Hugging Face's logo

mlx-community
/
Falcon-H1-0.5B-Instruct-8bit

Text Generation
MLX
Safetensors
falcon_h1
falcon-h1
conversational
8-bit precision
Model card Files
xet
Community
prince-canuma commited on
Commit
5e33037
·
verified ·
1 Parent(s): 9c1180c

Add files using upload-large-folder tool

Browse files
Files changed (9) hide show
  1. README.md +40 -0
  2. chat_template.jinja +17 -0
  3. config.json +72 -0
  4. generation_config.json +7 -0
  5. model.safetensors +3 -0
  6. model.safetensors.index.json +1239 -0
  7. special_tokens_map.json +356 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +0 -0
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: mlx
3
+ tags:
4
+ - falcon-h1
5
+ - mlx
6
+ license: other
7
+ license_name: falcon-llm-license
8
+ license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
9
+ base_model: tiiuae/Falcon-H1-0.5B-Instruct
10
+ inference: true
11
+ pipeline_tag: text-generation
12
+ ---
13
+
14
+ # mlx-community/Falcon-H1-0.5B-Instruct-8bit
15
+
16
+ This model [mlx-community/Falcon-H1-0.5B-Instruct-8bit](https://huggingface.co/mlx-community/Falcon-H1-0.5B-Instruct-8bit) was
17
+ converted to MLX format from [tiiuae/Falcon-H1-0.5B-Instruct](https://huggingface.co/tiiuae/Falcon-H1-0.5B-Instruct)
18
+ using mlx-lm version **0.25.2**.
19
+
20
+ ## Use with mlx
21
+
22
+ ```bash
23
+ pip install mlx-lm
24
+ ```
25
+
26
+ ```python
27
+ from mlx_lm import load, generate
28
+
29
+ model, tokenizer = load("mlx-community/Falcon-H1-0.5B-Instruct-8bit")
30
+
31
+ prompt = "hello"
32
+
33
+ if tokenizer.chat_template is not None:
34
+ messages = [{"role": "user", "content": prompt}]
35
+ prompt = tokenizer.apply_chat_template(
36
+ messages, add_generation_prompt=True
37
+ )
38
+
39
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
40
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{bos_token}}
2
+ {%- if tools %}
3
+ {{- '<|im_start|>system\n' }}
4
+ {%- if messages[0].role == 'system' %}
5
+ {{- messages[0].content + '\n\n' }}
6
+ {%- endif %}
7
+ {{- "You are a function calling AI model. You are provided with function signature within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.\n<tools>\n" }}
8
+ {%- for tool in tools %}[{{- tool | tojson }}]{%- endfor %}
9
+ {{- "\n</tools>\nFor each function call, return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:\n<tool_call>\n{'arguments': <args-dict>, 'name': <function-name>}\n</tool_call>\n" }}
10
+ {%- else %}
11
+ {%- if messages[0].role == 'system' %}
12
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
13
+ {%- endif %}
14
+ {%- endif %}{% for message in messages %}{%- if message.role != 'system' %}{{'<|im_start|>' + message['role'] + '
15
+ ' + message['content'] + '<|im_end|>' + '
16
+ '}}{%- endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
17
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FalconH1ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_in_multiplier": 1.0,
8
+ "attention_out_multiplier": 0.9375,
9
+ "attn_layer_indices": null,
10
+ "bos_token_id": 1,
11
+ "embedding_multiplier": 5.656854249492381,
12
+ "eos_token_id": 11,
13
+ "head_dim": 64,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 1024,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2048,
18
+ "key_multiplier": 0.39062499999999994,
19
+ "lm_head_multiplier": 0.0390625,
20
+ "mamba_chunk_size": 128,
21
+ "mamba_conv_bias": true,
22
+ "mamba_d_conv": 4,
23
+ "mamba_d_head": 64,
24
+ "mamba_d_ssm": 1536,
25
+ "mamba_d_state": 128,
26
+ "mamba_expand": 2,
27
+ "mamba_n_groups": 1,
28
+ "mamba_n_heads": 24,
29
+ "mamba_norm_before_gate": false,
30
+ "mamba_proj_bias": false,
31
+ "mamba_rms_norm": false,
32
+ "mamba_use_mlp": true,
33
+ "max_position_embeddings": 131072,
34
+ "mlp_bias": false,
35
+ "mlp_expansion_factor": 8,
36
+ "mlp_multipliers": [
37
+ 0.8838834764831844,
38
+ 0.5859375
39
+ ],
40
+ "model_type": "falcon_h1",
41
+ "num_attention_heads": 8,
42
+ "num_hidden_layers": 36,
43
+ "num_key_value_heads": 2,
44
+ "num_logits_to_keep": 1,
45
+ "pad_token_id": 0,
46
+ "projectors_bias": false,
47
+ "quantization": {
48
+ "group_size": 64,
49
+ "bits": 8
50
+ },
51
+ "quantization_config": {
52
+ "group_size": 64,
53
+ "bits": 8
54
+ },
55
+ "rms_norm_eps": 1e-05,
56
+ "rope_scaling": null,
57
+ "rope_theta": 100000000000.0,
58
+ "ssm_in_multiplier": 1.25,
59
+ "ssm_multipliers": [
60
+ 0.3535533905932738,
61
+ 0.25,
62
+ 0.3535533905932738,
63
+ 0.5,
64
+ 0.3535533905932738
65
+ ],
66
+ "ssm_out_multiplier": 0.23570226039551587,
67
+ "tie_word_embeddings": false,
68
+ "torch_dtype": "bfloat16",
69
+ "transformers_version": "4.52.0.dev0",
70
+ "use_cache": true,
71
+ "vocab_size": 32784
72
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [11, 228],
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.52.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5611d1444d5dc8844f7fa318ffa75e7e6415586a87f3399e93c1089544f59be
3
+ size 554511916
model.safetensors.index.json ADDED
@@ -0,0 +1,1239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 554374208,
4
+ "total_parameters": 521408512
5
+ },
6
+ "weight_map": {
7
+ "lm_head.biases": "model.safetensors",
8
+ "lm_head.scales": "model.safetensors",
9
+ "lm_head.weight": "model.safetensors",
10
+ "model.embed_tokens.biases": "model.safetensors",
11
+ "model.embed_tokens.scales": "model.safetensors",
12
+ "model.embed_tokens.weight": "model.safetensors",
13
+ "model.final_layernorm.weight": "model.safetensors",
14
+ "model.layers.0.feed_forward.down_proj.biases": "model.safetensors",
15
+ "model.layers.0.feed_forward.down_proj.scales": "model.safetensors",
16
+ "model.layers.0.feed_forward.down_proj.weight": "model.safetensors",
17
+ "model.layers.0.feed_forward.gate_proj.biases": "model.safetensors",
18
+ "model.layers.0.feed_forward.gate_proj.scales": "model.safetensors",
19
+ "model.layers.0.feed_forward.gate_proj.weight": "model.safetensors",
20
+ "model.layers.0.feed_forward.up_proj.biases": "model.safetensors",
21
+ "model.layers.0.feed_forward.up_proj.scales": "model.safetensors",
22
+ "model.layers.0.feed_forward.up_proj.weight": "model.safetensors",
23
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
24
+ "model.layers.0.mamba.A_log": "model.safetensors",
25
+ "model.layers.0.mamba.D": "model.safetensors",
26
+ "model.layers.0.mamba.conv1d.bias": "model.safetensors",
27
+ "model.layers.0.mamba.conv1d.weight": "model.safetensors",
28
+ "model.layers.0.mamba.dt_bias": "model.safetensors",
29
+ "model.layers.0.mamba.in_proj.biases": "model.safetensors",
30
+ "model.layers.0.mamba.in_proj.scales": "model.safetensors",
31
+ "model.layers.0.mamba.in_proj.weight": "model.safetensors",
32
+ "model.layers.0.mamba.out_proj.biases": "model.safetensors",
33
+ "model.layers.0.mamba.out_proj.scales": "model.safetensors",
34
+ "model.layers.0.mamba.out_proj.weight": "model.safetensors",
35
+ "model.layers.0.pre_ff_layernorm.weight": "model.safetensors",
36
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
37
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
38
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
39
