Add files using upload-large-folder tool

README.md

@@ -0,0 +1,26 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: other
+---
+
+Quantized model => https://huggingface.co/sophosympatheia/Midnight-Miqu-103B-v1.0
+
+**Quantization Details:**
+Quantization is done using turboderp's ExLlamaV2 v0.2.3.
+
+I use the default calibration datasets and arguments. The repo also includes a "measurement.json" file, which was used during the quantization process.
+
+For models with bits per weight (BPW) over 6.0, I default to quantizing the `lm_head` layer at 8 bits instead of the standard 6 bits.
+
+
+
+---
+
+**Who are you? What's with these weird BPWs on [insert model here]?**
+I specialize in optimized EXL2 quantization for models in the 70B to 100B+ range, specifically tailored for 48GB VRAM setups. My rig is built using 2 x 3090s with a Ryzen APU (APU used solely for desktop output—no VRAM wasted on the 3090s). I use TabbyAPI for inference, targeting context sizes between 32K and 64K.
+
+Every model I upload includes a `config.yml` file with my ideal TabbyAPI settings. If you're using my config, don’t forget to set `PYTORCH_CUDA_ALLOC_CONF=backend:cudaMallocAsync` to save some VRAM.

config.json

@@ -0,0 +1,40 @@
+{
+    "_name_or_path": "midnight-miqu-103b-v1.0",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 32764,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 120,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.36.2",
+    "use_cache": true,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.3",
+        "bits": 3.35,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

