Add files using upload-large-folder tool

README.md

@@ -0,0 +1,28 @@
+---
+license: other
+license_name: mrl
+language:
+- en
+tags:
+- chat
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+Quantized model => https://huggingface.co/MarsupialAI/Monstral-123B
+
+**Quantization Details:**
+Quantization is done using turboderp's ExLlamaV2 v0.2.4.
+
+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 +1,38 @@
+{
+    "_name_or_path": "I:\\raw\\behemoth",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 88,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.44.2",
+    "use_cache": true,
+    "vocab_size": 32768,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.4",
+        "bits": 2.85,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

config.yml

@@ -0,0 +1,228 @@
+# 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 authenticaion 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 to clients (default: False)
+  # NOTE: Only enable this for debug purposes
+  send_tracebacks: False
+
+  # Select API servers to enable (default: ["OAI"])
+  # Possible values: OAI
+  api_servers: ["OAI"]
+
+# Options for logging
+logging:
+  # Enable prompt logging (default: False)
+  prompt: False
+
+  # Enable generation parameter logging (default: False)
+  generation_params: False
+
+  # Enable request logging (default: False)
+  # NOTE: Only use this for debugging!
+  requests: False
+
+# Options for sampling
+sampling:
+  # Override preset name. Find this in the sampler-overrides folder (default: None)
+  # This overrides default fallbacks for sampler values that are passed to the API
+  # Server-side overrides are NOT needed by default
+  # WARNING: Using this can result in a generation speed penalty
+  #override_preset: 
+
+# Options for development and experimentation
+developer:
+  # Skips exllamav2 version check (default: False)
+  # It's highly recommended to update your dependencies rather than enabling this flag
+  # WARNING: Don't set this unless you know what you're doing!
+  #unsafe_launch: False
+
+  # Disable all request streaming (default: False)
+  # A kill switch for turning off SSE in the API server
+  #disable_request_streaming: False
+
+  # Enable the torch CUDA malloc backend (default: False)
+  # This can save a few MBs of VRAM, but has a risk of errors. Use at your own risk.
+  cuda_malloc_backend: True
+
+  # Enable Uvloop or Winloop (default: False)
+  # Make the program utilize a faster async event loop 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
+
+# Options for model overrides and loading
+# Please read the comments to understand how arguments are handled between initial and API loads
+model:
+  # Overrides the directory to look for models (default: models)
+  # Windows users, DO NOT put this path in quotes! This directory will be invalid otherwise.
+  model_dir: models
+
+  # Sends dummy model names when the models endpoint is queried
+  # Enable this if the program is looking for a specific OAI model
+  #use_dummy_models: False
+
+  # An initial model to load. Make sure the model is located in the model directory!
+  # A model can be loaded later via the API.
+  # REQUIRED: This must be filled out to load a model on startup!
+  model_name: Behemoth-123B-v1.1_exl2_2.85bpw
+
+  # The below parameters only apply for initial loads
+  # All API based loads do NOT inherit these settings unless specified in use_as_default
+
+  # Names of args to use as a default 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
+  # Ex. ["max_seq_len", "cache_mode"]
+  #use_as_default: []
+
+  # The below parameters apply only if model_name is set
+
+  # 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 ^
+  # Only use this if the model's base sequence length in config.json is incorrect (ex. Mistral 7B)
+  #override_base_seq_len:
+
+  # Load model with tensor parallelism
+  # If a GPU split isn't provided, the TP loader will fallback to autosplit
+  # Enabling ignores the gpu_split_auto and autosplit_reserve values
+  #tensor_parallel: True
+
+  # Automatically allocate resources to GPUs (default: True)
+  # NOTE: Not parsed for single GPU users
+  gpu_split_auto: True