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
40
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
41
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
42
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
43
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
44
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
45
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
46
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
47
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
48
+ "model.layers.1.feed_forward.down_proj.biases": "model.safetensors",
49
+ "model.layers.1.feed_forward.down_proj.scales": "model.safetensors",
50
+ "model.layers.1.feed_forward.down_proj.weight": "model.safetensors",
51
+ "model.layers.1.feed_forward.gate_proj.biases": "model.safetensors",
52
+ "model.layers.1.feed_forward.gate_proj.scales": "model.safetensors",
53
+ "model.layers.1.feed_forward.gate_proj.weight": "model.safetensors",
54
+ "model.layers.1.feed_forward.up_proj.biases": "model.safetensors",
55
+ "model.layers.1.feed_forward.up_proj.scales": "model.safetensors",
56
+ "model.layers.1.feed_forward.up_proj.weight": "model.safetensors",
57
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
58
+ "model.layers.1.mamba.A_log": "model.safetensors",
59
+ "model.layers.1.mamba.D": "model.safetensors",
60
+ "model.layers.1.mamba.conv1d.bias": "model.safetensors",
61
+ "model.layers.1.mamba.conv1d.weight": "model.safetensors",
62
+ "model.layers.1.mamba.dt_bias": "model.safetensors",
63
+ "model.layers.1.mamba.in_proj.biases": "model.safetensors",
64
+ "model.layers.1.mamba.in_proj.scales": "model.safetensors",
65
+ "model.layers.1.mamba.in_proj.weight": "model.safetensors",
66
+ "model.layers.1.mamba.out_proj.biases": "model.safetensors",
67
+ "model.layers.1.mamba.out_proj.scales": "model.safetensors",
68
+ "model.layers.1.mamba.out_proj.weight": "model.safetensors",
69
+ "model.layers.1.pre_ff_layernorm.weight": "model.safetensors",
70
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
71
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
72
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
73
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
74
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
75
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
76
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
77
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
78
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
79
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
80
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
81
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
82
+ "model.layers.10.feed_forward.down_proj.biases": "model.safetensors",
83
+ "model.layers.10.feed_forward.down_proj.scales": "model.safetensors",
84
+ "model.layers.10.feed_forward.down_proj.weight": "model.safetensors",
85
+ "model.layers.10.feed_forward.gate_proj.biases": "model.safetensors",
86
+ "model.layers.10.feed_forward.gate_proj.scales": "model.safetensors",
87
+ "model.layers.10.feed_forward.gate_proj.weight": "model.safetensors",
88
+ "model.layers.10.feed_forward.up_proj.biases": "model.safetensors",
89
+ "model.layers.10.feed_forward.up_proj.scales": "model.safetensors",
90
+ "model.layers.10.feed_forward.up_proj.weight": "model.safetensors",
91
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
92
+ "model.layers.10.mamba.A_log": "model.safetensors",
93
+ "model.layers.10.mamba.D": "model.safetensors",
94
+ "model.layers.10.mamba.conv1d.bias": "model.safetensors",
95
+ "model.layers.10.mamba.conv1d.weight": "model.safetensors",
96
+ "model.layers.10.mamba.dt_bias": "model.safetensors",
97
+ "model.layers.10.mamba.in_proj.biases": "model.safetensors",
98
+ "model.layers.10.mamba.in_proj.scales": "model.safetensors",
99
+ "model.layers.10.mamba.in_proj.weight": "model.safetensors",
100
+ "model.layers.10.mamba.out_proj.biases": "model.safetensors",
101
+ "model.layers.10.mamba.out_proj.scales": "model.safetensors",
102
+ "model.layers.10.mamba.out_proj.weight": "model.safetensors",
103
+ "model.layers.10.pre_ff_layernorm.weight": "model.safetensors",
104
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
105
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
106
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
107
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
108
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
109
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
110
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
111
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
112
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
113
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
114
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
115
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
116
+ "model.layers.11.feed_forward.down_proj.biases": "model.safetensors",
117
+ "model.layers.11.feed_forward.down_proj.scales": "model.safetensors",
118
+ "model.layers.11.feed_forward.down_proj.weight": "model.safetensors",
119
+ "model.layers.11.feed_forward.gate_proj.biases": "model.safetensors",
120
+ "model.layers.11.feed_forward.gate_proj.scales": "model.safetensors",
121
+ "model.layers.11.feed_forward.gate_proj.weight": "model.safetensors",
122
+ "model.layers.11.feed_forward.up_proj.biases": "model.safetensors",
123
+ "model.layers.11.feed_forward.up_proj.scales": "model.safetensors",
124
+ "model.layers.11.feed_forward.up_proj.weight": "model.safetensors",
125
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
126
+ "model.layers.11.mamba.A_log": "model.safetensors",
127
+ "model.layers.11.mamba.D": "model.safetensors",
128
+ "model.layers.11.mamba.conv1d.bias": "model.safetensors",
129
+ "model.layers.11.mamba.conv1d.weight": "model.safetensors",
130
+ "model.layers.11.mamba.dt_bias": "model.safetensors",
131
+ "model.layers.11.mamba.in_proj.biases": "model.safetensors",
132
+ "model.layers.11.mamba.in_proj.scales": "model.safetensors",
133
+ "model.layers.11.mamba.in_proj.weight": "model.safetensors",
134
+ "model.layers.11.mamba.out_proj.biases": "model.safetensors",
135
+ "model.layers.11.mamba.out_proj.scales": "model.safetensors",
136
+ "model.layers.11.mamba.out_proj.weight": "model.safetensors",
137
+ "model.layers.11.pre_ff_layernorm.weight": "model.safetensors",
138
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
139
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
140
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
141
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
142
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
143
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
144
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
145
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
146
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
147
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
148
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
149
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
150
+ "model.layers.12.feed_forward.down_proj.biases": "model.safetensors",
151
