3cc7676d3a +size 3961855356 diff --git a/model-00017-of-00033.safetensors b/model-00017-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e047e416fd3164defd1669d49a3f56ae43c0b2cf --- /dev/null +++ b/model-00017-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa4346facdacf80ff3b2c115f554e3024098673e2de3738bac0318ca2fa5902 +size 3676559044 diff --git a/model-00018-of-00033.safetensors b/model-00018-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7822664137812319694d47ee1cbd2cee98bcc7c8 --- /dev/null +++ b/model-00018-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4516c277e22b0d9f82b1e7209e3342265165a48eb66c1e1abad4eadaef869885 +size 4701975196 diff --git a/model-00019-of-00033.safetensors b/model-00019-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2be03b6c8d8beb152f9847b137adf6b18e9cb66 --- /dev/null +++ b/model-00019-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e44e60153c4e565f20d650e868e2e2ee78796fb2ee7402843812fbd4868257c +size 3615534910 diff --git a/model-00020-of-00033.safetensors b/model-00020-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e73217a84d5df0bc300fc6e9658aca7ff38f7f4 --- /dev/null +++ b/model-00020-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051f2cdff57b0073185d5575ddc3de979adde4bc09fcce7e99e84b6f7897f7eb +size 4850864624 diff --git a/model-00021-of-00033.safetensors b/model-00021-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e60ea3c87442a1a70bec5898f105bc558f54a7a --- /dev/null +++ b/model-00021-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafe833b58d2551ee5f3f7bdbdee592bcdee970216c88ec8221b6aaa58656061 +size 3477138356 diff --git a/model-00022-of-00033.safetensors b/model-00022-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96a3447f121a20625b9ca454ccc6363cabd2553e --- /dev/null +++ b/model-00022-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4974d4637964f78a6a5db513c2bf050cb2d6955d312a9ece711a617a385af68a +size 5020791324 diff --git a/model-00023-of-00033.safetensors b/model-00023-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee48c9d4749ce93ce4c0d34b257c89f80bf5d8a6 --- /dev/null +++ b/model-00023-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d3799de2e8cacace1df03abe109c90503a8c3bdb9d85fecf6fea5a6f13d9703 +size 4844582312 diff --git a/model-00024-of-00033.safetensors b/model-00024-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab609d6fa7537d27dcd2c353969749956d1461fb --- /dev/null +++ b/model-00024-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3fc079f1bbf748f805a8d40f916747787d53973806f6909553c02d1acd12872 +size 4915946096 diff --git a/model-00025-of-00033.safetensors b/model-00025-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3dc4e761f8a2210d83c7aabc71144b4d041fa03b --- /dev/null +++ b/model-00025-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e7c5365f2e576e377b27e0dc543458979b2700e66830dbc6e5ac7628a4b383a +size 4632691884 diff --git a/model-00026-of-00033.safetensors b/model-00026-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4860ab820a29cad7eafa47287586b9929bc79075 --- /dev/null +++ b/model-00026-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b79b2646860ec912fa31521e6d935bfd50525d97f4cac909834accdac8d266 +size 4571810092 diff --git a/model-00027-of-00033.safetensors b/model-00027-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..050aab7ae0b866efb1a777e01adb2dfea9a5b576 --- /dev/null +++ b/model-00027-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3966ec194474b6404cba78d0e10e5f1ed94b3508df4a5428aec124371e9509 +size 4775343344 diff --git a/model-00028-of-00033.safetensors b/model-00028-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..728ab973be45552337727040feae5d38e8a582b2 --- /dev/null +++ b/model-00028-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:410744ffd6f07956ba68daf95ca156304434c6584dbaabf8e29d2a7d5f0893d3 +size 4723077176 diff --git a/model-00029-of-00033.safetensors b/model-00029-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e49a9e571f0768701e487d05fc3f76942a55b307 --- /dev/null +++ b/model-00029-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3117ec491126a500a87e08b83305a372d428ac741c4a89f0d66b5a60d106dd5 +size 4714473684 diff --git a/model-00030-of-00033.safetensors b/model-00030-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..583897ff140b691690325cb2dab146464c3d43d5 --- /dev/null +++ b/model-00030-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05bbf88e6ad7f0574e4fc4f7d70ced033c758aa4176a2462415fc699b2498c69 +size 4699802708 diff --git a/model-00031-of-00033.safetensors b/model-00031-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07769ad887822ff8589759334f4ac64f8468e760 --- /dev/null +++ b/model-00031-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5714f0b41166665e807205658bd33ad07be6ae0716f521e4c6d20297a6e1713b +size 4596957956 diff --git a/model-00032-of-00033.safetensors b/model-00032-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c906c6f0c768a0acfb1dd5a8f583e38b3953f87 --- /dev/null +++ b/model-00032-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ebe21a387a182095082526c89836b11df099a68e0c840596e724b55b27b778 +size 3525521192 diff --git a/model-00033-of-00033.safetensors b/model-00033-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54af538acef55637b9114079484ee48135d5ff65 --- /dev/null +++ b/model-00033-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aac3b906b63c529ef7b0c9fc724f7860b5d0de58af21d39bd2013580dac7d7a5 +size 4463845360 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..f9d7d114e3e345ae92b059561cc201f13d3f9bdd --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1135 @@ +{ + "metadata": { + "total_size": 0 + }, + "weight_map": { + "model.audio.encoder.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.13.attn.wr_du.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.14.attn.k_norm.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.16.mlp.experts.w13_weight.weight_packed": "model-00001-of-00033.safetensors", + "model.llm.layers.16.mlp.experts.w13_weight.weight_scale": "model-00001-of-00033.safetensors", + "model.llm.layers.20.mlp_norm.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.30.mlp.experts.w2_weight.weight_packed": "model-00001-of-00033.safetensors", + "model.llm.layers.30.mlp.experts.w2_weight.weight_scale": "model-00001-of-00033.safetensors", + "model.llm.layers.34.attn.wk_dv.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.37.attn.wk_dv.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.37.attn.wo_ud.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.38.mlp.gate.global_scale": "model-00001-of-00033.safetensors", + "model.llm.embed_norm.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.16.mlp_sconv.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.24.attn.k_sconv.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.29.attn_sconv.weight": "model-00001-of-00033.safetensors", + "model.llm.layers.3.mlp.gate.weight": "model-00001-of-00033.safetensors", + "model.llm.unembed.weight": "model-00001-of-00033.safetensors", + "model.audio.final_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.10.attn.q_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.11.mlp.shared_experts.shared_w13_weight": "model-00002-of-00033.safetensors", + "model.llm.layers.13.attn.q_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.13.attn.wk_dv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.14.attn.q_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.15.mlp.gate.bias": "model-00002-of-00033.safetensors", + "model.llm.layers.15.mlp.shared_experts.shared_w13_weight": "model-00002-of-00033.safetensors", + "model.llm.layers.17.mlp.shared_experts.shared_w2_weight": "model-00002-of-00033.safetensors", + "model.llm.layers.18.attn.q_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.18.attn.wq_du.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.18.mlp.shared_experts.shared_w2_weight": "model-00002-of-00033.safetensors", + "model.llm.layers.19.attn.wo_ud.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.19.mlp.experts.w2_weight.weight_packed": "model-00002-of-00033.safetensors", + "model.llm.layers.19.mlp.experts.w2_weight.weight_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.2.attn.wv_dv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.20.attn.rel_logits_proj.proj": "model-00002-of-00033.safetensors", + "model.llm.layers.20.attn.wk_dv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.21.attn.k_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.21.attn.wk_dv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.21.mlp_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.22.attn.k_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.22.attn.wq_du.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.23.attn.wr_du.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.23.mlp.gate.global_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.24.mlp.gate.bias": "model-00002-of-00033.safetensors", + "model.llm.layers.25.attn.wo_ud.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.25.mlp.gate.global_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.25.mlp_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.26.attn_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.27.attn.wk_dv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.27.attn_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.27.mlp.gate.global_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.27.mlp.shared_experts.shared_w2_weight": "model-00002-of-00033.safetensors", + "model.llm.layers.29.attn.k_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.29.attn.wv_dv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.3.attn.wo_ud.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.3.attn.wr_du.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.31.attn.rel_logits_proj.proj": "model-00002-of-00033.safetensors", + "model.llm.layers.32.attn.wo_ud.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.32.attn.wq_du.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.32.mlp.gate.bias": "model-00002-of-00033.safetensors", + "model.llm.layers.33.attn.k_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.33.attn.rel_logits_proj.proj": "model-00002-of-00033.safetensors", + "model.llm.layers.33.mlp.gate.global_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.34.attn_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.34.mlp.experts.w13_weight.weight_packed": "model-00002-of-00033.safetensors", + "model.llm.layers.34.mlp.experts.w13_weight.weight_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.34.mlp.gate.global_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.36.mlp.gate.bias": "model-00002-of-00033.safetensors", + "model.llm.layers.37.attn.wr_du.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.37.mlp.shared_experts.shared_w2_weight": "model-00002-of-00033.safetensors", + "model.llm.layers.38.attn.rel_logits_proj.proj": "model-00002-of-00033.safetensors", + "model.llm.layers.4.attn.wk_dv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.4.attn.wq_du.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.40.attn.wr_du.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.41.attn_norm.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.5.mlp.gate.global_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.5.mlp.shared_experts.shared_w13_weight": "model-00002-of-00033.safetensors", + "model.llm.layers.5.mlp.shared_experts.shared_w2_weight": "model-00002-of-00033.safetensors", + "model.llm.layers.7.mlp.experts.w2_weight.weight_packed": "model-00002-of-00033.safetensors", + "model.llm.layers.7.mlp.experts.w2_weight.weight_scale": "model-00002-of-00033.safetensors", + "model.llm.layers.11.mlp.gate.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.18.attn.v_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.2.mlp.gate.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.25.mlp_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.3.attn.k_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.33.attn_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.34.attn.k_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.35.attn.v_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.36.attn.k_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.36.mlp_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.38.mlp_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.8.attn_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.9.mlp_sconv.weight": "model-00002-of-00033.safetensors", + "model.llm.layers.0.attn.q_norm.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.12.mlp_norm.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.13.mlp_norm.