config.yml

@@ -0,0 +1,212 @@
+# Sample YAML file for configuration.
+# Comment and uncomment values as needed.
+# Every value has a default within the application.
+# This file serves to be a drop in for config.yml
+
+# Unless specified in the comments, DO NOT put these options in quotes!
+# You can use https://www.yamllint.com/ if you want to check your YAML formatting.
+
+# Options for networking
+network:
+  # The IP to host on (default: 127.0.0.1).
+  # Use 0.0.0.0 to expose on all network adapters.
+  host: 0.0.0.0
+
+  # The port to host on (default: 5000).
+  port: 5000
+
+  # Disable HTTP token authentication with requests.
+  # WARNING: This will make your instance vulnerable!
+  # Turn on this option if you are ONLY connecting from localhost.
+  disable_auth: false
+
+  # Send tracebacks over the API (default: False).
+  # NOTE: Only enable this for debug purposes.
+  send_tracebacks: false
+
+  # Select API servers to enable (default: ["OAI"]).
+  # Possible values: OAI, Kobold.
+  api_servers: ["oai"]
+
+# Options for logging
+logging:
+  # Enable prompt logging (default: False).
+  log_prompt: false
+
+  # Enable generation parameter logging (default: False).
+  log_generation_params: false
+
+  # Enable request logging (default: False).
+  # NOTE: Only use this for debugging!
+  log_requests: false
+
+# Options for model overrides and loading
+# Please read the comments to understand how arguments are handled
+# between initial and API loads
+model:
+  # Directory to look for models (default: models).
+  # Windows users, do NOT put this path in quotes!
+  model_dir: models
+
+  # Allow direct loading of models from a completion or chat completion request (default: False).
+  inline_model_loading: false
+
+  # Sends dummy model names when the models endpoint is queried.
+  # Enable this if the client is looking for specific OAI models.
+  use_dummy_models: false
+
+  # An initial model to load.
+  # Make sure the model is located in the model directory!
+  # REQUIRED: This must be filled out to load a model on startup.
+  model_name: Midnight-Miqu-103B-v1.0_exl2_3.35bpw
+
+  # Names of args to use as a fallback for API load requests (default: []).
+  # For example, if you always want cache_mode to be Q4 instead of on the inital model load, add "cache_mode" to this array.
+  # Example: ['max_seq_len', 'cache_mode'].
+  use_as_default: []
+
+  # Max sequence length (default: Empty).
+  # Fetched from the model's base sequence length in config.json by default.
+  max_seq_len: 32768
+
+  # Overrides base model context length (default: Empty).
+  # WARNING: Don't set this unless you know what you're doing!
+  # Again, do NOT use this for configuring context length, use max_seq_len above ^
+  override_base_seq_len:
+
+  # Load model with tensor parallelism.
+  # Falls back to autosplit if GPU split isn't provided.
+  # This ignores the gpu_split_auto value.
+  tensor_parallel: false
+
+  # Automatically allocate resources to GPUs (default: True).
+  # Not parsed for single GPU users.
+  gpu_split_auto: true
+
+  # Reserve VRAM used for autosplit loading (default: 96 MB on GPU 0).
+  # Represented as an array of MB per GPU.
+  autosplit_reserve: [0]
+
+  # An integer array of GBs of VRAM to split between GPUs (default: []).
+  # Used with tensor parallelism.
+  gpu_split: []
+
+  # Rope scale (default: 1.0).
+  # Same as compress_pos_emb.
+  # Use if the model was trained on long context with rope.
+  # Leave blank to pull the value from the model.
+  rope_scale: 1.0
+
+  # Rope alpha (default: None).
+  # Same as alpha_value. Set to "auto" to auto-calculate.
+  # Leaving this value blank will either pull from the model or auto-calculate.
+  rope_alpha:
+
+  # Enable different cache modes for VRAM savings (default: FP16).
+  # Possible values: 'FP16', 'Q8', 'Q6', 'Q4'.
+  cache_mode: Q4
+
+  # Size of the prompt cache to allocate (default: max_seq_len).
+  # Must be a multiple of 256 and can't be less than max_seq_len.
+  # For CFG, set this to 2 * max_seq_len.
+  cache_size:
+
+  # Chunk size for prompt ingestion (default: 2048).
+  # A lower value reduces VRAM usage but decreases ingestion speed.
+  # NOTE: Effects vary depending on the model.
+  # An ideal value is between 512 and 4096.
+  chunk_size: 512
+
+  # Set the maximum number of prompts to process at one time (default: None/Automatic).
+  # Automatically calculated if left blank.
+  # NOTE: Only available for Nvidia ampere (30 series) and above GPUs.
+  max_batch_size:
+
+  # Set the prompt template for this model. (default: None)
+  # If empty, attempts to look for the model's chat template.
+  # If a model contains multiple templates in its tokenizer_config.json,
+  # set prompt_template to the name of the template you want to use.
+  # NOTE: Only works with chat completion message lists!
+  prompt_template:
+
+  # Number of experts to use per token.
+  # Fetched from the model's config.json if empty.
+  # NOTE: For MoE models only.
+  # WARNING: Don't set this unless you know what you're doing!
+  num_experts_per_token:
+
+  # Enables fasttensors to possibly increase model loading speeds (default: False).
+  fasttensors: false
+
+# Options for draft models (speculative decoding)
+# This will use more VRAM!
+draft_model:
+  # Directory to look for draft models (default: models)
+  draft_model_dir: models
+
+  # An initial draft model to load.
+  # Ensure the model is in the model directory.
+  draft_model_name:
+
+  # Rope scale for draft models (default: 1.0).
+  # Same as compress_pos_emb.
+  # Use if the draft model was trained on long context with rope.
+  draft_rope_scale: 1.0
+
+  # Rope alpha for draft models (default: None).
+  # Same as alpha_value. Set to "auto" to auto-calculate.
+  # Leaving this value blank will either pull from the model or auto-calculate.
+  draft_rope_alpha:
+
+  # Cache mode for draft models to save VRAM (default: FP16).
+  # Possible values: 'FP16', 'Q8', 'Q6', 'Q4'.
+  draft_cache_mode: FP16
+
+# Options for Loras
+lora:
+  # Directory to look for LoRAs (default: loras).
+  lora_dir: loras
+
+  # List of LoRAs to load and associated scaling factors (default scale: 1.0).
+  # For the YAML file, add each entry as a YAML list:
+  # - name: lora1
+  #   scaling: 1.0
+  loras:
+
+# Options for embedding models and loading.
+# NOTE: Embeddings requires the "extras" feature to be installed
+# Install it via "pip install .[extras]"
+embeddings:
+  # Directory to look for embedding models (default: models).
+  embedding_model_dir: models
+
+  # Device to load embedding models on (default: cpu).
+  # Possible values: cpu, auto, cuda.
+  # NOTE: It's recommended to load embedding models on the CPU.
+  # If using an AMD GPU, set this value to 'cuda'.
+  embeddings_device: cpu
+
+  # An initial embedding model to load on the infinity backend.
+  embedding_model_name:
+sampling:
+
+# Options for development and experimentation
+developer:
+  # Skip Exllamav2 version check (default: False).
+  # WARNING: It's highly recommended to update your dependencies rather than enabling this flag.
+  unsafe_launch: false
+
+  # Disable API request streaming (default: False).
+  disable_request_streaming: false
+
+  # Enable the torch CUDA malloc backend (default: False).
+  cuda_malloc_backend: true
+
+  # Run asyncio using Uvloop or Winloop which can improve performance.
+  # NOTE: It's recommended to enable this, but if something breaks turn this off.
+  uvloop: true
+
+  # Set process to use a higher priority.
+  # For realtime process priority, run as administrator or sudo.
+  # Otherwise, the priority will be set to high.
+  realtime_process_priority: true