+ "model.layers.12.feed_forward.down_proj.scales": "model.safetensors",
152
+ "model.layers.12.feed_forward.down_proj.weight": "model.safetensors",
153
+ "model.layers.12.feed_forward.gate_proj.biases": "model.safetensors",
154
+ "model.layers.12.feed_forward.gate_proj.scales": "model.safetensors",
155
+ "model.layers.12.feed_forward.gate_proj.weight": "model.safetensors",
156
+ "model.layers.12.feed_forward.up_proj.biases": "model.safetensors",
157
+ "model.layers.12.feed_forward.up_proj.scales": "model.safetensors",
158
+ "model.layers.12.feed_forward.up_proj.weight": "model.safetensors",
159
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
160
+ "model.layers.12.mamba.A_log": "model.safetensors",
161
+ "model.layers.12.mamba.D": "model.safetensors",
162
+ "model.layers.12.mamba.conv1d.bias": "model.safetensors",
163
+ "model.layers.12.mamba.conv1d.weight": "model.safetensors",
164
+ "model.layers.12.mamba.dt_bias": "model.safetensors",
165
+ "model.layers.12.mamba.in_proj.biases": "model.safetensors",
166
+ "model.layers.12.mamba.in_proj.scales": "model.safetensors",
167
+ "model.layers.12.mamba.in_proj.weight": "model.safetensors",
168
+ "model.layers.12.mamba.out_proj.biases": "model.safetensors",
169
+ "model.layers.12.mamba.out_proj.scales": "model.safetensors",
170
+ "model.layers.12.mamba.out_proj.weight": "model.safetensors",
171
+ "model.layers.12.pre_ff_layernorm.weight": "model.safetensors",
172
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
173
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
174
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
175
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
176
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
177
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
178
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
179
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
180
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
181
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
182
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
183
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
184
+ "model.layers.13.feed_forward.down_proj.biases": "model.safetensors",
185
+ "model.layers.13.feed_forward.down_proj.scales": "model.safetensors",
186
+ "model.layers.13.feed_forward.down_proj.weight": "model.safetensors",
187
+ "model.layers.13.feed_forward.gate_proj.biases": "model.safetensors",
188
+ "model.layers.13.feed_forward.gate_proj.scales": "model.safetensors",
189
+ "model.layers.13.feed_forward.gate_proj.weight": "model.safetensors",
190
+ "model.layers.13.feed_forward.up_proj.biases": "model.safetensors",
191
+ "model.layers.13.feed_forward.up_proj.scales": "model.safetensors",
192
+ "model.layers.13.feed_forward.up_proj.weight": "model.safetensors",
193
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
194
+ "model.layers.13.mamba.A_log": "model.safetensors",
195
+ "model.layers.13.mamba.D": "model.safetensors",
196
+ "model.layers.13.mamba.conv1d.bias": "model.safetensors",
197
+ "model.layers.13.mamba.conv1d.weight": "model.safetensors",
198
+ "model.layers.13.mamba.dt_bias": "model.safetensors",
199
+ "model.layers.13.mamba.in_proj.biases": "model.safetensors",
200
+ "model.layers.13.mamba.in_proj.scales": "model.safetensors",
201
+ "model.layers.13.mamba.in_proj.weight": "model.safetensors",
202
+ "model.layers.13.mamba.out_proj.biases": "model.safetensors",
203
+ "model.layers.13.mamba.out_proj.scales": "model.safetensors",
204
+ "model.layers.13.mamba.out_proj.weight": "model.safetensors",
205
+ "model.layers.13.pre_ff_layernorm.weight": "model.safetensors",
206
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
207
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
208
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
209
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
210
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
211
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
212
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
213
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
214
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
215
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
216
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
217
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
218
+ "model.layers.14.feed_forward.down_proj.biases": "model.safetensors",
219
+ "model.layers.14.feed_forward.down_proj.scales": "model.safetensors",
220
+ "model.layers.14.feed_forward.down_proj.weight": "model.safetensors",
221
+ "model.layers.14.feed_forward.gate_proj.biases": "model.safetensors",
222
+ "model.layers.14.feed_forward.gate_proj.scales": "model.safetensors",
223
+ "model.layers.14.feed_forward.gate_proj.weight": "model.safetensors",
224
+ "model.layers.14.feed_forward.up_proj.biases": "model.safetensors",
225
+ "model.layers.14.feed_forward.up_proj.scales": "model.safetensors",
226
+ "model.layers.14.feed_forward.up_proj.weight": "model.safetensors",
227
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
228
+ "model.layers.14.mamba.A_log": "model.safetensors",
229
+ "model.layers.14.mamba.D": "model.safetensors",
230
+ "model.layers.14.mamba.conv1d.bias": "model.safetensors",
231
+ "model.layers.14.mamba.conv1d.weight": "model.safetensors",
232
+ "model.layers.14.mamba.dt_bias": "model.safetensors",
233
+ "model.layers.14.mamba.in_proj.biases": "model.safetensors",
234
+ "model.layers.14.mamba.in_proj.scales": "model.safetensors",
235
+ "model.layers.14.mamba.in_proj.weight": "model.safetensors",
236
+ "model.layers.14.mamba.out_proj.biases": "model.safetensors",
237
+ "model.layers.14.mamba.out_proj.scales": "model.safetensors",
238
+ "model.layers.14.mamba.out_proj.weight": "model.safetensors",
239
+ "model.layers.14.pre_ff_layernorm.weight": "model.safetensors",
240
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
241
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
242
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
243
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
244
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
245
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
246
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
247
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
248
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
249
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
250
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
251
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
252
+ "model.layers.15.feed_forward.down_proj.biases": "model.safetensors",
253
+ "model.layers.15.feed_forward.down_proj.scales": "model.safetensors",
254
+ "model.layers.15.feed_forward.down_proj.weight": "model.safetensors",
255
+ "model.layers.15.feed_forward.gate_proj.biases": "model.safetensors",
256
+ "model.layers.15.feed_forward.gate_proj.scales": "model.safetensors",
257
+ "model.layers.15.feed_forward.gate_proj.weight": "model.safetensors",
258
+ "model.layers.15.feed_forward.up_proj.biases": "model.safetensors",
259
+ "model.layers.15.feed_forward.up_proj.scales": "model.safetensors",
260