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.14.mlp.shared_experts.shared_w13_weight": "model-00005-of-00033.safetensors", + "model.llm.layers.16.mlp.shared_experts.shared_w2_weight": "model-00005-of-00033.safetensors", + "model.llm.layers.19.attn.q_norm.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.22.mlp.gate.global_scale": "model-00005-of-00033.safetensors", + "model.llm.layers.23.attn.wk_dv.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.26.attn.rel_logits_proj.proj": "model-00005-of-00033.safetensors", + "model.llm.layers.27.mlp.experts.w2_weight.weight_packed": "model-00005-of-00033.safetensors", + "model.llm.layers.27.mlp.experts.w2_weight.weight_scale": "model-00005-of-00033.safetensors", + "model.llm.layers.30.attn.wr_du.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.34.attn.wv_dv.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.36.attn.wr_du.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.38.mlp.experts.w13_weight.weight_packed": "model-00005-of-00033.safetensors", + "model.llm.layers.38.mlp.experts.w13_weight.weight_scale": "model-00005-of-00033.safetensors", + "model.llm.layers.39.mlp.shared_experts.shared_w13_weight": "model-00005-of-00033.safetensors", + "model.llm.layers.6.attn.wr_du.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.8.attn.wr_du.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.9.attn.wr_du.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.15.mlp.gate.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.25.attn.k_sconv.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.37.mlp_sconv.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.4.mlp.gate.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.6.mlp_sconv.weight": "model-00005-of-00033.safetensors", + "model.llm.layers.11.mlp.experts.w13_weight.weight_packed": "model-00003-of-00033.safetensors", + "model.llm.layers.11.mlp.experts.w13_weight.weight_scale": "model-00003-of-00033.safetensors", + "model.llm.layers.18.attn.rel_logits_proj.proj": "model-00003-of-00033.safetensors", + "model.llm.layers.21.attn.rel_logits_proj.proj": "model-00003-of-00033.safetensors", + "model.llm.layers.3.attn_norm.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.30.attn.wq_du.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.31.mlp.experts.w13_weight.weight_packed": "model-00003-of-00033.safetensors", + "model.llm.layers.31.mlp.experts.w13_weight.weight_scale": "model-00003-of-00033.safetensors", + "model.llm.layers.32.mlp_norm.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.36.attn.rel_logits_proj.proj": "model-00003-of-00033.safetensors", + "model.llm.layers.39.attn_norm.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.4.attn_norm.weight": "model-00003-of-00033.safetensors", + "model.llm.embed.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.0.attn.k_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.1.attn.v_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.10.attn.v_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.12.mlp_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.14.attn.k_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.18.mlp.gate.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.22.attn.k_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.26.attn.k_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.26.attn_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.27.mlp.gate.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.34.attn_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.36.attn.v_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.9.attn_sconv.weight": "model-00003-of-00033.safetensors", + "model.llm.layers.0.attn.k_norm.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.0.attn.wq_du.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.0.mlp.w13_dn.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.13.attn.rel_logits_proj.proj": "model-00004-of-00033.safetensors", + "model.llm.layers.13.mlp.gate.bias": "model-00004-of-00033.safetensors", + "model.llm.layers.15.attn.rel_logits_proj.proj": "model-00004-of-00033.safetensors", + "model.llm.layers.15.mlp.shared_experts.shared_w2_weight": "model-00004-of-00033.safetensors", + "model.llm.layers.16.attn.rel_logits_proj.proj": "model-00004-of-00033.safetensors", + "model.llm.layers.16.mlp.gate.global_scale": "model-00004-of-00033.safetensors", + "model.llm.layers.17.attn.k_norm.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.19.mlp.gate.bias": "model-00004-of-00033.safetensors", + "model.llm.layers.20.attn.wv_dv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.21.mlp.gate.global_scale": "model-00004-of-00033.safetensors", + "model.llm.layers.22.mlp_norm.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.23.attn.wo_ud.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.23.attn.wq_du.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.23.attn.wv_dv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.24.attn.wq_du.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.26.attn.q_norm.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.27.attn.wq_du.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.28.mlp.experts.w2_weight.weight_packed": "model-00004-of-00033.safetensors", + "model.llm.layers.28.mlp.experts.w2_weight.weight_scale": "model-00004-of-00033.safetensors", + "model.llm.layers.32.attn_norm.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.32.mlp.gate.global_scale": "model-00004-of-00033.safetensors", + "model.llm.layers.34.mlp.shared_experts.shared_w2_weight": "model-00004-of-00033.safetensors", + "model.llm.layers.35.attn.wk_dv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.36.attn.wo_ud.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.39.attn.q_norm.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.4.mlp.experts.w13_weight.weight_packed": "model-00004-of-00033.safetensors", + "model.llm.layers.4.mlp.experts.w13_weight.weight_scale": "model-00004-of-00033.safetensors", + "model.llm.layers.4.mlp.gate.bias": "model-00004-of-00033.safetensors", + "model.llm.layers.41.attn.rel_logits_proj.proj": "model-00004-of-00033.safetensors", + "model.llm.layers.41.mlp.experts.w2_weight.weight_packed": "model-00004-of-00033.safetensors", + "model.llm.layers.41.mlp.experts.w2_weight.weight_scale": "model-00004-of-00033.safetensors", + "model.llm.layers.5.mlp_norm.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.7.attn.rel_logits_proj.proj": "model-00004-of-00033.safetensors", + "model.llm.layers.7.attn.wr_du.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.9.attn.rel_logits_proj.proj": "model-00004-of-00033.safetensors", + "model.visual.layers.linear_2.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.1.attn_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.11.attn.k_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.14.mlp.gate.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.18.attn_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.26.mlp.gate.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.28.attn.k_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.29.mlp_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.34.attn.v_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.37.attn.v_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.37.mlp.gate.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.38.attn.v_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.41.mlp.gate.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.5.attn.k_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.5.mlp.gate.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.8.attn.k_sconv.weight": "model-00004-of-00033.safetensors", + "model.llm.layers.0.attn.rel_logits_proj.proj": "model-00006-of-00033.safetensors", + "model.llm.layers.12.attn.wo_ud.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.14.attn.wq_du.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.16.attn.k_norm.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.25.mlp.experts.w2_weight.weight_packed": "model-00006-of-00033.safetensors", + "model.llm.layers.25.mlp.experts.w2_weight.weight_scale": "model-00006-of-00033.safetensors", + "model.llm.layers.27.attn.q_norm.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.28.attn.rel_logits_proj.proj": "model-00006-of-00033.safetensors", + "model.llm.layers.28.attn.wq_du.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.31.attn.wr_du.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.34.mlp_norm.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.35.attn.wr_du.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.36.mlp.experts.w2_weight.weight_packed": "model-00006-of-00033.safetensors", + "model.llm.layers.36.mlp.experts.w2_weight.weight_scale": "model-00006-of-00033.safetensors", + "model.llm.layers.36.mlp.shared_experts.shared_w2_weight": "model-00006-of-00033.safetensors", + "model.llm.layers.38.attn.wq_du.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.41.mlp.experts.w13_weight.weight_packed": "model-00006-of-00033.safetensors", + "model.llm.layers.41.mlp.experts.w13_weight.weight_scale": "model-00006-of-00033.safetensors", + "model.llm.layers.6.mlp.shared_experts.shared_w2_weight": "model-00006-of-00033.safetensors", + "model.llm.layers.8.attn.q_norm.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.8.attn.wo_ud.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.9.attn.wk_dv.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.25.attn.v_sconv.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.3.attn_sconv.weight": "model-00006-of-00033.safetensors", + "model.llm.layers.0.mlp.global_scale": "model-00007-of-00033.safetensors", + "model.llm.layers.11.attn.wk_dv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.11.mlp.experts.w2_weight.weight_packed": "model-00007-of-00033.safetensors", + "model.llm.layers.11.mlp.experts.w2_weight.weight_scale": "model-00007-of-00033.safetensors", + "model.llm.layers.11.mlp_norm.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.12.attn.wq_du.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.14.attn.wo_ud.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.15.attn.wk_dv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.17.attn.rel_logits_proj.proj": "model-00007-of-00033.safetensors", + "model.llm.layers.17.mlp.shared_experts.shared_w13_weight": "model-00007-of-00033.safetensors", + "model.llm.layers.2.attn.wo_ud.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.21.mlp.gate.bias": "model-00007-of-00033.safetensors", + "model.llm.layers.25.mlp.experts.w13_weight.weight_packed": "model-00007-of-00033.safetensors", + "model.llm.layers.25.mlp.experts.w13_weight.weight_scale": "model-00007-of-00033.safetensors", + "model.llm.layers.28.attn.wo_ud.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.28.mlp.gate.global_scale": "model-00007-of-00033.safetensors", + "model.llm.layers.3.attn.wk_dv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.3.mlp_norm.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.30.attn_norm.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.30.mlp.shared_experts.shared_w13_weight": "model-00007-of-00033.safetensors", + "model.llm.layers.32.attn.rel_logits_proj.proj": "model-00007-of-00033.safetensors", + "model.llm.layers.33.attn.wr_du.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.34.attn.wr_du.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.36.mlp.shared_experts.shared_w13_weight": "model-00007-of-00033.safetensors", + "model.llm.layers.38.attn.k_norm.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.6.attn.wo_ud.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.8.mlp.experts.w2_weight.weight_packed": "model-00007-of-00033.safetensors", + "model.llm.layers.8.mlp.experts.w2_weight.weight_scale": "model-00007-of-00033.safetensors", + "model.llm.layers.0.attn.v_sconv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.13.attn.v_sconv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.15.mlp_sconv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.19.mlp.gate.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.2.mlp_sconv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.24.mlp.gate.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.32.mlp_sconv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.35.attn_sconv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.35.mlp.gate.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.4.mlp_sconv.weight": "model-00007-of-00033.safetensors", + "model.llm.layers.0.attn.wk_dv.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.10.attn.wr_du.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.13.attn.wv_dv.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.15.attn.wr_du.