From 42eb2ab95d44a7b66b8c672e239f604f65b87fd1 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 23 Oct 2026 08:02:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: RedHatAI/Qwen3-8B-NVFP4 Source: Original Platform --- .gitattributes | 53 ++ README.md | 397 ++++++++++ added_tokens.json | 28 + chat_template.jinja | 89 +++ config.json | 114 +++ configuration.json | 1 + generation_config.json | 13 + merges.txt | 3 + model-00001-of-00002.safetensors | 3 + model-00002-of-00002.safetensors | 3 + model.safetensors.index.json | 1163 ++++++++++++++++++++++++++++++ recipe.yaml | 42 ++ special_tokens_map.json | 31 + tokenizer.json | 3 + tokenizer_config.json | 239 ++++++ vocab.json | 3 + 16 files changed, 2185 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 model-00001-of-00002.safetensors create mode 100644 model-00002-of-00002.safetensors create mode 100644 model.safetensors.index.json create mode 100644 recipe.yaml create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ac39f7d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..551e59c --- /dev/null +++ b/README.md @@ -0,0 +1,397 @@ +--- +tags: +- fp4 +- vllm +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +pipeline_tag: text-generation +license: apache-2.0 +base_model: Qwen/Qwen3-8B +--- + +# Qwen3-8B-NVFP4 + +## Model Overview +- **Model Architecture:** Qwen/Qwen3-8B + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** FP4 + - **Activation quantization:** FP4 +- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. +- **Release Date:** 6/25/2025 +- **Version:** 1.0 +- **Model Developers:** RedHatAI + +This model is a quantized version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B). +It was evaluated on a several tasks to assess the its quality in comparison to the unquatized model. + +### Model Optimizations + +This model was obtained by quantizing the weights and activations of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) to FP4 data type, ready for inference with vLLM>=0.9.1 +This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. + +Only the weights and activations of the linear operators within transformers blocks are quantized using [LLM Compressor](https://github.com/vllm-project/llm-compressor). + +## Deployment + +### Use with vLLM + +This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. + +```python +from vllm import LLM, SamplingParams +from transformers import AutoTokenizer + +model_id = "RedHatAI/Qwen3-8B-NVFP4" +number_gpus = 1 + +sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256) + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": "Who are you?"}, +] + +prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) + +llm = LLM(model=model_id, tensor_parallel_size=number_gpus) + +outputs = llm.generate(prompts, sampling_params) + +generated_text = outputs[0].outputs[0].text +print(generated_text) +``` + +vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. + +## Creation + +This model was created by applying [LLM Compressor with calibration samples from UltraChat](https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_w4a4_fp4/llama3_example.py), as presented in the code snipet below. + +
+ +```python +from datasets import load_dataset +from transformers import AutoModelForCausalLM, AutoTokenizer + +from llmcompressor import oneshot +from llmcompressor.modifiers.quantization import QuantizationModifier +from llmcompressor.modifiers.smoothquant import SmoothQuantModifier +from llmcompressor.utils import dispatch_for_generation + +MODEL_ID = "Qwen/Qwen3-8B" + +# Load model. +model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype="auto") +tokenizer = AutoTokenizer.from_pretrained(MODEL_ID) + +DATASET_ID = "HuggingFaceH4/ultrachat_200k" +DATASET_SPLIT = "train_sft" + +# Select number of samples. 512 samples is a good place to start. +# Increasing the number of samples can improve accuracy. +NUM_CALIBRATION_SAMPLES = 512 +MAX_SEQUENCE_LENGTH = 2048 + +# Load dataset and preprocess. +ds = load_dataset(DATASET_ID, split=f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]") +ds = ds.shuffle(seed=42) + +def preprocess(example): + return { + "text": tokenizer.apply_chat_template( + example["messages"], + tokenize=False, + ) + } + +ds = ds.map(preprocess) + +# Tokenize inputs. +def tokenize(sample): + return tokenizer( + sample["text"], + padding=False, + max_length=MAX_SEQUENCE_LENGTH, + truncation=True, + add_special_tokens=False, + ) + +ds = ds.map(tokenize, remove_columns=ds.column_names) + +# Configure the quantization algorithm and scheme. +# In this case, we: +# * quantize the weights to fp4 with per group 16 via ptq +# * calibrate a global_scale for activations, which will be used to +# quantize activations to fp4 on the fly +smoothing_strength = 0.8 +recipe = [ + SmoothQuantModifier(smoothing_strength=smoothing_strength), + QuantizationModifier( + ignore=["re:.*lm_head.*"], + config_groups={ + "group_0": { + "targets": ["Linear"], + "weights": { + "num_bits": 4, + "type": "float", + "strategy": "tensor_group", + "group_size": 16, + "symmetric": True, + "observer": "mse", + }, + "input_activations": { + "num_bits": 4, + "type": "float", + "strategy": "tensor_group", + "group_size": 16, + "symmetric": True, + "dynamic": "local", + "observer": "mse", + }, + } + }, + ) +] + +# Save to disk in compressed-tensors format. +SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-NVFP4" + +# Apply quantization. +oneshot( + model=model, + dataset=ds, + recipe=recipe, + max_seq_length=MAX_SEQUENCE_LENGTH, + num_calibration_samples=NUM_CALIBRATION_SAMPLES, + output_dir=SAVE_DIR, +) + +print("\n\n") +print("========== SAMPLE GENERATION ==============") +dispatch_for_generation(model) +input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda") +output = model.generate(input_ids, max_new_tokens=100) +print(tokenizer.decode(output[0])) +print("==========================================\n\n") + +model.save_pretrained(SAVE_DIR, save_compressed=True) +tokenizer.save_pretrained(SAVE_DIR) +``` +