+ "model.layers.15.feed_forward.up_proj.weight": "model.safetensors",
261
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
262
+ "model.layers.15.mamba.A_log": "model.safetensors",
263
+ "model.layers.15.mamba.D": "model.safetensors",
264
+ "model.layers.15.mamba.conv1d.bias": "model.safetensors",
265
+ "model.layers.15.mamba.conv1d.weight": "model.safetensors",
266
+ "model.layers.15.mamba.dt_bias": "model.safetensors",
267
+ "model.layers.15.mamba.in_proj.biases": "model.safetensors",
268
+ "model.layers.15.mamba.in_proj.scales": "model.safetensors",
269
+ "model.layers.15.mamba.in_proj.weight": "model.safetensors",
270
+ "model.layers.15.mamba.out_proj.biases": "model.safetensors",
271
+ "model.layers.15.mamba.out_proj.scales": "model.safetensors",
272
+ "model.layers.15.mamba.out_proj.weight": "model.safetensors",
273
+ "model.layers.15.pre_ff_layernorm.weight": "model.safetensors",
274
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
275
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
276
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
277
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
278
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
279
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
280
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
281
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
282
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
283
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
284
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
285
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
286
+ "model.layers.16.feed_forward.down_proj.biases": "model.safetensors",
287
+ "model.layers.16.feed_forward.down_proj.scales": "model.safetensors",
288
+ "model.layers.16.feed_forward.down_proj.weight": "model.safetensors",
289
+ "model.layers.16.feed_forward.gate_proj.biases": "model.safetensors",
290
+ "model.layers.16.feed_forward.gate_proj.scales": "model.safetensors",
291
+ "model.layers.16.feed_forward.gate_proj.weight": "model.safetensors",
292
+ "model.layers.16.feed_forward.up_proj.biases": "model.safetensors",
293
+ "model.layers.16.feed_forward.up_proj.scales": "model.safetensors",
294
+ "model.layers.16.feed_forward.up_proj.weight": "model.safetensors",
295
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
296
+ "model.layers.16.mamba.A_log": "model.safetensors",
297
+ "model.layers.16.mamba.D": "model.safetensors",
298
+ "model.layers.16.mamba.conv1d.bias": "model.safetensors",
299
+ "model.layers.16.mamba.conv1d.weight": "model.safetensors",
300
+ "model.layers.16.mamba.dt_bias": "model.safetensors",
301
+ "model.layers.16.mamba.in_proj.biases": "model.safetensors",
302
+ "model.layers.16.mamba.in_proj.scales": "model.safetensors",
303
+ "model.layers.16.mamba.in_proj.weight": "model.safetensors",
304
+ "model.layers.16.mamba.out_proj.biases": "model.safetensors",
305
+ "model.layers.16.mamba.out_proj.scales": "model.safetensors",
306
+ "model.layers.16.mamba.out_proj.weight": "model.safetensors",
307
+ "model.layers.16.pre_ff_layernorm.weight": "model.safetensors",
308
+ "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
309
+ "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
310
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
311
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
312
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
313
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
314
+ "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
315
+ "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
316
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
317
+ "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
318
+ "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
319
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
320
+ "model.layers.17.feed_forward.down_proj.biases": "model.safetensors",
321
+ "model.layers.17.feed_forward.down_proj.scales": "model.safetensors",
322
+ "model.layers.17.feed_forward.down_proj.weight": "model.safetensors",
323
+ "model.layers.17.feed_forward.gate_proj.biases": "model.safetensors",
324
+ "model.layers.17.feed_forward.gate_proj.scales": "model.safetensors",
325
+ "model.layers.17.feed_forward.gate_proj.weight": "model.safetensors",
326
+ "model.layers.17.feed_forward.up_proj.biases": "model.safetensors",
327
+ "model.layers.17.feed_forward.up_proj.scales": "model.safetensors",
328
+ "model.layers.17.feed_forward.up_proj.weight": "model.safetensors",
329
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
330
+ "model.layers.17.mamba.A_log": "model.safetensors",
331
+ "model.layers.17.mamba.D": "model.safetensors",
332
+ "model.layers.17.mamba.conv1d.bias": "model.safetensors",
333
+ "model.layers.17.mamba.conv1d.weight": "model.safetensors",
334
+ "model.layers.17.mamba.dt_bias": "model.safetensors",
335
+ "model.layers.17.mamba.in_proj.biases": "model.safetensors",
336
+ "model.layers.17.mamba.in_proj.scales": "model.safetensors",
337
+ "model.layers.17.mamba.in_proj.weight": "model.safetensors",
338
+ "model.layers.17.mamba.out_proj.biases": "model.safetensors",
339
+ "model.layers.17.mamba.out_proj.scales": "model.safetensors",
340
+ "model.layers.17.mamba.out_proj.weight": "model.safetensors",
341
+ "model.layers.17.pre_ff_layernorm.weight": "model.safetensors",
342
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
343
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
344
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
345
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
346
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
347
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
348
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
349
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
350
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
351
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
352
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
353
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
354
+ "model.layers.18.feed_forward.down_proj.biases": "model.safetensors",
355
+ "model.layers.18.feed_forward.down_proj.scales": "model.safetensors",
356
+ "model.layers.18.feed_forward.down_proj.weight": "model.safetensors",
357
+ "model.layers.18.feed_forward.gate_proj.biases": "model.safetensors",
358
+ "model.layers.18.feed_forward.gate_proj.scales": "model.safetensors",
359
+ "model.layers.18.feed_forward.gate_proj.weight": "model.safetensors",
360
+ "model.layers.18.feed_forward.up_proj.biases": "model.safetensors",
361
+ "model.layers.18.feed_forward.up_proj.scales": "model.safetensors",
362
+ "model.layers.18.feed_forward.up_proj.weight": "model.safetensors",
363
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
364
+ "model.layers.18.mamba.A_log": "model.safetensors",
365
+ "model.layers.18.mamba.D": "model.safetensors",
366
+ "model.layers.18.mamba.conv1d.bias": "model.safetensors",
367
+ "model.layers.18.mamba.conv1d.weight": "model.safetensors",
368
+ "model.layers.18.mamba.dt_bias": "model.safetensors",
369
+ "model.layers.18.mamba.in_proj.biases": "model.safetensors",
370