+
+  # Reserve VRAM used for autosplit loading (default: 96 MB on GPU 0)
+  # This is represented as an array of MB per GPU used
+  autosplit_reserve: [0]
+
+  # An integer array of GBs of vram to split between GPUs (default: [])
+  # Used with tensor parallelism
+  # NOTE: Not parsed for single GPU users
+  #gpu_split: [20.6, 24]
+
+  # Rope scale (default: 1.0)
+  # Same thing as compress_pos_emb
+  # Only use if your model was trained on long context with rope (check config.json)
+  # Leave blank to pull the value from the model
+  #rope_scale: 1.0
+
+  # Rope alpha (default: 1.0)
+  # Same thing as alpha_value
+  # Leave blank to automatically calculate alpha
+  #rope_alpha: 1.0
+
+  # Enable different cache modes for VRAM savings (slight performance hit).
+  # Possible values FP16, Q8, Q6, Q4. (default: FP16)
+  cache_mode: Q4
+
+  # Size of the prompt cache to allocate (default: max_seq_len)
+  # This must be a multiple of 256. A larger cache uses more VRAM, but allows for more prompts to be processed at once.
+  # NOTE: Cache size should not be less than max_seq_len.
+  # For CFG, set this to 2 * max_seq_len to make room for both positive and negative prompts.
+  # cache_size:
+
+  # Chunk size for prompt ingestion. A lower value reduces VRAM usage at the cost of ingestion speed (default: 2048)
+  # NOTE: Effects vary depending on the model. An ideal value is between 512 and 4096
+  chunk_size: 1024
+
+  # Set the maximum amount of prompts to process at one time (default: None/Automatic)
+  # This will be automatically calculated if left blank.
+  # A max batch size of 1 processes prompts one at a time.
+  # NOTE: Only available for Nvidia ampere (30 series) and above GPUs
+  #max_batch_size:
+
+  # Set the prompt template for this model. If empty, attempts to look for the model's chat template. (default: None)
+  # 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 not specified (default: Empty)
+  # WARNING: Don't set this unless you know what you're doing!
+  # NOTE: For MoE models (ex. Mixtral) only!
+  #num_experts_per_token:
+
+  # Enables fasttensors to possibly increase model loading speeds (default: False)
+  fasttensors: true
+
+  # Options for draft models (speculative decoding). This will use more VRAM!
+  #draft:
+    # Overrides the directory to look for draft (default: models)
+    #draft_model_dir: models
+
+    # An initial draft model to load. Make sure this model is located in the model directory!
+    # A draft model can be loaded later via the API.
+    #draft_model_name: A model name
+  
+    # The below parameters only apply for initial loads
+    # All API based loads do NOT inherit these settings unless specified in use_as_default
+
+    # Rope scale for draft models (default: 1.0)
+    # Same thing as compress_pos_emb
+    # Only use if your draft model was trained on long context with rope (check config.json)
+    #draft_rope_scale: 1.0
+
+    # Rope alpha for draft model (default: 1.0)
+    # Same thing as alpha_value
+    # Leave blank to automatically calculate alpha value
+    #draft_rope_alpha: 1.0
+
+    # Enable different draft model cache modes for VRAM savings (slight performance hit).
+    # Possible values FP16, Q8, Q6, Q4. (default: FP16)
+    #draft_cache_mode: FP16
+  
+  # Options for loras
+  #lora:
+    # Overrides the directory to look for loras (default: loras)
+    #lora_dir: loras
+    
+    # List of loras to load and associated scaling factors (default: 1.0). Comment out unused entries or add more rows as needed.
+    #loras:
+    #- name: lora1
+    #  scaling: 1.0
+
+# Options for embedding models and loading.
+# NOTE: Embeddings requires the "extras" feature to be installed
+# Install it via "pip install .[extras]"
+embeddings:
+  # Overrides 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 you'd like to load on an AMD gpu, set this value to "cuda" as well.
+  embeddings_device: cpu
+
+  # The below parameters only apply for initial loads
+  # All API based loads do NOT inherit these settings unless specified in use_as_default
+
+  # An initial embedding model to load on the infinity backend (default: None)
+  embedding_model_name:

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0.dev0"
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 245220139008}, "weight_map": {"lm_head.weight": "model-00001-of-00051.safetensors", "model.embed_tokens.weight": "model-00001-of-00051.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00051.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00051.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00051.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00051.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00051.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00051.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00051.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00051.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00051.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00051.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00051.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00051.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00051.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00051.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00051.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00051.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00051.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00051.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00051.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00051.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00051.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00051.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00051.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00051.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00051.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00051.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00051.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00051.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00051.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00051.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00051.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00051.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00051.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00051.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00051.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00051.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00051.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00051.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00051.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00051.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00051.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00051.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00051.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00051.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00051.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00051.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00051.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00051.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00051.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00051.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00051.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00051.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00051.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00051.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00051.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00051.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00051.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00051.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00051.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00051.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00051.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00051.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00051.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00051.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00051.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00051.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00051.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00051.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00051.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00051.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00051.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00051.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00051.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00051.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00051.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00051.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00051.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00051.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00051.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00051.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00051.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00051.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00051.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00051.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00051.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00051.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00051.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00051.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00051.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00051.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00051.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00051.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00051.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00051.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00051.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00051.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00051.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00051.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00051.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00051.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00051.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00051.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00051.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00051.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00051.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00051.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00051.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00051.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00051.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00051.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00051.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00051.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00051.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00051.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00051.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00051.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00051.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00051.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00051.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00051.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00051.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00051.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00051.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00051.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00051.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00051.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00051.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00051.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00051.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00051.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00051.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00051.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00051.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00051.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00051.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00051.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00051.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00051.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00051.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00051.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00051.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00051.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00051.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00051.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00051.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00051.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00051.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00051.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00051.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00051.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00051.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00051.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00051.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00051.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00051.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00051.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00051.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00051.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00051.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00051.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00051.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00051.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00051.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00051.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00051.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00051.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00051.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00051.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00051.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00051.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00051.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00051.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00012-of-00051.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00051.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00012-of-00051.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00051.