mergekit_config.yml

@@ -0,0 +1,12 @@
+slices:
+  - sources:
+      - model: /home/llm/mergequant/models/midnight-miqu-70b
+        layer_range: [0, 40] # 40
+  - sources:
+      - model: /home/llm/mergequant/models/midnight-miqu-70b
+        layer_range: [20, 60] # 40
+  - sources:
+      - model: /home/llm/mergequant/models/midnight-miqu-70b
+        layer_range: [40, 80] # 40
+merge_method: passthrough
+dtype: float16

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00021.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00021.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.embed_tokens.weight": "model-00001-of-00021.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00021.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00021.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00021.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00021.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00021.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00021.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00021.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00021.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00021.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00021.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00021.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00021.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00021.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00021.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00021.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00004-of-00021.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00021.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00021.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00021.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.41.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00004-of-00021.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00021.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00021.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00021.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00021.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00021.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00021.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00005-of-00021.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00021.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00021.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00021.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00021.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00021.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00021.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00021.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00021.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00021.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00008-of-00021.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00021.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00021.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00021.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00021.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00021.safetensors", "model.layers.51.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.50.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00021.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00021.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00021.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00021.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00021.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00021.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00021.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00021.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00009-of-00021.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00021.safetensors", "model.layers.58.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.57.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.37.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00010-of-00021.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00010-of-00021.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.56.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.36.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.55.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00021.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00010-of-00021.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.54.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00011-of-00021.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00021.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00011-of-00021.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00011-of-00021.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00012-of-00021.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.83.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.63.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00012-of-00021.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00021.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.82.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.81.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.61.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00012-of-00021.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00021.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.80.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.60.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00013-of-00021.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00021.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.59.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00013-of-00021.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00013-of-00021.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.92.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.72.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00013-of-00021.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00014-of-00021.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.89.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.69.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00014-of-00021.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00014-of-00021.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.88.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.68.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00014-of-00021.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00014-of-00021.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.87.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.67.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.86.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.66.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.85.input_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.65.input_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00015-of-00021.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00015-of-00021.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.84.input_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.64.input_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00015-of-00021.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00015-of-00021.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00015-of-00021.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00016-of-00021.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.94.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.74.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00016-of-00021.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00016-of-00021.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.93.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.73.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00016-of-00021.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00016-of-00021.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.91.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.71.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00017-of-00021.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00017-of-00021.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.90.input_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.70.input_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00017-of-00021.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00017-of-00021.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00017-of-00021.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00017-of-00021.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00017-of-00021.safetensors", "model.layers.103.input_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00017-of-00021.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00017-of-00021.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00017-of-00021.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00017-of-00021.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00017-of-00021.safetensors", "model.layers.100.input_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00017-of-00021.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.99.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.79.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.98.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.78.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.97.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.77.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00018-of-00021.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00018-of-00021.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.96.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.76.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.95.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.75.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00018-of-00021.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00019-of-00021.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00019-of-00021.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00019-of-00021.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.106.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00019-of-00021.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00019-of-00021.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00019-of-00021.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.105.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00019-of-00021.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.104.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00019-of-00021.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00019-of-00021.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00019-of-00021.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.102.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00019-of-00021.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.101.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00019-of-00021.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00019-of-00021.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00020-of-00021.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.114.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00020-of-00021.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00020-of-00021.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00020-of-00021.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.111.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00020-of-00021.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00020-of-00021.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.110.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.109.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00020-of-00021.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.108.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00020-of-00021.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00020-of-00021.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.107.input_layernorm.weight": "model-00020-of-00021.safetensors", "lm_head.weight": "model-00020-of-00021.safetensors", "model.norm.weight": "model-00020-of-00021.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00020-of-00021.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.layers.119.input_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00021-of-00021.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00021-of-00021.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00021-of-00021.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.layers.117.input_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00021-of-00021.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00021-of-00021.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.layers.116.input_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00021-of-00021.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00021-of-00021.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.115.input_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00021-of-00021.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.layers.113.input_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00021-of-00021.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.112.input_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00021-of-00021.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.118.input_layernorm.weight": "model-00021-of-00021.safetensors"}}