+ "model.layers.18.mamba.in_proj.scales": "model.safetensors",
371
+ "model.layers.18.mamba.in_proj.weight": "model.safetensors",
372
+ "model.layers.18.mamba.out_proj.biases": "model.safetensors",
373
+ "model.layers.18.mamba.out_proj.scales": "model.safetensors",
374
+ "model.layers.18.mamba.out_proj.weight": "model.safetensors",
375
+ "model.layers.18.pre_ff_layernorm.weight": "model.safetensors",
376
+ "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
377
+ "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
378
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
379
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
380
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
381
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
382
+ "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
383
+ "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
384
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
385
+ "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
386
+ "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
387
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
388
+ "model.layers.19.feed_forward.down_proj.biases": "model.safetensors",
389
+ "model.layers.19.feed_forward.down_proj.scales": "model.safetensors",
390
+ "model.layers.19.feed_forward.down_proj.weight": "model.safetensors",
391
+ "model.layers.19.feed_forward.gate_proj.biases": "model.safetensors",
392
+ "model.layers.19.feed_forward.gate_proj.scales": "model.safetensors",
393
+ "model.layers.19.feed_forward.gate_proj.weight": "model.safetensors",
394
+ "model.layers.19.feed_forward.up_proj.biases": "model.safetensors",
395
+ "model.layers.19.feed_forward.up_proj.scales": "model.safetensors",
396
+ "model.layers.19.feed_forward.up_proj.weight": "model.safetensors",
397
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
398
+ "model.layers.19.mamba.A_log": "model.safetensors",
399
+ "model.layers.19.mamba.D": "model.safetensors",
400
+ "model.layers.19.mamba.conv1d.bias": "model.safetensors",
401
+ "model.layers.19.mamba.conv1d.weight": "model.safetensors",
402
+ "model.layers.19.mamba.dt_bias": "model.safetensors",
403
+ "model.layers.19.mamba.in_proj.biases": "model.safetensors",
404
+ "model.layers.19.mamba.in_proj.scales": "model.safetensors",
405
+ "model.layers.19.mamba.in_proj.weight": "model.safetensors",
406
+ "model.layers.19.mamba.out_proj.biases": "model.safetensors",
407
+ "model.layers.19.mamba.out_proj.scales": "model.safetensors",
408
+ "model.layers.19.mamba.out_proj.weight": "model.safetensors",
409
+ "model.layers.19.pre_ff_layernorm.weight": "model.safetensors",
410
+ "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
411
+ "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
412
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
413
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
414
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
415
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
416
+ "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
417
+ "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
418
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
419
+ "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
420
+ "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
421
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
422
+ "model.layers.2.feed_forward.down_proj.biases": "model.safetensors",
423
+ "model.layers.2.feed_forward.down_proj.scales": "model.safetensors",
424
+ "model.layers.2.feed_forward.down_proj.weight": "model.safetensors",
425
+ "model.layers.2.feed_forward.gate_proj.biases": "model.safetensors",
426
+ "model.layers.2.feed_forward.gate_proj.scales": "model.safetensors",
427
+ "model.layers.2.feed_forward.gate_proj.weight": "model.safetensors",
428
+ "model.layers.2.feed_forward.up_proj.biases": "model.safetensors",
429
+ "model.layers.2.feed_forward.up_proj.scales": "model.safetensors",
430
+ "model.layers.2.feed_forward.up_proj.weight": "model.safetensors",
431
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
432
+ "model.layers.2.mamba.A_log": "model.safetensors",
433
+ "model.layers.2.mamba.D": "model.safetensors",
434
+ "model.layers.2.mamba.conv1d.bias": "model.safetensors",
435
+ "model.layers.2.mamba.conv1d.weight": "model.safetensors",
436
+ "model.layers.2.mamba.dt_bias": "model.safetensors",
437
+ "model.layers.2.mamba.in_proj.biases": "model.safetensors",
438
+ "model.layers.2.mamba.in_proj.scales": "model.safetensors",
439
+ "model.layers.2.mamba.in_proj.weight": "model.safetensors",
440
+ "model.layers.2.mamba.out_proj.biases": "model.safetensors",
441
+ "model.layers.2.mamba.out_proj.scales": "model.safetensors",
442
+ "model.layers.2.mamba.out_proj.weight": "model.safetensors",
443
+ "model.layers.2.pre_ff_layernorm.weight": "model.safetensors",
444
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
445
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
446
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
447
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
448
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
449
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
450
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
451
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
452
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
453
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
454
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
455
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
456
+ "model.layers.20.feed_forward.down_proj.biases": "model.safetensors",
457
+ "model.layers.20.feed_forward.down_proj.scales": "model.safetensors",
458
+ "model.layers.20.feed_forward.down_proj.weight": "model.safetensors",
459
+ "model.layers.20.feed_forward.gate_proj.biases": "model.safetensors",
460
+ "model.layers.20.feed_forward.gate_proj.scales": "model.safetensors",
461
+ "model.layers.20.feed_forward.gate_proj.weight": "model.safetensors",
462
+ "model.layers.20.feed_forward.up_proj.biases": "model.safetensors",
463
+ "model.layers.20.feed_forward.up_proj.scales": "model.safetensors",
464
+ "model.layers.20.feed_forward.up_proj.weight": "model.safetensors",
465
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
466
+ "model.layers.20.mamba.A_log": "model.safetensors",
467
+ "model.layers.20.mamba.D": "model.safetensors",
468
+ "model.layers.20.mamba.conv1d.bias": "model.safetensors",
469
+ "model.layers.20.mamba.conv1d.weight": "model.safetensors",
470
+ "model.layers.20.mamba.dt_bias": "model.safetensors",
471
+ "model.layers.20.mamba.in_proj.biases": "model.safetensors",
472
+ "model.layers.20.mamba.in_proj.scales": "model.safetensors",
473
+ "model.layers.20.mamba.in_proj.weight": "model.safetensors",
474
+ "model.layers.20.mamba.out_proj.biases": "model.safetensors",
475
+ "model.layers.20.mamba.out_proj.scales": "model.safetensors",
476
+ "model.layers.20.mamba.out_proj.weight": "model.safetensors",
477
+ "model.layers.20.pre_ff_layernorm.weight": "model.safetensors",
478
+ "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
479
+ "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