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.15.mlp_norm.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.16.mlp.experts.w2_weight.weight_packed": "model-00008-of-00033.safetensors", + "model.llm.layers.16.mlp.experts.w2_weight.weight_scale": "model-00008-of-00033.safetensors", + "model.llm.layers.17.attn.wo_ud.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.19.mlp.shared_experts.shared_w13_weight": "model-00008-of-00033.safetensors", + "model.llm.layers.19.mlp.shared_experts.shared_w2_weight": "model-00008-of-00033.safetensors", + "model.llm.layers.2.attn.k_norm.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.2.attn.q_norm.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.2.mlp.shared_experts.shared_w2_weight": "model-00008-of-00033.safetensors", + "model.llm.layers.20.attn.wr_du.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.23.mlp_norm.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.24.mlp_norm.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.30.mlp.gate.global_scale": "model-00008-of-00033.safetensors", + "model.llm.layers.31.attn.q_norm.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.31.mlp.experts.w2_weight.weight_packed": "model-00008-of-00033.safetensors", + "model.llm.layers.31.mlp.experts.w2_weight.weight_scale": "model-00008-of-00033.safetensors", + "model.llm.layers.36.attn.wv_dv.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.37.mlp.experts.w13_weight.weight_packed": "model-00008-of-00033.safetensors", + "model.llm.layers.37.mlp.experts.w13_weight.weight_scale": "model-00008-of-00033.safetensors", + "model.llm.layers.38.attn.wk_dv.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.41.attn.wo_ud.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.5.attn.rel_logits_proj.proj": "model-00008-of-00033.safetensors", + "model.llm.layers.6.attn.rel_logits_proj.proj": "model-00008-of-00033.safetensors", + "model.llm.layers.9.attn.wo_ud.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.9.attn.wv_dv.weight": "model-00008-of-00033.safetensors", + "model.llm.norm.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.2.attn.v_sconv.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.32.attn.v_sconv.weight": "model-00008-of-00033.safetensors", + "model.llm.layers.0.attn.wo_ud.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.1.attn_norm.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.10.attn.wq_du.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.12.attn.rel_logits_proj.proj": "model-00009-of-00033.safetensors", + "model.llm.layers.17.mlp.experts.w2_weight.weight_packed": "model-00009-of-00033.safetensors", + "model.llm.layers.17.mlp.experts.w2_weight.weight_scale": "model-00009-of-00033.safetensors", + "model.llm.layers.19.attn.wv_dv.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.20.mlp.shared_experts.shared_w13_weight": "model-00009-of-00033.safetensors", + "model.llm.layers.21.attn.wo_ud.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.24.mlp.shared_experts.shared_w13_weight": "model-00009-of-00033.safetensors", + "model.llm.layers.25.attn.rel_logits_proj.proj": "model-00009-of-00033.safetensors", + "model.llm.layers.28.attn.k_norm.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.28.attn.wr_du.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.3.mlp.shared_experts.shared_w13_weight": "model-00009-of-00033.safetensors", + "model.llm.layers.30.attn.wo_ud.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.30.mlp.gate.bias": "model-00009-of-00033.safetensors", + "model.llm.layers.30.mlp_norm.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.32.mlp.experts.w2_weight.weight_packed": "model-00009-of-00033.safetensors", + "model.llm.layers.32.mlp.experts.w2_weight.weight_scale": "model-00009-of-00033.safetensors", + "model.llm.layers.35.attn.wq_du.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.35.mlp.experts.w13_weight.weight_packed": "model-00009-of-00033.safetensors", + "model.llm.layers.35.mlp.experts.w13_weight.weight_scale": "model-00009-of-00033.safetensors", + "model.llm.layers.35.mlp_norm.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.37.mlp.shared_experts.shared_w13_weight": "model-00009-of-00033.safetensors", + "model.llm.layers.40.attn.wo_ud.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.7.attn.q_norm.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.8.attn.wq_du.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.9.mlp.gate.bias": "model-00009-of-00033.safetensors", + "model.llm.layers.10.mlp.gate.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.13.attn_sconv.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.17.mlp_sconv.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.18.attn.k_sconv.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.19.attn.k_sconv.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.27.attn_sconv.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.31.attn.v_sconv.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.31.mlp_sconv.weight": "model-00009-of-00033.safetensors", + "model.llm.layers.0.attn.wr_du.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.0.attn.wv_dv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.1.attn.wo_ud.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.1.attn.wv_dv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.1.mlp_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.12.mlp.shared_experts.shared_w2_weight": "model-00010-of-00033.safetensors", + "model.llm.layers.14.attn_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.14.mlp.experts.w2_weight.weight_packed": "model-00010-of-00033.safetensors", + "model.llm.layers.14.mlp.experts.w2_weight.weight_scale": "model-00010-of-00033.safetensors", + "model.llm.layers.16.attn.wr_du.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.17.attn_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.18.attn.k_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.18.attn_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.19.attn_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.19.mlp_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.21.attn.wq_du.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.21.attn.wv_dv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.23.attn.q_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.24.attn.rel_logits_proj.proj": "model-00010-of-00033.safetensors", + "model.llm.layers.24.attn.wv_dv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.25.attn.wq_du.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.26.attn.wk_dv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.27.attn.wo_ud.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.28.mlp.shared_experts.shared_w13_weight": "model-00010-of-00033.safetensors", + "model.llm.layers.29.attn.wq_du.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.3.attn.k_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.30.attn.k_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.30.attn.q_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.31.attn.k_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.31.mlp_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.33.attn.wv_dv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.33.mlp.experts.w2_weight.weight_packed": "model-00010-of-00033.safetensors", + "model.llm.layers.33.mlp.experts.w2_weight.weight_scale": "model-00010-of-00033.safetensors", + "model.llm.layers.36.attn.wk_dv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.39.attn.rel_logits_proj.proj": "model-00010-of-00033.safetensors", + "model.llm.layers.39.attn.wr_du.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.39.mlp.shared_experts.shared_w2_weight": "model-00010-of-00033.safetensors", + "model.llm.layers.4.attn.rel_logits_proj.proj": "model-00010-of-00033.safetensors", + "model.llm.layers.4.mlp.gate.global_scale": "model-00010-of-00033.safetensors", + "model.llm.layers.5.attn.q_norm.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.5.mlp.experts.w13_weight.weight_packed": "model-00010-of-00033.safetensors", + "model.llm.layers.5.mlp.experts.w13_weight.weight_scale": "model-00010-of-00033.safetensors", + "model.llm.layers.5.mlp.gate.bias": "model-00010-of-00033.safetensors", + "model.llm.layers.8.mlp.shared_experts.shared_w2_weight": "model-00010-of-00033.safetensors", + "model.visual.layers.norm_2.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.10.mlp_sconv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.12.attn_sconv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.14.attn_sconv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.19.attn.v_sconv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.23.mlp.gate.bias": "model-00010-of-00033.safetensors", + "model.llm.layers.23.mlp.gate.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.28.attn.v_sconv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.30.mlp_sconv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.41.attn_sconv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.7.attn.k_sconv.weight": "model-00010-of-00033.safetensors", + "model.llm.layers.0.attn_norm.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.1.attn.k_norm.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.13.attn.wq_du.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.14.attn.rel_logits_proj.proj": "model-00011-of-00033.safetensors", + "model.llm.layers.14.mlp.shared_experts.shared_w2_weight": "model-00011-of-00033.safetensors", + "model.llm.layers.15.attn.wq_du.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.16.attn.wq_du.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.16.mlp.gate.bias": "model-00011-of-00033.safetensors", + "model.llm.layers.18.attn.wk_dv.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.2.mlp_norm.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.20.attn.wo_ud.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.20.mlp.gate.bias": "model-00011-of-00033.safetensors", + "model.llm.layers.20.mlp.gate.global_scale": "model-00011-of-00033.safetensors", + "model.llm.layers.22.attn.wo_ud.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.25.mlp.shared_experts.shared_w13_weight": "model-00011-of-00033.safetensors", + "model.llm.layers.26.mlp.experts.w13_weight.weight_packed": "model-00011-of-00033.safetensors", + "model.llm.layers.26.mlp.experts.w13_weight.weight_scale": "model-00011-of-00033.safetensors", + "model.llm.layers.27.attn.wr_du.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.27.mlp.gate.bias": "model-00011-of-00033.safetensors", + "model.llm.layers.3.mlp.shared_experts.shared_w2_weight": "model-00011-of-00033.safetensors", + "model.llm.layers.35.attn.q_norm.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.38.attn.q_norm.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.39.mlp.experts.w2_weight.weight_packed": "model-00011-of-00033.safetensors", + "model.llm.layers.39.mlp.experts.w2_weight.weight_scale": "model-00011-of-00033.safetensors", + "model.llm.layers.4.mlp.shared_experts.shared_w13_weight": "model-00011-of-00033.safetensors", + "model.llm.layers.40.attn.k_norm.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.6.mlp.experts.w2_weight.weight_packed": "model-00011-of-00033.safetensors", + "model.llm.layers.6.mlp.experts.w2_weight.weight_scale": "model-00011-of-00033.safetensors", + "model.llm.layers.8.attn.k_norm.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.8.attn.rel_logits_proj.proj": "model-00011-of-00033.safetensors", + "model.visual.layers.norm_0.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.12.attn.k_sconv.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.20.mlp_sconv.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.21.attn_sconv.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.29.mlp.gate.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.32.attn.k_sconv.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.35.mlp_sconv.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.41.attn.v_sconv.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.7.attn.v_sconv.weight": "model-00011-of-00033.safetensors", + "model.llm.layers.15.mlp.experts.w13_weight.weight_packed": "model-00012-of-00033.safetensors", + "model.llm.layers.15.mlp.experts.w13_weight.weight_scale": "model-00012-of-00033.safetensors", + "model.llm.layers.16.attn.wv_dv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.17.attn.wq_du.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.19.attn.wq_du.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.2.mlp.gate.global_scale": "model-00012-of-00033.safetensors", + "model.llm.layers.20.attn.k_norm.