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00051.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00051.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00051.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00051.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00051.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00051.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00051.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00051.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00051.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00051.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00051.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00051.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00051.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00051.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00051.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00051.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00051.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00051.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00051.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00051.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00051.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00051.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00051.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00014-of-00051.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00051.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00051.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00051.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00051.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00051.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00051.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00051.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00051.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00051.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00014-of-00051.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00051.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00051.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00051.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00015-of-00051.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00015-of-00051.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00015-of-00051.safetensors", "model.layers.30.input_layernorm.weight": "model-00015-of-00051.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00015-of-00051.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00051.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00051.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00051.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00051.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00051.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00051.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00051.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00051.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00051.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00051.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00016-of-00051.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00051.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00051.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00051.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00051.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00051.safetensors", "model.layers.32.input_layernorm.weight": "model-00016-of-00051.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00016-of-00051.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00016-of-00051.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00016-of-00051.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00051.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00016-of-00051.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00016-of-00051.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00016-of-00051.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00016-of-00051.safetensors", "model.layers.33.input_layernorm.weight": "model-00016-of-00051.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00016-of-00051.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00017-of-00051.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00017-of-00051.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00017-of-00051.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00017-of-00051.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00017-of-00051.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00017-of-00051.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00017-of-00051.safetensors", "model.layers.34.input_layernorm.weight": "model-00017-of-00051.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00017-of-00051.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00017-of-00051.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00017-of-00051.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00051.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00051.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00051.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00051.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00051.safetensors", "model.layers.35.input_layernorm.weight": "model-00017-of-00051.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00018-of-00051.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00018-of-00051.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00018-of-00051.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00051.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00018-of-00051.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00018-of-00051.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00051.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00051.safetensors", "model.layers.36.input_layernorm.weight": "model-00018-of-00051.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00051.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00051.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00018-of-00051.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00051.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00051.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00051.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00051.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00051.safetensors", "model.layers.37.input_layernorm.weight": "model-00019-of-00051.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00019-of-00051.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00019-of-00051.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00019-of-00051.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00051.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00051.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00051.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00051.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00051.safetensors", "model.layers.38.input_layernorm.weight": "model-00019-of-00051.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00019-of-00051.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00051.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00020-of-00051.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00051.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00051.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00051.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00051.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00051.safetensors", "model.layers.39.input_layernorm.weight": "model-00020-of-00051.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00051.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00051.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00020-of-00051.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00051.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00051.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00051.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00051.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00051.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00051.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00051.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00051.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00051.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00051.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00051.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00051.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00051.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00051.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00051.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00051.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00051.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00051.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00051.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00051.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00051.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00051.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00051.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00051.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00022-of-00051.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00051.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00051.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00051.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00022-of-00051.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00051.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00051.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00051.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00051.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00022-of-00051.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00051.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00022-of-00051.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00022-of-00051.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00051.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00023-of-00051.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00023-of-00051.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00023-of-00051.safetensors", "model.layers.43.input_layernorm.weight": "model-00023-of-00051.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00023-of-00051.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00023-of-00051.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00023-of-00051.