480
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
481
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
482
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
483
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
484
+ "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
485
+ "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
486
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
487
+ "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
488
+ "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
489
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
490
+ "model.layers.21.feed_forward.down_proj.biases": "model.safetensors",
491
+ "model.layers.21.feed_forward.down_proj.scales": "model.safetensors",
492
+ "model.layers.21.feed_forward.down_proj.weight": "model.safetensors",
493
+ "model.layers.21.feed_forward.gate_proj.biases": "model.safetensors",
494
+ "model.layers.21.feed_forward.gate_proj.scales": "model.safetensors",
495
+ "model.layers.21.feed_forward.gate_proj.weight": "model.safetensors",
496
+ "model.layers.21.feed_forward.up_proj.biases": "model.safetensors",
497
+ "model.layers.21.feed_forward.up_proj.scales": "model.safetensors",
498
+ "model.layers.21.feed_forward.up_proj.weight": "model.safetensors",
499
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
500
+ "model.layers.21.mamba.A_log": "model.safetensors",
501
+ "model.layers.21.mamba.D": "model.safetensors",
502
+ "model.layers.21.mamba.conv1d.bias": "model.safetensors",
503
+ "model.layers.21.mamba.conv1d.weight": "model.safetensors",
504
+ "model.layers.21.mamba.dt_bias": "model.safetensors",
505
+ "model.layers.21.mamba.in_proj.biases": "model.safetensors",
506
+ "model.layers.21.mamba.in_proj.scales": "model.safetensors",
507
+ "model.layers.21.mamba.in_proj.weight": "model.safetensors",
508
+ "model.layers.21.mamba.out_proj.biases": "model.safetensors",
509
+ "model.layers.21.mamba.out_proj.scales": "model.safetensors",
510
+ "model.layers.21.mamba.out_proj.weight": "model.safetensors",
511
+ "model.layers.21.pre_ff_layernorm.weight": "model.safetensors",
512
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
513
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
514
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
515
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
516
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
517
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
518
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
519
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
520
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
521
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
522
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
523
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
524
+ "model.layers.22.feed_forward.down_proj.biases": "model.safetensors",
525
+ "model.layers.22.feed_forward.down_proj.scales": "model.safetensors",
526
+ "model.layers.22.feed_forward.down_proj.weight": "model.safetensors",
527
+ "model.layers.22.feed_forward.gate_proj.biases": "model.safetensors",
528
+ "model.layers.22.feed_forward.gate_proj.scales": "model.safetensors",
529
+ "model.layers.22.feed_forward.gate_proj.weight": "model.safetensors",
530
+ "model.layers.22.feed_forward.up_proj.biases": "model.safetensors",
531
+ "model.layers.22.feed_forward.up_proj.scales": "model.safetensors",
532
+ "model.layers.22.feed_forward.up_proj.weight": "model.safetensors",
533
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
534
+ "model.layers.22.mamba.A_log": "model.safetensors",
535
+ "model.layers.22.mamba.D": "model.safetensors",
536
+ "model.layers.22.mamba.conv1d.bias": "model.safetensors",
537
+ "model.layers.22.mamba.conv1d.weight": "model.safetensors",
538
+ "model.layers.22.mamba.dt_bias": "model.safetensors",
539
+ "model.layers.22.mamba.in_proj.biases": "model.safetensors",
540
+ "model.layers.22.mamba.in_proj.scales": "model.safetensors",
541
+ "model.layers.22.mamba.in_proj.weight": "model.safetensors",
542
+ "model.layers.22.mamba.out_proj.biases": "model.safetensors",
543
+ "model.layers.22.mamba.out_proj.scales": "model.safetensors",
544
+ "model.layers.22.mamba.out_proj.weight": "model.safetensors",
545
+ "model.layers.22.pre_ff_layernorm.weight": "model.safetensors",
546
+ "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
547
+ "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
548
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
549
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
550
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
551
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
552
+ "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
553
+ "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
554
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
555
+ "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
556
+ "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
557
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
558
+ "model.layers.23.feed_forward.down_proj.biases": "model.safetensors",
559
+ "model.layers.23.feed_forward.down_proj.scales": "model.safetensors",
560
+ "model.layers.23.feed_forward.down_proj.weight": "model.safetensors",
561
+ "model.layers.23.feed_forward.gate_proj.biases": "model.safetensors",
562
+ "model.layers.23.feed_forward.gate_proj.scales": "model.safetensors",
563
+ "model.layers.23.feed_forward.gate_proj.weight": "model.safetensors",
564
+ "model.layers.23.feed_forward.up_proj.biases": "model.safetensors",
565
+ "model.layers.23.feed_forward.up_proj.scales": "model.safetensors",
566
+ "model.layers.23.feed_forward.up_proj.weight": "model.safetensors",
567
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
568
+ "model.layers.23.mamba.A_log": "model.safetensors",
569
+ "model.layers.23.mamba.D": "model.safetensors",
570
+ "model.layers.23.mamba.conv1d.bias": "model.safetensors",
571
+ "model.layers.23.mamba.conv1d.weight": "model.safetensors",
572
+ "model.layers.23.mamba.dt_bias": "model.safetensors",
573
+ "model.layers.23.mamba.in_proj.biases": "model.safetensors",
574
+ "model.layers.23.mamba.in_proj.scales": "model.safetensors",
575
+ "model.layers.23.mamba.in_proj.weight": "model.safetensors",
576
+ "model.layers.23.mamba.out_proj.biases": "model.safetensors",
577
+ "model.layers.23.mamba.out_proj.scales": "model.safetensors",
578
+ "model.layers.23.mamba.out_proj.weight": "model.safetensors",
579
+ "model.layers.23.pre_ff_layernorm.weight": "model.safetensors",
580
+ "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
581
+ "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
582
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
583
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
584
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
585
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
586
+ "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
587
+ "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
588
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
589
+ "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
590