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.24.mlp.experts.w13_weight.weight_packed": "model-00012-of-00033.safetensors", + "model.llm.layers.24.mlp.experts.w13_weight.weight_scale": "model-00012-of-00033.safetensors", + "model.llm.layers.25.attn_norm.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.27.attn.k_norm.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.27.attn.wv_dv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.29.attn.wo_ud.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.33.mlp.gate.bias": "model-00012-of-00033.safetensors", + "model.llm.layers.33.mlp_norm.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.36.mlp.gate.global_scale": "model-00012-of-00033.safetensors", + "model.llm.layers.37.attn_norm.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.38.attn.wv_dv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.39.attn.wk_dv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.4.attn.wo_ud.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.5.attn_norm.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.0.attn_sconv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.15.attn.k_sconv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.22.mlp_sconv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.33.attn.v_sconv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.4.attn_sconv.weight": "model-00012-of-00033.safetensors", + "model.llm.layers.12.mlp.gate.bias": "model-00015-of-00033.safetensors", + "model.llm.layers.14.attn.wv_dv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.16.attn.wk_dv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.17.attn.q_norm.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.18.attn.wo_ud.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.18.mlp.gate.bias": "model-00015-of-00033.safetensors", + "model.llm.layers.19.attn.k_norm.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.21.mlp.experts.w2_weight.weight_packed": "model-00015-of-00033.safetensors", + "model.llm.layers.21.mlp.experts.w2_weight.weight_scale": "model-00015-of-00033.safetensors", + "model.llm.layers.22.attn.wv_dv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.22.mlp.shared_experts.shared_w13_weight": "model-00015-of-00033.safetensors", + "model.llm.layers.24.mlp.shared_experts.shared_w2_weight": "model-00015-of-00033.safetensors", + "model.llm.layers.26.attn.k_norm.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.27.mlp.shared_experts.shared_w13_weight": "model-00015-of-00033.safetensors", + "model.llm.layers.28.attn.q_norm.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.3.mlp.experts.w2_weight.weight_packed": "model-00015-of-00033.safetensors", + "model.llm.layers.3.mlp.experts.w2_weight.weight_scale": "model-00015-of-00033.safetensors", + "model.llm.layers.40.attn.q_norm.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.40.attn.wk_dv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.41.mlp.gate.global_scale": "model-00015-of-00033.safetensors", + "model.llm.layers.41.mlp_norm.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.5.attn.wv_dv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.6.mlp.gate.bias": "model-00015-of-00033.safetensors", + "model.llm.layers.7.attn.wo_ud.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.9.attn.k_norm.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.9.mlp.experts.w2_weight.weight_packed": "model-00015-of-00033.safetensors", + "model.llm.layers.9.mlp.experts.w2_weight.weight_scale": "model-00015-of-00033.safetensors", + "model.llm.layers.9.mlp.shared_experts.shared_w13_weight": "model-00015-of-00033.safetensors", + "model.llm.layers.9.mlp_norm.weight": "model-00015-of-00033.safetensors", + "model.visual.layers.linear_1.weight": "model-00015-of-00033.safetensors", + "model.visual.layers.linear_3.weight": "model-00015-of-00033.safetensors", + "model.visual.layers.norm_1.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.0.mlp_sconv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.23.attn_sconv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.24.attn.v_sconv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.28.mlp.gate.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.29.attn.v_sconv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.30.attn_sconv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.31.mlp.gate.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.39.attn.v_sconv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.39.attn_sconv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.40.attn.v_sconv.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.8.mlp.gate.weight": "model-00015-of-00033.safetensors", + "model.llm.layers.0.mlp.w2_md.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.1.attn.rel_logits_proj.proj": "model-00013-of-00033.safetensors", + "model.llm.layers.10.attn.k_norm.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.12.mlp.experts.w13_weight.weight_packed": "model-00013-of-00033.safetensors", + "model.llm.layers.12.mlp.experts.w13_weight.weight_scale": "model-00013-of-00033.safetensors", + "model.llm.layers.18.attn.wv_dv.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.20.attn.wq_du.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.20.mlp.shared_experts.shared_w2_weight": "model-00013-of-00033.safetensors", + "model.llm.layers.24.attn.wr_du.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.25.attn.wk_dv.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.26.mlp.shared_experts.shared_w13_weight": "model-00013-of-00033.safetensors", + "model.llm.layers.29.mlp.experts.w2_weight.weight_packed": "model-00013-of-00033.safetensors", + "model.llm.layers.29.mlp.experts.w2_weight.weight_scale": "model-00013-of-00033.safetensors", + "model.llm.layers.3.attn.wq_du.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.33.attn.wq_du.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.37.mlp.gate.global_scale": "model-00013-of-00033.safetensors", + "model.llm.layers.38.attn_norm.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.39.attn.wo_ud.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.40.mlp.experts.w2_weight.weight_packed": "model-00013-of-00033.safetensors", + "model.llm.layers.40.mlp.experts.w2_weight.weight_scale": "model-00013-of-00033.safetensors", + "model.llm.layers.40.mlp.shared_experts.shared_w13_weight": "model-00013-of-00033.safetensors", + "model.llm.layers.6.attn.q_norm.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.6.mlp.gate.global_scale": "model-00013-of-00033.safetensors", + "model.llm.layers.9.attn_norm.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.14.attn.v_sconv.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.33.mlp.gate.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.4.attn.v_sconv.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.6.attn_sconv.weight": "model-00013-of-00033.safetensors", + "model.llm.layers.0.mlp_norm.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.1.attn.q_norm.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.10.mlp.gate.bias": "model-00014-of-00033.safetensors", + "model.llm.layers.12.attn.wk_dv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.13.attn.wo_ud.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.14.mlp.experts.w13_weight.weight_packed": "model-00014-of-00033.safetensors", + "model.llm.layers.14.mlp.experts.w13_weight.weight_scale": "model-00014-of-00033.safetensors", + "model.llm.layers.16.attn.wo_ud.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.2.mlp.experts.w2_weight.weight_packed": "model-00014-of-00033.safetensors", + "model.llm.layers.2.mlp.experts.w2_weight.weight_scale": "model-00014-of-00033.safetensors", + "model.llm.layers.20.attn.q_norm.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.23.attn.k_norm.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.25.mlp.shared_experts.shared_w2_weight": "model-00014-of-00033.safetensors", + "model.llm.layers.28.attn.wk_dv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.29.attn.wr_du.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.3.attn.rel_logits_proj.proj": "model-00014-of-00033.safetensors", + "model.llm.layers.31.mlp.shared_experts.shared_w13_weight": "model-00014-of-00033.safetensors", + "model.llm.layers.34.attn.wo_ud.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.36.attn_norm.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.38.attn.wo_ud.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.38.attn.wr_du.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.38.mlp.experts.w2_weight.weight_packed": "model-00014-of-00033.safetensors", + "model.llm.layers.38.mlp.experts.w2_weight.weight_scale": "model-00014-of-00033.safetensors", + "model.llm.layers.38.mlp.shared_experts.shared_w2_weight": "model-00014-of-00033.safetensors", + "model.llm.layers.4.attn.wr_du.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.4.attn.wv_dv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.7.attn.wv_dv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.8.mlp.gate.global_scale": "model-00014-of-00033.safetensors", + "model.llm.layers.9.mlp.shared_experts.shared_w2_weight": "model-00014-of-00033.safetensors", + "model.llm.layers.1.mlp_sconv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.12.attn.v_sconv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.19.mlp_sconv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.20.attn.v_sconv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.21.mlp.gate.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.23.mlp_sconv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.28.attn_sconv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.41.attn.k_sconv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.6.attn.v_sconv.weight": "model-00014-of-00033.safetensors", + "model.llm.layers.1.attn.wr_du.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.11.attn.wo_ud.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.13.attn.k_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.16.mlp_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.18.attn.wr_du.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.2.attn.rel_logits_proj.proj": "model-00016-of-00033.safetensors", + "model.llm.layers.21.attn.q_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.21.mlp.shared_experts.shared_w2_weight": "model-00016-of-00033.safetensors", + "model.llm.layers.23.attn_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.23.mlp.experts.w2_weight.weight_packed": "model-00016-of-00033.safetensors", + "model.llm.layers.23.mlp.experts.w2_weight.weight_scale": "model-00016-of-00033.safetensors", + "model.llm.layers.23.mlp.shared_experts.shared_w13_weight": "model-00016-of-00033.safetensors", + "model.llm.layers.24.attn.q_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.26.attn.wo_ud.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.26.attn.wv_dv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.27.mlp_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.29.attn_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.30.mlp.experts.w13_weight.weight_packed": "model-00016-of-00033.safetensors", + "model.llm.layers.30.mlp.experts.w13_weight.weight_scale": "model-00016-of-00033.safetensors", + "model.llm.layers.31.attn.wq_du.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.34.mlp.shared_experts.shared_w13_weight": "model-00016-of-00033.safetensors", + "model.llm.layers.35.attn.rel_logits_proj.proj": "model-00016-of-00033.safetensors", + "model.llm.layers.36.attn.wq_du.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.37.attn.wq_du.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.38.mlp.shared_experts.shared_w13_weight": "model-00016-of-00033.safetensors", + "model.llm.layers.39.attn.k_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.39.attn.wq_du.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.4.attn.q_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.4.mlp.shared_experts.shared_w2_weight": "model-00016-of-00033.safetensors", + "model.llm.layers.40.attn.wq_du.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.5.attn.wr_du.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.6.attn.k_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.6.mlp_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.7.attn.k_norm.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.8.attn.wv_dv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.1.attn.k_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.16.mlp.gate.