Upload folder using huggingface_hub (#1)

- f5eff921afe6393c05055b9aa97307165eb607d83d111834c61a33d3c14ac592 (abc0f1db867490b4ac6b6319345647ea81c2d37c)
- 2d0b9ae4c7d32b3627a813237617786df03293cbb35915d756820a37d07dc7e4 (5453fd16d98a5b09be26dd2c75a9e756b916a652)
- f6d7011006cc5d4b2a3427e01eda02139b3956c7a92900ff128b58d6b628889e (d4db7b49bdef75f3624d5346d7a19ec0b295952a)
- df4b755e60991cec42bdfa61ad6f19757776cdb2887aa1ca1e01ed2346dd4c21 (482f9a2c55b53ef68c5e526de9f7d9b1dec328b1)
- c3a433a167df50d0e4e696bfdf1301abc2b2d8acbc9010cbeb9d212b186a56af (659452bd3c5a647f51ebd1c22f628416f7302cc0)
- 8f13952f1022c9f2ec493d927ca509f4b2436a6d955eb172933b2bff32e2780a (ed7dd647d2406a3268e21edd46026f07fcd87c35)
- e19b55811e2b09cb678a7bcad2356fd7f67321bde750af000845bc110e8fe21d (6d5139459ae0876bc31ec079b4b894d9f48c0592)
- bd213ef5972a1f9513098a8302c1a8881fe0f405107b7d415f09d4fd78ea8a3c (43ca5e30075901f3c0afec5e21df64209f24941a)