+ "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
591
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
592
+ "model.layers.24.feed_forward.down_proj.biases": "model.safetensors",
593
+ "model.layers.24.feed_forward.down_proj.scales": "model.safetensors",
594
+ "model.layers.24.feed_forward.down_proj.weight": "model.safetensors",
595
+ "model.layers.24.feed_forward.gate_proj.biases": "model.safetensors",
596
+ "model.layers.24.feed_forward.gate_proj.scales": "model.safetensors",
597
+ "model.layers.24.feed_forward.gate_proj.weight": "model.safetensors",
598
+ "model.layers.24.feed_forward.up_proj.biases": "model.safetensors",
599
+ "model.layers.24.feed_forward.up_proj.scales": "model.safetensors",
600
+ "model.layers.24.feed_forward.up_proj.weight": "model.safetensors",
601
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
602
+ "model.layers.24.mamba.A_log": "model.safetensors",
603
+ "model.layers.24.mamba.D": "model.safetensors",
604
+ "model.layers.24.mamba.conv1d.bias": "model.safetensors",
605
+ "model.layers.24.mamba.conv1d.weight": "model.safetensors",
606
+ "model.layers.24.mamba.dt_bias": "model.safetensors",
607
+ "model.layers.24.mamba.in_proj.biases": "model.safetensors",
608
+ "model.layers.24.mamba.in_proj.scales": "model.safetensors",
609
+ "model.layers.24.mamba.in_proj.weight": "model.safetensors",
610
+ "model.layers.24.mamba.out_proj.biases": "model.safetensors",
611
+ "model.layers.24.mamba.out_proj.scales": "model.safetensors",
612
+ "model.layers.24.mamba.out_proj.weight": "model.safetensors",
613
+ "model.layers.24.pre_ff_layernorm.weight": "model.safetensors",
614
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
615
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
616
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
617
+ "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
618
+ "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
619
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
620
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
621
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
622
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
623
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
624
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
625
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
626
+ "model.layers.25.feed_forward.down_proj.biases": "model.safetensors",
627
+ "model.layers.25.feed_forward.down_proj.scales": "model.safetensors",
628
+ "model.layers.25.feed_forward.down_proj.weight": "model.safetensors",
629
+ "model.layers.25.feed_forward.gate_proj.biases": "model.safetensors",
630
+ "model.layers.25.feed_forward.gate_proj.scales": "model.safetensors",
631
+ "model.layers.25.feed_forward.gate_proj.weight": "model.safetensors",
632
+ "model.layers.25.feed_forward.up_proj.biases": "model.safetensors",
633
+ "model.layers.25.feed_forward.up_proj.scales": "model.safetensors",
634
+ "model.layers.25.feed_forward.up_proj.weight": "model.safetensors",
635
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
636
+ "model.layers.25.mamba.A_log": "model.safetensors",
637
+ "model.layers.25.mamba.D": "model.safetensors",
638
+ "model.layers.25.mamba.conv1d.bias": "model.safetensors",
639
+ "model.layers.25.mamba.conv1d.weight": "model.safetensors",
640
+ "model.layers.25.mamba.dt_bias": "model.safetensors",
641
+ "model.layers.25.mamba.in_proj.biases": "model.safetensors",
642
+ "model.layers.25.mamba.in_proj.scales": "model.safetensors",
643
+ "model.layers.25.mamba.in_proj.weight": "model.safetensors",
644
+ "model.layers.25.mamba.out_proj.biases": "model.safetensors",
645
+ "model.layers.25.mamba.out_proj.scales": "model.safetensors",
646
+ "model.layers.25.mamba.out_proj.weight": "model.safetensors",
647
+ "model.layers.25.pre_ff_layernorm.weight": "model.safetensors",
648
+ "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
649
+ "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
650
+ "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
651
+ "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
652
+ "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
653
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
654
+ "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
655
+ "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
656
+ "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
657
+ "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
658
+ "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
659
+ "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
660
+ "model.layers.26.feed_forward.down_proj.biases": "model.safetensors",
661
+ "model.layers.26.feed_forward.down_proj.scales": "model.safetensors",
662
+ "model.layers.26.feed_forward.down_proj.weight": "model.safetensors",
663
+ "model.layers.26.feed_forward.gate_proj.biases": "model.safetensors",
664
+ "model.layers.26.feed_forward.gate_proj.scales": "model.safetensors",
665
+ "model.layers.26.feed_forward.gate_proj.weight": "model.safetensors",
666
+ "model.layers.26.feed_forward.up_proj.biases": "model.safetensors",
667
+ "model.layers.26.feed_forward.up_proj.scales": "model.safetensors",
668
+ "model.layers.26.feed_forward.up_proj.weight": "model.safetensors",
669
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
670
+ "model.layers.26.mamba.A_log": "model.safetensors",
671
+ "model.layers.26.mamba.D": "model.safetensors",
672
+ "model.layers.26.mamba.conv1d.bias": "model.safetensors",
673
+ "model.layers.26.mamba.conv1d.weight": "model.safetensors",
674
+ "model.layers.26.mamba.dt_bias": "model.safetensors",
675
+ "model.layers.26.mamba.in_proj.biases": "model.safetensors",
676
+ "model.layers.26.mamba.in_proj.scales": "model.safetensors",
677
+ "model.layers.26.mamba.in_proj.weight": "model.safetensors",
678
+ "model.layers.26.mamba.out_proj.biases": "model.safetensors",
679
+ "model.layers.26.mamba.out_proj.scales": "model.safetensors",
680
+ "model.layers.26.mamba.out_proj.weight": "model.safetensors",
681
+ "model.layers.26.pre_ff_layernorm.weight": "model.safetensors",
682
+ "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
683
+ "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
684
+ "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
685
+ "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
686
+ "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
687
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
688
+ "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
689
+ "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
690
+ "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
691
+ "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
692
+ "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
693
+ "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
694
+ "model.layers.27.feed_forward.down_proj.biases": "model.safetensors",
695
+ "model.layers.27.feed_forward.down_proj.scales": "model.safetensors",
696
+ "model.layers.27.feed_forward.down_proj.weight": "model.safetensors",
697
+ "model.layers.27.feed_forward.gate_proj.biases": "model.safetensors",
698