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.18.mlp_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.19.attn_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.20.attn.k_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.27.attn.k_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.27.attn.v_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.28.mlp_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.3.attn.v_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.33.mlp_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.40.attn.k_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.40.mlp.gate.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.9.attn.v_sconv.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.9.mlp.gate.global_scale": "model-00016-of-00033.safetensors", + "model.llm.layers.9.mlp.gate.weight": "model-00016-of-00033.safetensors", + "model.llm.layers.1.attn.wk_dv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.1.mlp.w2_md.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.10.attn.rel_logits_proj.proj": "model-00017-of-00033.safetensors", + "model.llm.layers.10.attn.wk_dv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.17.attn.wr_du.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.22.attn.wk_dv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.24.attn_norm.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.24.mlp.gate.global_scale": "model-00017-of-00033.safetensors", + "model.llm.layers.33.mlp.experts.w13_weight.weight_packed": "model-00017-of-00033.safetensors", + "model.llm.layers.33.mlp.experts.w13_weight.weight_scale": "model-00017-of-00033.safetensors", + "model.llm.layers.35.attn_norm.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.35.mlp.experts.w2_weight.weight_packed": "model-00017-of-00033.safetensors", + "model.llm.layers.35.mlp.experts.w2_weight.weight_scale": "model-00017-of-00033.safetensors", + "model.llm.layers.36.mlp_norm.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.40.mlp_norm.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.41.attn.wr_du.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.41.attn.wv_dv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.41.mlp.shared_experts.shared_w13_weight": "model-00017-of-00033.safetensors", + "model.llm.layers.8.attn.wk_dv.weight": "model-00017-of-00033.safetensors", + "model.visual.layers.linear_0.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.24.attn_sconv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.26.mlp_sconv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.34.mlp_sconv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.38.mlp.gate.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.39.mlp_sconv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.40.mlp_sconv.weight": "model-00017-of-00033.safetensors", + "model.llm.layers.1.mlp.global_scale": "model-00019-of-00033.safetensors", + "model.llm.layers.11.mlp.gate.global_scale": "model-00019-of-00033.safetensors", + "model.llm.layers.12.attn.q_norm.weight": "model-00019-of-00033.safetensors", + "model.llm.layers.12.mlp.experts.w2_weight.weight_packed": "model-00019-of-00033.safetensors", + "model.llm.layers.12.mlp.experts.w2_weight.weight_scale": "model-00019-of-00033.safetensors", + "model.llm.layers.12.mlp.shared_experts.shared_w13_weight": "model-00019-of-00033.safetensors", + "model.llm.layers.19.mlp.experts.w13_weight.weight_packed": "model-00019-of-00033.safetensors", + "model.llm.layers.19.mlp.experts.w13_weight.weight_scale": "model-00019-of-00033.safetensors", + "model.llm.layers.22.attn_norm.weight": "model-00019-of-00033.safetensors", + "model.llm.layers.29.attn.q_norm.weight": "model-00019-of-00033.safetensors", + "model.llm.layers.29.mlp.shared_experts.shared_w2_weight": "model-00019-of-00033.safetensors", + "model.llm.layers.31.attn.wk_dv.weight": "model-00019-of-00033.safetensors", + "model.llm.layers.31.attn.wv_dv.weight": "model-00019-of-00033.safetensors", + "model.llm.layers.32.attn.wk_dv.weight": "model-00019-of-00033.safetensors", + "model.llm.layers.32.mlp.shared_experts.shared_w13_weight": "model-00019-of-00033.safetensors", + "model.llm.layers.34.attn.q_norm.weight": "model-00019-of-00033.safetensors", + "model.llm.layers.37.mlp.gate.bias": "model-00019-of-00033.safetensors", + "model.llm.layers.7.attn_sconv.weight": "model-00019-of-00033.safetensors", + "model.llm.layers.1.attn.wq_du.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.10.mlp.experts.w2_weight.weight_packed": "model-00018-of-00033.safetensors", + "model.llm.layers.10.mlp.experts.w2_weight.weight_scale": "model-00018-of-00033.safetensors", + "model.llm.layers.13.attn_norm.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.13.mlp.experts.w13_weight.weight_packed": "model-00018-of-00033.safetensors", + "model.llm.layers.13.mlp.experts.w13_weight.weight_scale": "model-00018-of-00033.safetensors", + "model.llm.layers.13.mlp.experts.w2_weight.weight_packed": "model-00018-of-00033.safetensors", + "model.llm.layers.13.mlp.experts.w2_weight.weight_scale": "model-00018-of-00033.safetensors", + "model.llm.layers.14.mlp.gate.bias": "model-00018-of-00033.safetensors", + "model.llm.layers.17.mlp.gate.bias": "model-00018-of-00033.safetensors", + "model.llm.layers.18.mlp.gate.global_scale": "model-00018-of-00033.safetensors", + "model.llm.layers.18.mlp.shared_experts.shared_w13_weight": "model-00018-of-00033.safetensors", + "model.llm.layers.24.attn.wo_ud.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.33.attn.q_norm.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.11.mlp_sconv.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.15.attn_sconv.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.20.mlp.gate.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.21.attn.k_sconv.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.21.mlp_sconv.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.25.mlp.gate.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.30.attn.k_sconv.weight": "model-00018-of-00033.safetensors", + "model.llm.layers.11.attn.rel_logits_proj.proj": "model-00021-of-00033.safetensors", + "model.llm.layers.13.mlp.shared_experts.shared_w2_weight": "model-00021-of-00033.safetensors", + "model.llm.layers.16.attn.q_norm.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.17.attn.wk_dv.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.17.attn.wv_dv.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.22.attn.wr_du.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.3.attn.q_norm.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.33.attn_norm.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.36.attn.q_norm.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.39.mlp.experts.w13_weight.weight_packed": "model-00021-of-00033.safetensors", + "model.llm.layers.39.mlp.experts.w13_weight.weight_scale": "model-00021-of-00033.safetensors", + "model.llm.layers.4.mlp.experts.w2_weight.weight_packed": "model-00021-of-00033.safetensors", + "model.llm.layers.4.mlp.experts.w2_weight.weight_scale": "model-00021-of-00033.safetensors", + "model.llm.layers.40.mlp.gate.global_scale": "model-00021-of-00033.safetensors", + "model.llm.layers.41.attn.k_norm.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.10.attn.k_sconv.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.17.attn.v_sconv.weight": "model-00021-of-00033.safetensors", + "model.llm.layers.1.mlp.w13_dn.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.12.attn.k_norm.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.12.attn.wr_du.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.15.mlp.experts.w2_weight.weight_packed": "model-00020-of-00033.safetensors", + "model.llm.layers.15.mlp.experts.w2_weight.weight_scale": "model-00020-of-00033.safetensors", + "model.llm.layers.24.attn.k_norm.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.25.attn.wr_du.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.26.mlp.experts.w2_weight.weight_packed": "model-00020-of-00033.safetensors", + "model.llm.layers.26.mlp.experts.w2_weight.weight_scale": "model-00020-of-00033.safetensors", + "model.llm.layers.27.attn.rel_logits_proj.proj": "model-00020-of-00033.safetensors", + "model.llm.layers.28.mlp_norm.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.35.attn.wv_dv.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.37.mlp_norm.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.39.mlp.gate.bias": "model-00020-of-00033.safetensors", + "model.llm.layers.4.attn.k_norm.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.40.attn_norm.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.6.attn_norm.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.7.mlp.experts.w13_weight.weight_packed": "model-00020-of-00033.safetensors", + "model.llm.layers.7.mlp.experts.w13_weight.weight_scale": "model-00020-of-00033.safetensors", + "model.llm.layers.10.attn_sconv.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.21.attn.v_sconv.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.31.attn_sconv.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.36.mlp.gate.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.6.attn.k_sconv.weight": "model-00020-of-00033.safetensors", + "model.llm.layers.10.attn.wo_ud.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.10.mlp.shared_experts.shared_w2_weight": "model-00022-of-00033.safetensors", + "model.llm.layers.11.attn.k_norm.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.11.attn_norm.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.14.attn.wr_du.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.14.mlp_norm.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.15.attn.k_norm.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.15.attn.wv_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.18.mlp.experts.w13_weight.weight_packed": "model-00022-of-00033.safetensors", + "model.llm.layers.18.mlp.experts.w13_weight.weight_scale": "model-00022-of-00033.safetensors", + "model.llm.layers.19.attn.rel_logits_proj.proj": "model-00022-of-00033.safetensors", + "model.llm.layers.19.mlp.gate.global_scale": "model-00022-of-00033.safetensors", + "model.llm.layers.2.attn.wk_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.20.attn_norm.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.23.attn.rel_logits_proj.proj": "model-00022-of-00033.safetensors", + "model.llm.layers.24.attn.wk_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.24.mlp.experts.w2_weight.weight_packed": "model-00022-of-00033.safetensors", + "model.llm.layers.24.mlp.experts.w2_weight.weight_scale": "model-00022-of-00033.safetensors", + "model.llm.layers.25.attn.wv_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.25.mlp.gate.bias": "model-00022-of-00033.safetensors", + "model.llm.layers.26.attn.wr_du.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.26.mlp.gate.bias": "model-00022-of-00033.safetensors", + "model.llm.layers.28.attn_norm.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.28.mlp.shared_experts.shared_w2_weight": "model-00022-of-00033.safetensors", + "model.llm.layers.29.attn.wk_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.29.mlp_norm.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.31.mlp.gate.bias": "model-00022-of-00033.safetensors", + "model.llm.layers.31.mlp.gate.global_scale": "model-00022-of-00033.safetensors", + "model.llm.layers.32.attn.wr_du.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.32.attn.wv_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.33.mlp.shared_experts.shared_w13_weight": "model-00022-of-00033.safetensors", + "model.llm.layers.34.mlp.gate.bias": "model-00022-of-00033.safetensors", + "model.llm.layers.35.attn.k_norm.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.35.attn.wo_ud.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.35.mlp.gate.global_scale": "model-00022-of-00033.safetensors", + "model.llm.layers.35.mlp.shared_experts.shared_w13_weight": "model-00022-of-00033.safetensors", + "model.llm.layers.40.attn.rel_logits_proj.proj": "model-00022-of-00033.safetensors", + "model.llm.layers.41.mlp.shared_experts.shared_w2_weight": "model-00022-of-00033.safetensors", + "model.llm.layers.5.attn.wk_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.5.mlp.experts.w2_weight.weight_packed": "model-00022-of-00033.safetensors", + "model.llm.layers.5.mlp.experts.w2_weight.weight_scale": "model-00022-of-00033.safetensors", + "model.llm.layers.6.attn.wk_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.6.attn.wq_du.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.6.attn.wv_dv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.7.mlp.gate.bias": "model-00022-of-00033.safetensors", + "model.llm.layers.8.mlp.gate.bias": "model-00022-of-00033.safetensors", + "model.llm.layers.9.attn.wq_du.