.gitattributes

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

README.md

@@ -0,0 +1,291 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ja
+- ko
+- zh
+- ar
+library_name: transformers
+license: cc-by-nc-4.0
+tags:
+- mlx
+extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license)  and
+  acknowledge that the information you provide will be collected, used, and shared
+  in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy).
+extra_gated_fields:
+  Name: text
+  Affiliation: text
+  Country:
+    type: select
+    options:
+    - Aruba
+    - Afghanistan
+    - Angola
+    - Anguilla
+    - Åland Islands
+    - Albania
+    - Andorra
+    - United Arab Emirates
+    - Argentina
+    - Armenia
+    - American Samoa
+    - Antarctica
+    - French Southern Territories
+    - Antigua and Barbuda
+    - Australia
+    - Austria
+    - Azerbaijan
+    - Burundi
+    - Belgium
+    - Benin
+    - Bonaire Sint Eustatius and Saba
+    - Burkina Faso
+    - Bangladesh
+    - Bulgaria
+    - Bahrain
+    - Bahamas
+    - Bosnia and Herzegovina
+    - Saint Barthélemy
+    - Belarus
+    - Belize
+    - Bermuda
+    - Plurinational State of Bolivia
+    - Brazil
+    - Barbados
+    - Brunei-Darussalam
+    - Bhutan
+    - Bouvet-Island
+    - Botswana
+    - Central African Republic
+    - Canada
+    - Cocos (Keeling) Islands
+    - Switzerland
+    - Chile
+    - China
+    - Côte-dIvoire
+    - Cameroon
+    - Democratic Republic of the Congo
+    - Cook Islands
+    - Colombia
+    - Comoros
+    - Cabo Verde
+    - Costa Rica
+    - Cuba
+    - Curaçao
+    - Christmas Island
+    - Cayman Islands
+    - Cyprus
+    - Czechia
+    - Germany
+    - Djibouti
+    - Dominica
+    - Denmark
+    - Dominican Republic
+    - Algeria
+    - Ecuador
+    - Egypt
+    - Eritrea
+    - Western Sahara
+    - Spain
+    - Estonia
+    - Ethiopia
+    - Finland
+    - Fiji
+    - Falkland Islands (Malvinas)
+    - France
+    - Faroe Islands
+    - Federated States of Micronesia
+    - Gabon
+    - United Kingdom
+    - Georgia
+    - Guernsey
+    - Ghana
+    - Gibraltar
+    - Guinea
+    - Guadeloupe
+    - Gambia
+    - Guinea Bissau
+    - Equatorial Guinea
+    - Greece
+    - Grenada
+    - Greenland
+    - Guatemala
+    - French Guiana
+    - Guam
+    - Guyana
+    - Hong Kong
+    - Heard Island and McDonald Islands
+    - Honduras
+    - Croatia
+    - Haiti
+    - Hungary
+    - Indonesia
+    - Isle of Man
+    - India
+    - British Indian Ocean Territory
+    - Ireland
+    - Islamic Republic of Iran
+    - Iraq
+    - Iceland
+    - Israel
+    - Italy
+    - Jamaica
+    - Jersey
+    - Jordan
+    - Japan
+    - Kazakhstan
+    - Kenya
+    - Kyrgyzstan
+    - Cambodia
+    - Kiribati
+    - Saint-Kitts-and-Nevis
+    - South Korea
+    - Kuwait
+    - Lao-Peoples-Democratic-Republic
+    - Lebanon
+    - Liberia
+    - Libya
+    - Saint-Lucia
+    - Liechtenstein
+    - Sri Lanka
+    - Lesotho
+    - Lithuania
+    - Luxembourg
+    - Latvia
+    - Macao
+    - Saint Martin (French-part)
+    - Morocco
+    - Monaco
+    - Republic of Moldova
+    - Madagascar
+    - Maldives
+    - Mexico
+    - Marshall Islands
+    - North Macedonia
+    - Mali
+    - Malta
+    - Myanmar
+    - Montenegro
+    - Mongolia
+    - Northern Mariana Islands
+    - Mozambique
+    - Mauritania
+    - Montserrat
+    - Martinique
+    - Mauritius
+    - Malawi
+    - Malaysia
+    - Mayotte
+    - Namibia
+    - New Caledonia
+    - Niger
+    - Norfolk Island
+    - Nigeria
+    - Nicaragua
+    - Niue
+    - Netherlands
+    - Norway
+    - Nepal
+    - Nauru
+    - New Zealand
+    - Oman
+    - Pakistan
+    - Panama
+    - Pitcairn
+    - Peru
+    - Philippines
+    - Palau
+    - Papua New Guinea
+    - Poland
+    - Puerto Rico
+    - North Korea
+    - Portugal
+    - Paraguay
+    - State of Palestine
+    - French Polynesia
+    - Qatar
+    - Réunion
+    - Romania
+    - Russia
+    - Rwanda
+    - Saudi Arabia
+    - Sudan
+    - Senegal
+    - Singapore
+    - South Georgia and the South Sandwich Islands
+    - Saint Helena Ascension and Tristan da Cunha
+    - Svalbard and Jan Mayen
+    - Solomon Islands
+    - Sierra Leone
+    - El Salvador
+    - San Marino
+    - Somalia
+    - Saint Pierre and Miquelon
+    - Serbia
+    - South Sudan
+    - Sao Tome and Principe
+    - Suriname
+    - Slovakia
+    - Slovenia
+    - Sweden
+    - Eswatini
+    - Sint Maarten (Dutch-part)
+    - Seychelles
+    - Syrian Arab Republic
+    - Turks and Caicos Islands
+    - Chad
+    - Togo
+    - Thailand
+    - Tajikistan
+    - Tokelau
+    - Turkmenistan
+    - Timor Leste
+    - Tonga
+    - Trinidad and Tobago
+    - Tunisia
+    - Turkey
+    - Tuvalu
+    - Taiwan
+    - United Republic of Tanzania
+    - Uganda
+    - Ukraine
+    - United States Minor Outlying Islands
+    - Uruguay
+    - United-States
+    - Uzbekistan
+    - Holy See (Vatican City State)
+    - Saint Vincent and the Grenadines
+    - Bolivarian Republic of Venezuela
+    - Virgin Islands British
+    - Virgin Islands U.S.
+    - VietNam
+    - Vanuatu
+    - Wallis and Futuna
+    - Samoa
+    - Yemen
+    - South Africa
+    - Zambia
+    - Zimbabwe
+---
+
+# mlx-community/c4ai-command-r-08-2024-8bit
+
+The Model [mlx-community/c4ai-command-r-08-2024-8bit](https://huggingface.co/mlx-community/c4ai-command-r-08-2024-8bit) was converted to MLX format from [CohereForAI/c4ai-command-r-08-2024](https://huggingface.co/CohereForAI/c4ai-command-r-08-2024) using mlx-lm version **0.18.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/c4ai-command-r-08-2024-8bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,31 @@
+{
+    "architectures": [
+        "CohereForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 5,
+    "eos_token_id": 255001,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 24576,
+    "layer_norm_eps": 1e-05,
+    "logit_scale": 0.0625,
+    "max_position_embeddings": 131072,
+    "model_type": "cohere",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rope_theta": 4000000,
+    "torch_dtype": "float16",
+    "transformers_version": "4.44.0",
+    "use_cache": true,
+    "use_qk_norm": false,
+    "vocab_size": 256000
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa6aa290db23cc43edc506c84405ae03211e7ba33185ab62abb41d53c1aa421
+size 5223016074