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00023-of-00051.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00023-of-00051.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00023-of-00051.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00023-of-00051.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00023-of-00051.safetensors", "model.layers.44.input_layernorm.weight": "model-00023-of-00051.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00023-of-00051.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00023-of-00051.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00024-of-00051.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00024-of-00051.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00024-of-00051.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00024-of-00051.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00024-of-00051.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00024-of-00051.safetensors", "model.layers.45.input_layernorm.weight": "model-00024-of-00051.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00024-of-00051.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00024-of-00051.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00024-of-00051.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00024-of-00051.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00024-of-00051.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00024-of-00051.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00024-of-00051.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00024-of-00051.safetensors", "model.layers.46.input_layernorm.weight": "model-00024-of-00051.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00024-of-00051.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00025-of-00051.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00025-of-00051.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00025-of-00051.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00025-of-00051.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00025-of-00051.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00025-of-00051.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00025-of-00051.safetensors", "model.layers.47.input_layernorm.weight": "model-00025-of-00051.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00025-of-00051.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00025-of-00051.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00025-of-00051.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00025-of-00051.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00025-of-00051.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00025-of-00051.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00025-of-00051.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00025-of-00051.safetensors", "model.layers.48.input_layernorm.weight": "model-00025-of-00051.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00026-of-00051.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00026-of-00051.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00026-of-00051.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00026-of-00051.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00026-of-00051.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00026-of-00051.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00026-of-00051.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00026-of-00051.safetensors", "model.layers.49.input_layernorm.weight": "model-00026-of-00051.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00026-of-00051.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00026-of-00051.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00026-of-00051.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00026-of-00051.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00026-of-00051.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00027-of-00051.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00027-of-00051.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00027-of-00051.safetensors", "model.layers.5.input_layernorm.weight": "model-00027-of-00051.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00027-of-00051.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00027-of-00051.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00027-of-00051.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00027-of-00051.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00027-of-00051.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00027-of-00051.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00027-of-00051.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00027-of-00051.safetensors", "model.layers.50.input_layernorm.weight": "model-00027-of-00051.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00027-of-00051.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00027-of-00051.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00028-of-00051.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00028-of-00051.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00028-of-00051.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00028-of-00051.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00028-of-00051.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00028-of-00051.safetensors", "model.layers.51.input_layernorm.weight": "model-00028-of-00051.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00028-of-00051.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00028-of-00051.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00028-of-00051.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00028-of-00051.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00028-of-00051.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00028-of-00051.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00028-of-00051.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00028-of-00051.safetensors", "model.layers.52.input_layernorm.weight": "model-00028-of-00051.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00028-of-00051.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00029-of-00051.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00029-of-00051.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00029-of-00051.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00029-of-00051.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00029-of-00051.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00029-of-00051.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00029-of-00051.safetensors", "model.layers.53.input_layernorm.weight": "model-00029-of-00051.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00029-of-00051.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00029-of-00051.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00029-of-00051.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00029-of-00051.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00029-of-00051.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00029-of-00051.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00029-of-00051.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00029-of-00051.safetensors", "model.layers.54.input_layernorm.weight": "model-00029-of-00051.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00030-of-00051.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00030-of-00051.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00030-of-00051.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00030-of-00051.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00030-of-00051.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00030-of-00051.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00030-of-00051.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00030-of-00051.safetensors", "model.layers.55.input_layernorm.weight": "model-00030-of-00051.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00030-of-00051.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00030-of-00051.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00030-of-00051.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00030-of-00051.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00030-of-00051.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00031-of-00051.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00031-of-00051.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00031-of-00051.safetensors", "model.layers.56.input_layernorm.weight": "model-00031-of-00051.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00031-of-00051.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00031-of-00051.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00031-of-00051.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00031-of-00051.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00031-of-00051.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00031-of-00051.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00031-of-00051.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00031-of-00051.safetensors", "model.layers.57.input_layernorm.weight": "model-00031-of-00051.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00031-of-00051.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00031-of-00051.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00032-of-00051.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00032-of-00051.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00032-of-00051.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00032-of-00051.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00032-of-00051.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00032-of-00051.safetensors", "model.layers.58.input_layernorm.weight": "model-00032-of-00051.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00032-of-00051.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00032-of-00051.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00032-of-00051.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00032-of-00051.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00032-of-00051.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00032-of-00051.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00032-of-00051.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00032-of-00051.safetensors", "model.layers.59.input_layernorm.weight": "model-00032-of-00051.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00032-of-00051.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00033-of-00051.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00033-of-00051.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00033-of-00051.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00033-of-00051.