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.16.attn_sconv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.24.mlp_sconv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.29.attn.k_sconv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.38.attn.k_sconv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.9.attn.k_sconv.weight": "model-00022-of-00033.safetensors", + "model.llm.layers.10.attn.wv_dv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.10.mlp.gate.global_scale": "model-00023-of-00033.safetensors", + "model.llm.layers.10.mlp.shared_experts.shared_w13_weight": "model-00023-of-00033.safetensors", + "model.llm.layers.11.attn.wr_du.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.12.attn.wv_dv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.20.mlp.experts.w13_weight.weight_packed": "model-00023-of-00033.safetensors", + "model.llm.layers.20.mlp.experts.w13_weight.weight_scale": "model-00023-of-00033.safetensors", + "model.llm.layers.21.attn.wr_du.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.23.mlp.shared_experts.shared_w2_weight": "model-00023-of-00033.safetensors", + "model.llm.layers.25.attn.q_norm.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.26.mlp.shared_experts.shared_w2_weight": "model-00023-of-00033.safetensors", + "model.llm.layers.26.mlp_norm.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.3.attn.wv_dv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.32.attn.k_norm.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.37.attn.q_norm.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.39.mlp.gate.global_scale": "model-00023-of-00033.safetensors", + "model.llm.layers.41.attn.q_norm.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.41.mlp.gate.bias": "model-00023-of-00033.safetensors", + "model.llm.layers.7.attn.wk_dv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.7.mlp.shared_experts.shared_w2_weight": "model-00023-of-00033.safetensors", + "model.llm.layers.8.mlp.shared_experts.shared_w13_weight": "model-00023-of-00033.safetensors", + "model.llm.layers.9.mlp.experts.w13_weight.weight_packed": "model-00023-of-00033.safetensors", + "model.llm.layers.9.mlp.experts.w13_weight.weight_scale": "model-00023-of-00033.safetensors", + "model.llm.layers.22.mlp.gate.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.23.attn.v_sconv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.32.attn_sconv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.33.attn.k_sconv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.5.mlp_sconv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.6.mlp.gate.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.7.mlp_sconv.weight": "model-00023-of-00033.safetensors", + "model.llm.layers.10.attn_norm.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.11.attn.wv_dv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.11.mlp.gate.bias": "model-00024-of-00033.safetensors", + "model.llm.layers.12.attn_norm.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.13.mlp.shared_experts.shared_w13_weight": "model-00024-of-00033.safetensors", + "model.llm.layers.14.mlp.gate.global_scale": "model-00024-of-00033.safetensors", + "model.llm.layers.16.mlp.shared_experts.shared_w13_weight": "model-00024-of-00033.safetensors", + "model.llm.layers.17.mlp.experts.w13_weight.weight_packed": "model-00024-of-00033.safetensors", + "model.llm.layers.17.mlp.experts.w13_weight.weight_scale": "model-00024-of-00033.safetensors", + "model.llm.layers.19.attn.wk_dv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.19.attn.wr_du.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.2.attn_norm.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.28.attn.wv_dv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.3.mlp.gate.bias": "model-00024-of-00033.safetensors", + "model.llm.layers.31.attn_norm.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.32.mlp.experts.w13_weight.weight_packed": "model-00024-of-00033.safetensors", + "model.llm.layers.32.mlp.experts.w13_weight.weight_scale": "model-00024-of-00033.safetensors", + "model.llm.layers.32.mlp.shared_experts.shared_w2_weight": "model-00024-of-00033.safetensors", + "model.llm.layers.33.attn.wk_dv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.33.attn.wo_ud.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.34.attn.rel_logits_proj.proj": "model-00024-of-00033.safetensors", + "model.llm.layers.35.mlp.gate.bias": "model-00024-of-00033.safetensors", + "model.llm.layers.35.mlp.shared_experts.shared_w2_weight": "model-00024-of-00033.safetensors", + "model.llm.layers.37.attn.rel_logits_proj.proj": "model-00024-of-00033.safetensors", + "model.llm.layers.39.mlp_norm.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.40.attn.wv_dv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.40.mlp.gate.bias": "model-00024-of-00033.safetensors", + "model.llm.layers.6.mlp.shared_experts.shared_w13_weight": "model-00024-of-00033.safetensors", + "model.llm.layers.8.mlp_norm.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.9.attn.q_norm.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.12.mlp.gate.global_scale": "model-00024-of-00033.safetensors", + "model.llm.layers.12.mlp.gate.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.14.mlp_sconv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.16.attn.k_sconv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.17.mlp.gate.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.2.attn.k_sconv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.23.attn.k_sconv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.40.attn_sconv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.5.attn.v_sconv.weight": "model-00024-of-00033.safetensors", + "model.llm.layers.10.mlp.experts.w13_weight.weight_packed": "model-00025-of-00033.safetensors", + "model.llm.layers.10.mlp.experts.w13_weight.weight_scale": "model-00025-of-00033.safetensors", + "model.llm.layers.15.attn.wo_ud.weight": "model-00025-of-00033.safetensors", + "model.llm.layers.23.mlp.experts.w13_weight.weight_packed": "model-00025-of-00033.safetensors", + "model.llm.layers.23.mlp.experts.w13_weight.weight_scale": "model-00025-of-00033.safetensors", + "model.llm.layers.3.mlp.gate.global_scale": "model-00025-of-00033.safetensors", + "model.llm.layers.31.attn.wo_ud.weight": "model-00025-of-00033.safetensors", + "model.llm.layers.30.mlp.gate.weight": "model-00025-of-00033.safetensors", + "model.llm.layers.36.attn_sconv.weight": "model-00025-of-00033.safetensors", + "model.llm.layers.5.attn_sconv.weight": "model-00025-of-00033.safetensors", + "model.mtp.layers.0.hidden_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.input_proj.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.rel_logits_proj.proj": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.wk_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.wo_ud.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.wq_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.wr_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.wv_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.mlp.global_scale": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.mlp.w13_dn.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.mlp.w2_md.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.mlp_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.hidden_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.input_proj.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.rel_logits_proj.proj": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.wk_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.wo_ud.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.wq_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.wr_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.wv_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.mlp.global_scale": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.mlp.w13_dn.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.mlp.w2_md.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.mlp_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.hidden_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.input_proj.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.rel_logits_proj.proj": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.wk_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.wo_ud.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.wq_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.wr_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.wv_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.mlp.global_scale": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.mlp.w13_dn.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.mlp.w2_md.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.mlp_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.hidden_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.input_proj.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.rel_logits_proj.proj": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.wk_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.wo_ud.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.wq_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.wr_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.wv_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.mlp.global_scale": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.mlp.w13_dn.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.mlp.w2_md.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.mlp_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.hidden_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.input_proj.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.rel_logits_proj.proj": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.wk_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.wo_ud.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.wq_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.wr_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.wv_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.mlp.global_scale": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.mlp.w13_dn.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.mlp.w2_md.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.mlp_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.hidden_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.input_proj.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.rel_logits_proj.proj": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.wk_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.wo_ud.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.wq_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.wr_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.wv_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.mlp.global_scale": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.mlp.w13_dn.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.mlp.w2_md.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.mlp_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.hidden_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.input_proj.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.rel_logits_proj.proj": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.wk_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.wo_ud.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.wq_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.wr_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.wv_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.mlp.global_scale": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.mlp.w13_dn.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.mlp.w2_md.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.mlp_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.hidden_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.input_proj.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.rel_logits_proj.proj": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.wk_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.wo_ud.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.wq_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.wr_du.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.wv_dv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.mlp.global_scale": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.mlp.w13_dn.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.mlp.w2_md.