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ba0bff9ae51627548df62b3fe3146c21cf60d5aeb1e3002c25321cf8e67ebd
+size 5187436975

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db47fdf7d89a44da4e125523bbc48679533f317b2b5ee35169bf23a61c2a3f6b
+size 5240896964

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cd65a951b802940b82ac14415c9d1a28fdef4b4255b08d3d8506cea82d08ba
+size 5187437143

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d6dbbe9add58154b1eb11ae0415633b2544f50da2288332755f0a8843b8508
+size 5240896964

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf9cae3e5505537be5976d53857fb0f24a2dca8fe5f4b5973dc5e36e756b2b2
+size 5187437105

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06a3afb104038274bd85e669589c96d5a7f957f339a07a82662818ddc0b5414
+size 3048301106

model.safetensors.index.json

@@ -0,0 +1,891 @@
+{
+    "metadata": {
+        "total_size": 34315321344
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model-00001-of-00007.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00007.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.36.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.norm.weight": "model-00007-of-00007.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e773a231706a3ee5d05050ff27aa122a19df09ee7dd59eafa906b7487035b9
+size 12778456

tokenizer_config.json

@@ -0,0 +1,370 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|EXTRA_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|EXTRA_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|EXTRA_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|EXTRA_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|EXTRA_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|EXTRA_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|EXTRA_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|EXTRA_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255033": {
+      "content": "<|EXTRA_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<BOS_TOKEN>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are a large language model called Command R built by the company Cohere. You act as a brilliant, sophisticated, AI-assistant chatbot trained to assist human users by providing thorough responses.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{'\n\n## Available Tools\nHere is a list of tools that you have available to you:\n\n'}}{% for tool in tools %}{% if loop.index0 != 0 %}{{ '\n\n'}}{% endif %}{{'```python\ndef ' + tool.name + '('}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ ', '}}{% endif %}{{param_name}}: {% if not param_fields.required %}{{'Optional[' + param_fields.type + '] = None'}}{% else %}{{ param_fields.type }}{% endif %}{% endfor %}{{ ') -> List[Dict]:\n    \"\"\"'}}{{ tool.description }}{% if tool.parameter_definitions|length != 0 %}{{ '\n\n    Args:\n        '}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ '\n        ' }}{% endif %}{{ param_name + ' ('}}{% if not param_fields.required %}{{'Optional[' + param_fields.type + ']'}}{% else %}{{ param_fields.type }}{% endif %}{{ '): ' + param_fields.description }}{% endfor %}{% endif %}{{ '\n    \"\"\"\n    pass\n```' }}{% endfor %}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \\'Action:\\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:\n```json\n[\n    {\n        \"tool_name\": title of the tool in the specification,\n        \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n    }\n]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    },
+    {
+      "name": "rag",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '<results>' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{value}}\n{% endfor %}{% endfor %}{{ '</results>'}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Carefully perform the following instructions, in order, starting each with a new line.\n' }}{{ 'Firstly, Decide which of the retrieved documents are relevant to the user\\'s last input by writing \\'Relevant Documents:\\' followed by comma-separated list of document numbers. If none are relevant, you should instead write \\'None\\'.\n' }}{{ 'Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user\\'s last input by writing \\'Cited Documents:\\' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write \\'None\\'.\n' }}{% if citation_mode=='accurate' %}{{ 'Thirdly, Write \\'Answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.\n' }}{% endif %}{{ 'Finally, Write \\'Grounded answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    }
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}