Upload 14 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+10226_10111_000000.wav filter=lfs diff=lfs merge=lfs -text

10226_10111_000000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee3e432f4ce88415747f0549628bfef0df742365813d38b18bf28067a40cd51
+size 539884

adapter_config.json

@@ -0,0 +1,29 @@
+{
+    "alpha_pattern": {},
+    "auto_mapping": null,
+    "base_model_name_or_path": "ibm-granite/granite-speech-3.3-8b",
+    "bias": "none",
+    "fan_in_fan_out": false,
+    "inference_mode": true,
+    "init_lora_weights": true,
+    "layer_replication": null,
+    "layers_pattern": null,
+    "layers_to_transform": null,
+    "loftq_config": {},
+    "lora_alpha": 32,
+    "lora_dropout": 0.0,
+    "megatron_config": null,
+    "megatron_core": "megatron.core",
+    "modules_to_save": null,
+    "peft_type": "LORA",
+    "r": 64,
+    "rank_pattern": {},
+    "revision": null,
+    "target_modules": [
+        "v_proj",
+        "q_proj"
+    ],
+    "task_type": "CAUSAL_LM",
+    "use_dora": false,
+    "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d15987eb81e2faafece88b358d5d3a2d01297c37373f8567eaf7ef5b94eb6f
+size 136336192

added_tokens.json

@@ -0,0 +1,10 @@
+{
+  "<|audio|>": 49159,
+  "<|end_of_cite|>": 49156,
+  "<|end_of_plugin|>": 49158,
+  "<|end_of_role|>": 49153,
+  "<|start_of_cite|>": 49155,
+  "<|start_of_plugin|>": 49157,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

chat_template.jinja

@@ -0,0 +1,62 @@
+{%- if messages[0]['role'] == 'system' %}
+     {%- set system_message = messages[0]['content'] %}
+     {%- set loop_messages = messages[1:] %}
+ {%- else %}
+     {%- set system_message = " Knowledge Cutoff Date: April 2024.
+ Today's Date: " + strftime_now('%B %d, %Y') + ". You are Granite, developed by IBM." %}
+     {%- if tools and documents %}
+         {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request. 
+Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+     {%- elif tools %}
+         {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
+     {%- elif documents %}
+         {%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+    {%- elif thinking %}
+    {%- set system_message = system_message + " You are a helpful AI assistant.
+Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
+     {%- else %}
+         {%- set system_message = system_message + " You are a helpful AI assistant." %}
+     {%- endif %}
+     {%- if 'citations' in controls and documents %}
+         {%- set system_message = system_message + ' 
+Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
+     {%- endif %}
+     {%- if 'hallucinations' in controls and documents %}
+         {%- set system_message = system_message + ' 
+Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
+     {%- endif %}
+     {%- set loop_messages = messages %}
+ {%- endif %}
+ {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
+' }}
+ {%- if available_tools %}
+     {{- '<|start_of_role|>available_tools<|end_of_role|>' }}
+     {{- available_tools | tojson(indent=4) }}
+     {{- '<|end_of_text|>
+' }}
+ {%- endif %}
+ {%- if documents %}
+     {%- for document in documents %}
+         {{- '<|start_of_role|>document {"document_id" :"' + document['doc_id'] | string + '"}<|end_of_role|>
+' }}
+         {{- document['text'] }}
+         {{- '<|end_of_text|>
+' }}
+         {%- if not loop.last %}
+             {{- '
+
+'}}
+         {%- endif %}
+     {%- endfor %}
+ {%- endif %}
+ {%- for message in loop_messages %}
+     {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
+' }}
+     {%- if loop.last and add_generation_prompt %}
+         {{- '<|start_of_role|>assistant' }}
+             {%- if controls %}
+                 {{- ' ' + controls | tojson()}}
+             {%- endif %}
+         {{- '<|end_of_role|>' }}
+     {%- endif %}
+ {%- endfor %}