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.mlp_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.embed_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.k_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn.v_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.attn_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.0.transformer_block.mlp_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.embed_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.k_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn.v_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.attn_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.1.transformer_block.mlp_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.embed_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.k_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn.v_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.attn_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.2.transformer_block.mlp_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.embed_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.k_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn.v_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.attn_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.3.transformer_block.mlp_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.embed_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.k_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn.v_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.attn_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.4.transformer_block.mlp_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.embed_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.k_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn.v_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.attn_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.5.transformer_block.mlp_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.embed_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.k_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn.v_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.attn_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.6.transformer_block.mlp_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.embed_norm.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.k_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn.v_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.attn_sconv.weight": "model-00033-of-00033.safetensors", + "model.mtp.layers.7.transformer_block.mlp_sconv.weight": "model-00033-of-00033.safetensors", + "model.llm.layers.10.mlp_norm.weight": "model-00026-of-00033.safetensors", + "model.llm.layers.14.attn.wk_dv.weight": "model-00026-of-00033.safetensors", + "model.llm.layers.17.mlp.gate.global_scale": "model-00026-of-00033.safetensors", + "model.llm.layers.20.mlp.experts.w2_weight.weight_packed": "model-00026-of-00033.safetensors", + "model.llm.layers.20.mlp.experts.w2_weight.weight_scale": "model-00026-of-00033.safetensors", + "model.llm.layers.34.mlp.experts.w2_weight.weight_packed": "model-00026-of-00033.safetensors", + "model.llm.layers.34.mlp.experts.w2_weight.weight_scale": "model-00026-of-00033.safetensors", + "model.llm.layers.38.mlp.gate.bias": "model-00026-of-00033.safetensors", + "model.llm.layers.40.mlp.experts.w13_weight.weight_packed": "model-00026-of-00033.safetensors", + "model.llm.layers.40.mlp.experts.w13_weight.weight_scale": "model-00026-of-00033.safetensors", + "model.llm.layers.4.attn.k_sconv.weight": "model-00026-of-00033.safetensors", + "model.llm.layers.2.attn.wr_du.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.21.mlp.experts.w13_weight.weight_packed": "model-00028-of-00033.safetensors", + "model.llm.layers.21.mlp.experts.w13_weight.weight_scale": "model-00028-of-00033.safetensors", + "model.llm.layers.21.mlp.shared_experts.shared_w13_weight": "model-00028-of-00033.safetensors", + "model.llm.layers.22.attn.rel_logits_proj.proj": "model-00028-of-00033.safetensors", + "model.llm.layers.22.mlp.experts.w13_weight.weight_packed": "model-00028-of-00033.safetensors", + "model.llm.layers.22.mlp.experts.w13_weight.weight_scale": "model-00028-of-00033.safetensors", + "model.llm.layers.25.attn.k_norm.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.29.attn.rel_logits_proj.proj": "model-00028-of-00033.safetensors", + "model.llm.layers.29.mlp.shared_experts.shared_w13_weight": "model-00028-of-00033.safetensors", + "model.llm.layers.30.attn.wv_dv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.34.attn.k_norm.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.36.attn.k_norm.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.37.attn.k_norm.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.38.mlp_norm.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.39.attn.wv_dv.weight": "model-00028-of-00033.safetensors", + "model.visual.final_norm.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.11.attn.v_sconv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.15.attn.v_sconv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.2.attn_sconv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.20.attn_sconv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.3.mlp_sconv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.38.attn_sconv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.39.attn.k_sconv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.39.mlp.gate.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.7.mlp.gate.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.8.mlp_sconv.weight": "model-00028-of-00033.safetensors", + "model.llm.layers.11.attn.q_norm.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.15.attn.q_norm.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.17.mlp_norm.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.18.mlp.experts.w2_weight.weight_packed": "model-00027-of-00033.safetensors", + "model.llm.layers.18.mlp.experts.w2_weight.weight_scale": "model-00027-of-00033.safetensors", + "model.llm.layers.28.mlp.gate.bias": "model-00027-of-00033.safetensors", + "model.llm.layers.29.mlp.gate.bias": "model-00027-of-00033.safetensors", + "model.llm.layers.3.mlp.experts.w13_weight.weight_packed": "model-00027-of-00033.safetensors", + "model.llm.layers.3.mlp.experts.w13_weight.weight_scale": "model-00027-of-00033.safetensors", + "model.llm.layers.30.attn.rel_logits_proj.proj": "model-00027-of-00033.safetensors", + "model.llm.layers.30.attn.wk_dv.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.31.mlp.shared_experts.shared_w2_weight": "model-00027-of-00033.safetensors", + "model.llm.layers.34.attn.wq_du.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.37.mlp.experts.w2_weight.weight_packed": "model-00027-of-00033.safetensors", + "model.llm.layers.37.mlp.experts.w2_weight.weight_scale": "model-00027-of-00033.safetensors", + "model.llm.layers.40.mlp.shared_experts.shared_w2_weight": "model-00027-of-00033.safetensors", + "model.llm.layers.41.attn.wq_du.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.5.attn.wq_du.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.7.attn.wq_du.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.7.attn_norm.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.13.mlp.gate.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.25.attn_sconv.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.41.mlp_sconv.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.8.attn.v_sconv.weight": "model-00027-of-00033.safetensors", + "model.llm.layers.11.attn.wq_du.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.15.mlp.gate.global_scale": "model-00029-of-00033.safetensors", + "model.llm.layers.29.mlp.experts.w13_weight.weight_packed": "model-00029-of-00033.safetensors", + "model.llm.layers.29.mlp.experts.w13_weight.weight_scale": "model-00029-of-00033.safetensors", + "model.llm.layers.33.mlp.shared_experts.shared_w2_weight": "model-00029-of-00033.safetensors", + "model.llm.layers.36.mlp.experts.w13_weight.weight_packed": "model-00029-of-00033.safetensors", + "model.llm.layers.36.mlp.experts.w13_weight.weight_scale": "model-00029-of-00033.safetensors", + "model.llm.layers.37.attn.wv_dv.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.4.mlp_norm.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.41.attn.wk_dv.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.5.attn.k_norm.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.7.mlp.shared_experts.shared_w13_weight": "model-00029-of-00033.safetensors", + "model.llm.layers.7.mlp_norm.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.8.attn_norm.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.13.mlp_sconv.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.17.attn.k_sconv.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.22.attn.v_sconv.weight": "model-00029-of-00033.safetensors", + "model.llm.layers.15.attn_norm.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.16.attn_norm.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.22.attn.q_norm.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.22.mlp.experts.w2_weight.weight_packed": "model-00032-of-00033.safetensors", + "model.llm.layers.22.mlp.experts.w2_weight.weight_scale": "model-00032-of-00033.safetensors", + "model.llm.layers.22.mlp.gate.bias": "model-00032-of-00033.safetensors", + "model.llm.layers.26.attn.wq_du.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.26.mlp.gate.global_scale": "model-00032-of-00033.safetensors", + "model.llm.layers.27.mlp.experts.w13_weight.weight_packed": "model-00032-of-00033.safetensors", + "model.llm.layers.27.mlp.experts.w13_weight.weight_scale": "model-00032-of-00033.safetensors", + "model.llm.layers.29.mlp.gate.global_scale": "model-00032-of-00033.safetensors", + "model.llm.layers.30.mlp.shared_experts.shared_w2_weight": "model-00032-of-00033.safetensors", + "model.llm.layers.5.attn.wo_ud.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.16.attn.v_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.17.attn_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.22.attn_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.27.mlp_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.30.attn.v_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.31.attn.k_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.32.mlp.gate.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.35.attn.k_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.37.attn.k_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.37.attn_sconv.weight": "model-00032-of-00033.safetensors", + "model.llm.layers.18.mlp_norm.weight": "model-00030-of-00033.safetensors", + "model.llm.layers.2.attn.wq_du.weight": "model-00030-of-00033.safetensors", + "model.llm.layers.2.mlp.experts.w13_weight.weight_packed": "model-00030-of-00033.safetensors", + "model.llm.layers.2.mlp.experts.w13_weight.weight_scale": "model-00030-of-00033.safetensors", + "model.llm.layers.2.mlp.gate.bias": "model-00030-of-00033.safetensors", + "model.llm.layers.2.mlp.shared_experts.shared_w13_weight": "model-00030-of-00033.safetensors", + "model.llm.layers.21.attn_norm.weight": "model-00030-of-00033.safetensors", + "model.llm.layers.22.mlp.shared_experts.shared_w2_weight": "model-00030-of-00033.safetensors", + "model.llm.layers.28.mlp.experts.w13_weight.weight_packed": "model-00030-of-00033.safetensors", + "model.llm.layers.28.mlp.experts.w13_weight.weight_scale": "model-00030-of-00033.safetensors", + "model.llm.layers.32.attn.q_norm.weight": "model-00030-of-00033.safetensors", + "model.llm.layers.7.mlp.gate.global_scale": "model-00030-of-00033.safetensors", + "model.llm.layers.11.attn_sconv.weight": "model-00030-of-00033.safetensors", + "model.llm.layers.13.attn.k_sconv.weight": "model-00030-of-00033.safetensors", + "model.llm.layers.26.attn.v_sconv.weight": "model-00030-of-00033.safetensors", + "model.llm.layers.34.mlp.gate.weight": "model-00030-of-00033.safetensors", + "model.llm.layers.11.mlp.shared_experts.shared_w2_weight": "model-00031-of-00033.safetensors", + "model.llm.layers.13.mlp.gate.global_scale": "model-00031-of-00033.safetensors", + "model.llm.layers.6.mlp.experts.w13_weight.weight_packed": "model-00031-of-00033.safetensors", + "model.llm.layers.6.mlp.experts.w13_weight.weight_scale": "model-00031-of-00033.safetensors", + "model.llm.layers.8.mlp.experts.w13_weight.weight_packed": "model-00031-of-00033.safetensors", + "model.llm.layers.8.mlp.experts.w13_weight.weight_scale": "model-00031-of-00033.safetensors" + } +} \ No newline at end of file diff --git a/processor_config.json b/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5119c4247a30de9fea35fe269cc786db37b8d67b --- /dev/null +++ b/processor_config.json @@ -0,0 +1,46 @@ +{ + "audio_token": "<|unused_200053|>", + "audio_bos_token": "<|content_audio_input|>", + "dmel_max_value": 2.0, + "dmel_min_value": -7.0, + "feature_extractor": { + "audio_token_duration_s": 0.05, + "feature_extractor_type": "InklingFeatureExtractor", + "feature_size": 80, + "hop_length": 800, + "n_fft": 1600, + "padding_side": "right", + "padding_value": 0.0, + "return_attention_mask": true, + "sampling_rate": 16000, + "window_size": 1600, + "window_size_multiplier": 2.0 + }, + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "InklingImageProcessor", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "height": 40, + "width": 40 + } + }, + "image_token": "<|unused_200054|>", + "image_bos_token": "<|content_image|>", + "num_dmel_bins": 16, + "processor_class": "InklingProcessor" +} diff --git a/quantization_config.json b/quantization_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b1a85ddb232661ad40f249e378bc7ded2645636e --- /dev/null +++ b/quantization_config.json @@ -0,0 +1,1963 @@ +{ + "quant_method": "auto-round", + "packing_format": "auto_round:llm_compressor", + "bits": 4, + "group_size": 32, + "sym": true, + "data_type": "mx_fp", + "iters": 0, + "model_free": true, + "autoround_version": "0.15.0", + "enable_quanted_input": false, + "block_name_to_quantize": "model.llm.layers", + "act_bits": 16, + "act_data_type": "fp", + "act_dynamic": true, + "act_group_size": 128, + "act_sym": true, + "extra_config": { + "mlp.experts": { + "act_bits": 4, + "act_group_size": 32, + "act_data_type": "mx_fp" + }, + "model.audio.encoder": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.visual.layers.linear_2": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.23.