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00033-of-00051.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00033-of-00051.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00033-of-00051.safetensors", "model.layers.6.input_layernorm.weight": "model-00033-of-00051.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00033-of-00051.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00033-of-00051.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00033-of-00051.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00033-of-00051.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00033-of-00051.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00033-of-00051.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00033-of-00051.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00033-of-00051.safetensors", "model.layers.60.input_layernorm.weight": "model-00033-of-00051.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00034-of-00051.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00034-of-00051.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00034-of-00051.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00034-of-00051.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00034-of-00051.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00034-of-00051.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00034-of-00051.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00034-of-00051.safetensors", "model.layers.61.input_layernorm.weight": "model-00034-of-00051.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00034-of-00051.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00034-of-00051.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00034-of-00051.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00034-of-00051.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00034-of-00051.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00035-of-00051.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00035-of-00051.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00035-of-00051.safetensors", "model.layers.62.input_layernorm.weight": "model-00035-of-00051.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00035-of-00051.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00035-of-00051.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00035-of-00051.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00035-of-00051.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00035-of-00051.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00035-of-00051.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00035-of-00051.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00035-of-00051.safetensors", "model.layers.63.input_layernorm.weight": "model-00035-of-00051.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00035-of-00051.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00035-of-00051.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00036-of-00051.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00036-of-00051.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00036-of-00051.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00036-of-00051.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00036-of-00051.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00036-of-00051.safetensors", "model.layers.64.input_layernorm.weight": "model-00036-of-00051.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00036-of-00051.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00036-of-00051.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00036-of-00051.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00036-of-00051.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00036-of-00051.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00036-of-00051.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00036-of-00051.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00036-of-00051.safetensors", "model.layers.65.input_layernorm.weight": "model-00036-of-00051.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00036-of-00051.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00037-of-00051.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00037-of-00051.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00037-of-00051.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00037-of-00051.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00037-of-00051.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00037-of-00051.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00037-of-00051.safetensors", "model.layers.66.input_layernorm.weight": "model-00037-of-00051.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00037-of-00051.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00037-of-00051.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00037-of-00051.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00037-of-00051.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00037-of-00051.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00037-of-00051.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00037-of-00051.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00037-of-00051.safetensors", "model.layers.67.input_layernorm.weight": "model-00037-of-00051.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00038-of-00051.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00038-of-00051.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00038-of-00051.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00038-of-00051.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00038-of-00051.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00038-of-00051.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00038-of-00051.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00038-of-00051.safetensors", "model.layers.68.input_layernorm.weight": "model-00038-of-00051.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00038-of-00051.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00038-of-00051.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00038-of-00051.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00038-of-00051.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00038-of-00051.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00039-of-00051.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00039-of-00051.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00039-of-00051.safetensors", "model.layers.69.input_layernorm.weight": "model-00039-of-00051.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00039-of-00051.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00039-of-00051.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00039-of-00051.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00039-of-00051.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00039-of-00051.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00039-of-00051.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00039-of-00051.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00039-of-00051.safetensors", "model.layers.7.input_layernorm.weight": "model-00039-of-00051.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00039-of-00051.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00039-of-00051.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00040-of-00051.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00040-of-00051.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00040-of-00051.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00040-of-00051.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00040-of-00051.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00040-of-00051.safetensors", "model.layers.70.input_layernorm.weight": "model-00040-of-00051.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00040-of-00051.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00040-of-00051.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00040-of-00051.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00040-of-00051.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00040-of-00051.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00040-of-00051.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00040-of-00051.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00040-of-00051.safetensors", "model.layers.71.input_layernorm.weight": "model-00040-of-00051.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00040-of-00051.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00041-of-00051.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00041-of-00051.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00041-of-00051.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00041-of-00051.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00041-of-00051.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00041-of-00051.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00041-of-00051.safetensors", "model.layers.72.input_layernorm.weight": "model-00041-of-00051.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00041-of-00051.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00041-of-00051.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00041-of-00051.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00041-of-00051.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00041-of-00051.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00041-of-00051.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00041-of-00051.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00041-of-00051.safetensors", "model.layers.73.input_layernorm.weight": "model-00041-of-00051.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00042-of-00051.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00042-of-00051.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00042-of-00051.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00042-of-00051.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00042-of-00051.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00042-of-00051.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00042-of-00051.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00042-of-00051.safetensors", "model.layers.74.input_layernorm.weight": "model-00042-of-00051.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00042-of-00051.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00042-of-00051.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00042-of-00051.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00042-of-00051.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00042-of-00051.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00043-of-00051.