config.json

@@ -0,0 +1,79 @@
+{
+    "architectures": [
+        "GraniteSpeechForConditionalGeneration"
+    ],
+    "audio_token_index": 49159,
+    "downsample_rate": 5,
+    "encoder_config": {
+        "context_size": 200,
+        "conv_expansion_factor": 2,
+        "conv_kernel_size": 15,
+        "dim_head": 128,
+        "dropout": 0.1,
+        "feedforward_mult": 4,
+        "hidden_dim": 1024,
+        "input_dim": 160,
+        "max_pos_emb": 512,
+        "model_type": "granite_speech_encoder",
+        "num_heads": 8,
+        "num_layers": 10,
+        "output_dim": 42
+    },
+    "has_lora_adapter": true,
+    "initializer_range": 0.02,
+    "model_type": "granite_speech",
+    "projector_config": {
+        "_attn_implementation_autoset": true,
+        "attention_probs_dropout_prob": 0.1,
+        "cross_attention_frequency": 1,
+        "encoder_hidden_size": 1024,
+        "hidden_act": "gelu",
+        "hidden_dropout_prob": 0.1,
+        "hidden_size": 1024,
+        "initializer_range": 0.02,
+        "intermediate_size": 4096,
+        "layer_norm_eps": 1e-12,
+        "max_position_embeddings": 2048,
+        "model_type": "blip_2_qformer",
+        "num_attention_heads": 16,
+        "num_hidden_layers": 2,
+        "position_embedding_type": "absolute",
+        "use_qformer_text_input": false,
+        "vocab_size": 30522
+    },
+    "text_config": {
+        "_name_or_path": "/proj/speech/data/granite-3.3-8b-instruct/r250409a/",
+        "architectures": [
+            "GraniteForCausalLM"
+        ],
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attention_multiplier": 0.0078125,
+        "bos_token_id": 0,
+        "embedding_multiplier": 12.0,
+        "eos_token_id": 0,
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "initializer_range": 0.02,
+        "intermediate_size": 12800,
+        "logits_scaling": 16.0,
+        "max_position_embeddings": 131072,
+        "mlp_bias": false,
+        "model_type": "granite",
+        "num_attention_heads": 32,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 8,
+        "pad_token_id": 0,
+        "residual_multiplier": 0.22,
+        "rms_norm_eps": 1e-05,
+        "rope_scaling": null,
+        "rope_theta": 10000000.0,
+        "tie_word_embeddings": true,
+        "torch_dtype": "bfloat16",
+        "use_cache": false,
+        "vocab_size": 49160
+    },
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.52.0.dev0",
+    "window_size": 15
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": false
+}

model.safetensors.index.json

@@ -0,0 +1,762 @@
+{
+  "metadata": {
+    "total_size": 16967021220
+  },
+  "weight_map": {
+    "encoder.input_linear.bias": "model-00009-of-00009.safetensors",
+    "encoder.input_linear.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.0.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.1.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.2.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.3.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.4.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.5.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.6.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.7.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.8.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.attn.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.attn.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.attn.rel_pos_emb.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.attn.to_kv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.attn.to_out.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.attn.to_out.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.attn.to_q.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.batch_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.batch_norm.num_batches_tracked": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.batch_norm.running_mean": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.batch_norm.running_var": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.batch_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.depth_conv.conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.down_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.down_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.up_conv.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.conv.up_conv.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff1.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff1.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff1.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff1.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff1.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff1.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff2.down_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff2.down_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff2.pre_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff2.pre_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff2.up_proj.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.ff2.up_proj.weight": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.post_norm.bias": "model-00009-of-00009.safetensors",
+    "encoder.layers.9.post_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.out.bias": "model-00009-of-00009.safetensors",
+    "encoder.out.weight": "model-00009-of-00009.safetensors",
+    "encoder.out_mid.bias": "model-00009-of-00009.safetensors",
+    "encoder.out_mid.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.norm.weight": "model-00009-of-00009.safetensors",
+    "projector.linear.bias": "model-00009-of-00009.safetensors",
+    "projector.linear.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.attention.key.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.attention.key.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.attention.query.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.attention.query.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.attention.value.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.attention.value.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.output.LayerNorm.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.output.LayerNorm.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.output.dense.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.attention.output.dense.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.attention.key.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.attention.key.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.attention.query.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.attention.query.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.attention.value.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.attention.value.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.output.dense.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.crossattention.output.dense.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.intermediate_query.dense.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.intermediate_query.dense.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.output_query.LayerNorm.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.output_query.LayerNorm.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.output_query.dense.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.0.output_query.dense.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.attention.key.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.attention.key.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.attention.query.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.attention.query.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.attention.value.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.attention.value.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.output.LayerNorm.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.output.LayerNorm.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.output.dense.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.attention.output.dense.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.attention.key.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.attention.key.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.attention.query.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.attention.query.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.attention.value.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.attention.value.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.output.LayerNorm.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.output.LayerNorm.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.output.dense.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.crossattention.output.dense.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.intermediate_query.dense.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.intermediate_query.dense.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.output_query.LayerNorm.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.output_query.LayerNorm.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.output_query.dense.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.encoder.layer.1.output_query.dense.weight": "model-00009-of-00009.safetensors",
+    "projector.qformer.layernorm.bias": "model-00009-of-00009.safetensors",
+    "projector.qformer.layernorm.weight": "model-00009-of-00009.safetensors",
+    "projector.query": "model-00009-of-00009.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1 @@
+{}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,242 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49155": {
+      "content": "<|start_of_cite|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49156": {
+      "content": "<|end_of_cite|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49157": {
+      "content": "<|start_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49158": {
+      "content": "<|end_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49159": {
+      "content": "<|audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}