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.27.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.visual.layers.linear_1": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.visual.layers.linear_3": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.0.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.4.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.16.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.18.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.38.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.8.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.visual.layers.linear_0": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.20.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.1.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.36.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.24.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.25.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.29.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.35.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.9.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.10.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.21.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.22.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.3.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.6.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.12.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.17.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.19.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.28.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.33.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.40.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.15.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.31.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.0.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.1.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.2.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.3.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.4.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.5.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.6.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.input_proj": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.mlp.w13_dn": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.mtp.layers.7.transformer_block.mlp.w2_md": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.14.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wr_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.39.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.13.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.30.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.7.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.11.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.37.attn.wv_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.41.attn.wk_dv": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.26.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.32.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.5.attn.wo_ud": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.2.attn.wq_du": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + }, + "model.llm.layers.34.mlp.gate": { + "bits": 16, + "data_type": "float", + "act_bits": 16, + "act_data_type": "float" + } + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0c6ed62743194dc98ba50d3ca338bf906503b80b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,22 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "<|message_user|>", + "<|message_model|>", + "<|message_system|>", + "<|message_tool|>", + "<|content_text|>", + "<|content_image|>", + "<|content_model_end_sampling|>", + "<|content_thinking|>", + "<|end_message|>", + "<|content_audio_input|>", + "<|content_tool_error|>", + "<|audio|>", + "<|content_xml|>", + "<|begin_of_text|>", + "<|audio_end|>", + "<|content_invoke_tool_json|>", + "<|content_invoke_tool_text|>" + ] +} diff --git a/tiktoken/tokenizer.model b/tiktoken/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..9367ddda1a28202d89d24db9b93f34e1834ea01c --- /dev/null +++ b/tiktoken/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc253fd2b702f7a6da7105eaa8f3463b2f1247e83614f23e5323b921088bed2a +size 3615874 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..8375e6ba74d80af765dbaf2acbaffd33885ad379 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb6333a7db8fe5da90728e741e4a3ee4ac2ae12c5dd4958cc6f31688787d3c2 +size 27875797 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3f7b53bb76be489908376923167e78d060fa20c6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,508 @@ +{ + "added_tokens_decoder": { + "199998": { + "content": "<|unused|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "199999": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200000": { + "content": "<|message_user|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200001": { + "content": "<|message_model|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200002": { + "content": "<|message_system|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200003": { + "content": "<|message_tool|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200004": { + "content": "<|content_text|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200005": { + "content": "<|content_image|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200006": { + "content": "<|content_model_end_sampling|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200007": { + "content": "<|unused_200007|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200008": { + "content": "<|content_thinking|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200009": { + "content": "<|unused_200009|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200010": { + "content": "<|end_message|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200011": { + "content": "<|unused_200011|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200012": { + "content": "<|unused_200012|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200013": { + "content": "<|unused_200013|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200014": { + "content": "<|unused_200014|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200015": { + "content": "<|unused_200015|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200016": { + "content": "<|unused_200016|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200017": { + "content": "<|unused_200017|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200018": { + "content": "<|unused_200018|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200019": { + "content": "<|unused_200019|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200020": { + "content": "<|content_audio_input|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200021": { + "content": "<|unused_200021|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200022": { + "content": "<|content_tool_error|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200023": { + "content": "<|audio|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200024": { + "content": "<|content_xml|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200025": { + "content": "<|unused_200025|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200026": { + "content": "<|unused_200026|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200027": { + "content": "<|unused_200027|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200028": { + "content": "<|begin_of_text|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200029": { + "content": "<|unused_200029|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200030": { + "content": "<|unused_200030|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200031": { + "content": "<|unused_200031|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200032": { + "content": "<|unused_200032|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200033": { + "content": "<|unused_200033|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200034": { + "content": "<|unused_200034|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200035": { + "content": "<|unused_200035|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200036": { + "content": "<|unused_200036|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200037": { + "content": "<|unused_200037|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200038": { + "content": "<|unused_200038|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200039": { + "content": "<|unused_200039|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200040": { + "content": "<|unused_200040|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200041": { + "content": "<|unused_200041|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200042": { + "content": "<|unused_200042|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200043": { + "content": "<|audio_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200044": { + "content": "<|unused_200044|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200045": { + "content": "<|unused_200045|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200046": { + "content": "<|unused_200046|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200047": { + "content": "<|unused_200047|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200048": { + "content": "<|unused_200048|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200049": { + "content": "<|content_invoke_tool_json|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200050": { + "content": "<|unused_200050|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200051": { + "content": "<|unused_200051|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200052": { + "content": "<|unused_200052|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200053": { + "content": "<|unused_200053|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200054": { + "content": "<|unused_200054|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200055": { + "content": "<|unused_200055|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200056": { + "content": "<|unused_200056|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "200057": { + "content": "<|content_invoke_tool_text|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + }, + "clean_up_tokenization_spaces": false, + "fix_mistral_regex": false, + "extra_special_tokens": { + "endoftext": "<|endoftext|>", + "message_user": "<|message_user|>", + "message_model": "<|message_model|>", + "message_system": "<|message_system|>", + "message_tool": "<|message_tool|>", + "content_text": "<|content_text|>", + "content_image": "<|content_image|>", + "content_model_end_sampling": "<|content_model_end_sampling|>", + "content_thinking": "<|content_thinking|>", + "end_message": "<|end_message|>", + "content_audio_input": "<|content_audio_input|>", + "content_tool_error": "<|content_tool_error|>", + "audio": "<|audio|>", + "content_xml": "<|content_xml|>", + "begin_of_text": "<|begin_of_text|>", + "audio_end": "<|audio_end|>", + "content_invoke_tool_json": "<|content_invoke_tool_json|>", + "content_invoke_tool_text": "<|content_invoke_tool_text|>" + }, + "model_max_length": 1000000000000000019884624838656, + "tokenizer_class": "PreTrainedTokenizerFast" +}