output-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afb8fe7403d2ceaef251d9f0a44a8be4fd41b050919e91c1dbfa011fc52efe9
+size 8499442506

output-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ded519126edcab066882b260fdd732776fc93329eb25c965704b86356f94fe
+size 8588234324

output-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19bc8e3bb58959c66a4776184a84f4b17af0c1fdbe8897cbd92fb4b944bacae5
+size 8512131786

output-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017977d74c65aed62ebf079579949b1ad4a8c9f222e05ef79fa8d5e81197954b
+size 8529261478

output-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e613f65124349db0f511d9fdbfbd1dee9a35f65d398eaab5d6ccbb6fb37b68
+size 8553043442

output-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca09d0ca32eabd61350f7ec4a2ebb51f2c33e5fd43ed1ff42175608bd09fd98
+size 1032500136

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

upload.py

@@ -0,0 +1,45 @@
+from huggingface_hub import HfApi
+from pathlib import Path
+
+# Define the parameters for uploading
+repo_id = "DBMe/Midnight-Miqu-103B-v1.0-3.35bpw-h6-exl2"  # Replace with your actual repo ID
+folder_path = "/home/asusws-x570-ace/programs/tabbyAPI/models/Midnight-Miqu-103B-v1.0_exl2_3.35bpw/"  # Replace with your folder path
+repo_type = "model"  # Change to "model" or "space" if applicable
+revision = "main"  # Optional: specify the branch or use "main"
+private = False  # Set to True if the repository should be private
+allow_patterns = None  # Optional: specify patterns of files to include
+ignore_patterns = None  # Optional: specify patterns of files to exclude
+num_workers = 1  # Set based on your system; lower if your internet is unstable
+print_report = True  # Enable progress reporting
+print_report_every = 60  # Report frequency in seconds
+
+# Initialize the Hugging Face API client
+api = HfApi()
+
+# Function to upload the folder in a resumable manner
+def upload_resumable():
+    try:
+        print("Starting upload process...")
+
+        # Perform the upload with the provided parameters
+        api.upload_large_folder(
+            repo_id=repo_id,
+            folder_path=Path(folder_path),
+            repo_type=repo_type,
+            revision=revision,
+            private=private,
+            allow_patterns=allow_patterns,
+            ignore_patterns=ignore_patterns,
+            num_workers=num_workers,
+            print_report=print_report,
+            print_report_every=print_report_every,
+        )
+
+        print("Upload completed successfully!")
+
+    except Exception as e:
+        print(f"Upload interrupted due to error: {e}")
+        print("You can resume the upload by running the script again.")
+
+# Call the function to start the upload
+upload_resumable()