+ +## Evaluation + +This model was evaluated on the well-known OpenLLM v1, OpenLLM v2 and HumanEval_64 benchmarks using [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness). The Reasoning evals were done using [ligheval](https://github.com/neuralmagic/lighteval). + +### Accuracy + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
CategoryMetricQwen/Qwen3-8BQwen3-8B-NVFP4 (this model)Recovery
OpenLLM V1arc_challenge64.7663.9198.69
gsm8k87.2686.7399.39
hellaswag76.6875.3498.25
mmlu74.9773.0797.47
truthfulqa_mc254.4255.07101.19
winogrande71.4368.4395.80
Average71.5970.4398.38
OpenLLM V2BBH (3-shot)47.4649.33103.94
MMLU-Pro (5-shot)34.6427.4979.36
MuSR (0-shot)40.6142.86105.54
IFEval (0-shot)87.8987.6599.73
GPQA (0-shot)25.1726.34104.65
Math-|v|-5 (4-shot)53.5550.8394.92
Average48.2247.4298.33
CodingHumanEval_64 pass@286.5185.3298.62
ReasoningAIME24 (0-shot)75.8662.0781.82
AIME25 (0-shot)65.5262.0794.74
GPQA (Diamond, 0-shot)59.9054.8291.51
Average67.0959.6589.36
+ + + + +### Reproduction + +The results were obtained using the following commands: + +
+ +``` +lm_eval \ + --model vllm \ + --model_args pretrained="RedHatAI/Qwen3-8B-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True,enforce_eager=True\ + --apply_chat_template \ + --fewshot_as_multiturn \ + --tasks openllm \ + --batch_size auto +``` + + +#### OpenLLM v2 +``` +lm_eval \ + --model vllm \ + --model_args pretrained="RedHatAI/Qwen3-8B-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True,enforce_eager=True\ + --apply_chat_template \ + --fewshot_as_multiturn \ + --tasks leaderboard \ + --batch_size auto +``` + +#### HumanEval_64 +``` +lm_eval \ + --model vllm \ + --model_args pretrained="RedHatAI/Qwen3-8B-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True,enforce_eager=True\ + --apply_chat_template \ + --fewshot_as_multiturn \ + --tasks humaneval_64_instruct \ + --batch_size auto +``` + +#### LightEval +``` +# --- model_args.yaml --- +cat > model_args.yaml <<'YAML' +model_parameters: + model_name: "RedHatAI/Qwen3-8B-NVFP4" + dtype: auto + gpu_memory_utilization: 0.9 + tensor_parallel_size: 2 + max_model_length: 40960 + generation_parameters: + seed: 42 + temperature: 0.6 + top_k: 20 + top_p: 0.95 + min_p: 0.0 + max_new_tokens: 32768 +YAML + +lighteval vllm model_args.yaml \ + "lighteval|aime24|0,lighteval|aime25|0,lighteval|gpqa:diamond|0" \ + --max-samples -1 \ + --output-dir out_dir + +``` +
\ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..98c8559 --- /dev/null +++ b/config.json @@ -0,0 +1,114 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "quantization_config": { + "config_groups": { + "group_0": { + "format": "nvfp4-pack-quantized", + "input_activations": { + "actorder": null, + "block_structure": null, + "dynamic": "local", + "group_size": 16, + "num_bits": 4, + "observer": "mse", + "observer_kwargs": {}, + "strategy": "tensor_group", + "symmetric": true, + "type": "float" + }, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "actorder": null, + "block_structure": null, + "dynamic": false, + "group_size": 16, + "num_bits": 4, + "observer": "mse", + "observer_kwargs": {}, + "strategy": "tensor_group", + "symmetric": true, + "type": "float" + } + } + }, + "format": "nvfp4-pack-quantized", + "global_compression_ratio": null, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed", + "sparsity_config": {}, + "transform_config": {}, + "version": "0.11.1.a20250917" + }, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.56.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..f5af93d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.56.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..2e36abc --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e5a73b61e46972c0674b332d32867dfc921b10ebc98158cbae1bdcb0c2acd4 +size 4987207472 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..4d47da5 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:246b3e2a04e5d30170b3cf2ccfd85cd8881486d927f4cd503753841c02f2a6f8 +size 1409856952 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..3242e00 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1163 @@ +{ + "metadata": { + "total_parameters": 5151962616, + "total_size": 6396932064 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.34.mlp.up_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.input_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight_global_scale": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.input_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight_global_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..309f800 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,42 @@ +default_stage: + default_modifiers: + SmoothQuantModifier: + smoothing_strength: 0.8 + mappings: + - !!python/tuple + - ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj'] + - re:.*input_layernorm + - !!python/tuple + - ['re:.*gate_proj', 're:.*up_proj'] + - re:.*post_attention_layernorm + ignore: [] + QuantizationModifier: + config_groups: + group_0: + targets: [Linear] + weights: + num_bits: 4 + type: float + symmetric: true + group_size: 16 + strategy: tensor_group + block_structure: null + dynamic: false + actorder: null + observer: mse + observer_kwargs: {} + input_activations: + num_bits: 4 + type: float + symmetric: true + group_size: 16 + strategy: tensor_group + block_structure: null + dynamic: local + actorder: null + observer: mse + observer_kwargs: {} + output_activations: null + format: null + targets: [Linear] + ignore: ['re:.*lm_head.*'] diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ddaf698 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,239 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833