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00043-of-00051.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00043-of-00051.safetensors", "model.layers.75.input_layernorm.weight": "model-00043-of-00051.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00043-of-00051.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00043-of-00051.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00043-of-00051.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00043-of-00051.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00043-of-00051.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00043-of-00051.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00043-of-00051.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00043-of-00051.safetensors", "model.layers.76.input_layernorm.weight": "model-00043-of-00051.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00043-of-00051.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00043-of-00051.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00044-of-00051.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00044-of-00051.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00044-of-00051.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00044-of-00051.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00044-of-00051.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00044-of-00051.safetensors", "model.layers.77.input_layernorm.weight": "model-00044-of-00051.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00044-of-00051.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00044-of-00051.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00044-of-00051.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00044-of-00051.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00044-of-00051.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00044-of-00051.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00044-of-00051.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00044-of-00051.safetensors", "model.layers.78.input_layernorm.weight": "model-00044-of-00051.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00044-of-00051.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00045-of-00051.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00045-of-00051.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00045-of-00051.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00045-of-00051.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00045-of-00051.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00045-of-00051.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00045-of-00051.safetensors", "model.layers.79.input_layernorm.weight": "model-00045-of-00051.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00045-of-00051.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00045-of-00051.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00045-of-00051.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00045-of-00051.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00045-of-00051.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00045-of-00051.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00045-of-00051.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00045-of-00051.safetensors", "model.layers.8.input_layernorm.weight": "model-00045-of-00051.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00046-of-00051.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00046-of-00051.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00046-of-00051.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00046-of-00051.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00046-of-00051.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00046-of-00051.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00046-of-00051.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00046-of-00051.safetensors", "model.layers.80.input_layernorm.weight": "model-00046-of-00051.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00046-of-00051.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00046-of-00051.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00046-of-00051.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00046-of-00051.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00046-of-00051.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00047-of-00051.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00047-of-00051.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00047-of-00051.safetensors", "model.layers.81.input_layernorm.weight": "model-00047-of-00051.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00047-of-00051.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00047-of-00051.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00047-of-00051.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00047-of-00051.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00047-of-00051.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00047-of-00051.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00047-of-00051.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00047-of-00051.safetensors", "model.layers.82.input_layernorm.weight": "model-00047-of-00051.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00047-of-00051.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00047-of-00051.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00048-of-00051.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00048-of-00051.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00048-of-00051.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00048-of-00051.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00048-of-00051.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00048-of-00051.safetensors", "model.layers.83.input_layernorm.weight": "model-00048-of-00051.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00048-of-00051.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00048-of-00051.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00048-of-00051.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00048-of-00051.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00048-of-00051.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00048-of-00051.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00048-of-00051.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00048-of-00051.safetensors", "model.layers.84.input_layernorm.weight": "model-00048-of-00051.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00048-of-00051.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00049-of-00051.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00049-of-00051.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00049-of-00051.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00049-of-00051.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00049-of-00051.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00049-of-00051.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00049-of-00051.safetensors", "model.layers.85.input_layernorm.weight": "model-00049-of-00051.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00049-of-00051.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00049-of-00051.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00049-of-00051.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00049-of-00051.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00049-of-00051.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00049-of-00051.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00049-of-00051.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00049-of-00051.safetensors", "model.layers.86.input_layernorm.weight": "model-00049-of-00051.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00050-of-00051.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00050-of-00051.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00050-of-00051.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00050-of-00051.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00050-of-00051.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00050-of-00051.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00050-of-00051.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00050-of-00051.safetensors", "model.layers.87.input_layernorm.weight": "model-00050-of-00051.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00050-of-00051.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00050-of-00051.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00050-of-00051.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00050-of-00051.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00050-of-00051.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00051-of-00051.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00051-of-00051.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00051-of-00051.safetensors", "model.layers.9.input_layernorm.weight": "model-00051-of-00051.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00051-of-00051.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00051-of-00051.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00051-of-00051.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00051-of-00051.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00051-of-00051.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00051-of-00051.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00051-of-00051.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00051-of-00051.safetensors", "model.norm.weight": "model-00051-of-00051.safetensors"}}

output-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8cd0bd5bac9d1c862530c9fb6a50fa6bcb20e00f41d29f1e2933b478803ff4
+size 8587760250

output-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7675a7b5d8ac95059fca23e1d354a99a9c7b94c6d720dec180acb8b0f81b94d
+size 8583206386

output-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc05b16ab6552cf7e4d98058da3dbc7975f322734be3a3b42fb6a19a3fee8757
+size 8530776186

output-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677121bd2c5c74ee3a831caac4eb45b07e0c1b4ad0146ee97cd98c1796f216d8
+size 8540639104

output-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cf218a4e99d3aedd4b75bcff07c5a73a84b0dee2e05102baae4a990693abcd
+size 8568626264

output-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6c9a8ae19958ecb9ba239990b348c1cb19ad8fee0df74f77f176873d09e620
+size 1699810716

recipe.txt

@@ -0,0 +1,8 @@
+models:
+  - model: TheDrummer/Behemoth-123B-v1
+  - model: anthracite-org/magnum-v4-123b
+merge_method: slerp
+base_model: TheDrummer/Behemoth-123B-v1
+parameters:
+  t: [0.1, 0.3, 0.6, 0.3, 0.1]
+dtype: float16

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583