+ "model.layers.27.feed_forward.gate_proj.scales": "model.safetensors",
699
+ "model.layers.27.feed_forward.gate_proj.weight": "model.safetensors",
700
+ "model.layers.27.feed_forward.up_proj.biases": "model.safetensors",
701
+ "model.layers.27.feed_forward.up_proj.scales": "model.safetensors",
702
+ "model.layers.27.feed_forward.up_proj.weight": "model.safetensors",
703
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
704
+ "model.layers.27.mamba.A_log": "model.safetensors",
705
+ "model.layers.27.mamba.D": "model.safetensors",
706
+ "model.layers.27.mamba.conv1d.bias": "model.safetensors",
707
+ "model.layers.27.mamba.conv1d.weight": "model.safetensors",
708
+ "model.layers.27.mamba.dt_bias": "model.safetensors",
709
+ "model.layers.27.mamba.in_proj.biases": "model.safetensors",
710
+ "model.layers.27.mamba.in_proj.scales": "model.safetensors",
711
+ "model.layers.27.mamba.in_proj.weight": "model.safetensors",
712
+ "model.layers.27.mamba.out_proj.biases": "model.safetensors",
713
+ "model.layers.27.mamba.out_proj.scales": "model.safetensors",
714
+ "model.layers.27.mamba.out_proj.weight": "model.safetensors",
715
+ "model.layers.27.pre_ff_layernorm.weight": "model.safetensors",
716
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
717
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
718
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
719
+ "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
720
+ "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
721
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
722
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
723
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
724
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
725
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
726
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
727
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
728
+ "model.layers.28.feed_forward.down_proj.biases": "model.safetensors",
729
+ "model.layers.28.feed_forward.down_proj.scales": "model.safetensors",
730
+ "model.layers.28.feed_forward.down_proj.weight": "model.safetensors",
731
+ "model.layers.28.feed_forward.gate_proj.biases": "model.safetensors",
732
+ "model.layers.28.feed_forward.gate_proj.scales": "model.safetensors",
733
+ "model.layers.28.feed_forward.gate_proj.weight": "model.safetensors",
734
+ "model.layers.28.feed_forward.up_proj.biases": "model.safetensors",
735
+ "model.layers.28.feed_forward.up_proj.scales": "model.safetensors",
736
+ "model.layers.28.feed_forward.up_proj.weight": "model.safetensors",
737
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
738
+ "model.layers.28.mamba.A_log": "model.safetensors",
739
+ "model.layers.28.mamba.D": "model.safetensors",
740
+ "model.layers.28.mamba.conv1d.bias": "model.safetensors",
741
+ "model.layers.28.mamba.conv1d.weight": "model.safetensors",
742
+ "model.layers.28.mamba.dt_bias": "model.safetensors",
743
+ "model.layers.28.mamba.in_proj.biases": "model.safetensors",
744
+ "model.layers.28.mamba.in_proj.scales": "model.safetensors",
745
+ "model.layers.28.mamba.in_proj.weight": "model.safetensors",
746
+ "model.layers.28.mamba.out_proj.biases": "model.safetensors",
747
+ "model.layers.28.mamba.out_proj.scales": "model.safetensors",
748
+ "model.layers.28.mamba.out_proj.weight": "model.safetensors",
749
+ "model.layers.28.pre_ff_layernorm.weight": "model.safetensors",
750
+ "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
751
+ "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
752
+ "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
753
+ "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
754
+ "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
755
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
756
+ "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
757
+ "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
758
+ "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
759
+ "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
760
+ "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
761
+ "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
762
+ "model.layers.29.feed_forward.down_proj.biases": "model.safetensors",
763
+ "model.layers.29.feed_forward.down_proj.scales": "model.safetensors",
764
+ "model.layers.29.feed_forward.down_proj.weight": "model.safetensors",
765
+ "model.layers.29.feed_forward.gate_proj.biases": "model.safetensors",
766
+ "model.layers.29.feed_forward.gate_proj.scales": "model.safetensors",
767
+ "model.layers.29.feed_forward.gate_proj.weight": "model.safetensors",
768
+ "model.layers.29.feed_forward.up_proj.biases": "model.safetensors",
769
+ "model.layers.29.feed_forward.up_proj.scales": "model.safetensors",
770
+ "model.layers.29.feed_forward.up_proj.weight": "model.safetensors",
771
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
772
+ "model.layers.29.mamba.A_log": "model.safetensors",
773
+ "model.layers.29.mamba.D": "model.safetensors",
774
+ "model.layers.29.mamba.conv1d.bias": "model.safetensors",
775
+ "model.layers.29.mamba.conv1d.weight": "model.safetensors",
776
+ "model.layers.29.mamba.dt_bias": "model.safetensors",
777
+ "model.layers.29.mamba.in_proj.biases": "model.safetensors",
778
+ "model.layers.29.mamba.in_proj.scales": "model.safetensors",
779
+ "model.layers.29.mamba.in_proj.weight": "model.safetensors",
780
+ "model.layers.29.mamba.out_proj.biases": "model.safetensors",
781
+ "model.layers.29.mamba.out_proj.scales": "model.safetensors",
782
+ "model.layers.29.mamba.out_proj.weight": "model.safetensors",
783
+ "model.layers.29.pre_ff_layernorm.weight": "model.safetensors",
784
+ "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
785
+ "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
786
+ "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
787
+ "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
788
+ "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
789
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
790
+ "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
791
+ "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
792
+ "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
793
+ "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
794
+ "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
795
+ "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
796
+ "model.layers.3.feed_forward.down_proj.biases": "model.safetensors",
797
+ "model.layers.3.feed_forward.down_proj.scales": "model.safetensors",
798
+ "model.layers.3.feed_forward.down_proj.weight": "model.safetensors",
799
+ "model.layers.3.feed_forward.gate_proj.biases": "model.safetensors",
800
+ "model.layers.3.feed_forward.gate_proj.scales": "model.safetensors",
801
+ "model.layers.3.feed_forward.gate_proj.weight": "model.safetensors",
802
+ "model.layers.3.feed_forward.up_proj.biases": "model.safetensors",
803
+ "model.layers.3.feed_forward.up_proj.scales": "model.safetensors",
804
+ "model.layers.3.feed_forward.up_proj.weight": "model.safetensors",
805
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
806
+ "model.layers.3.mamba.A_log": "model.safetensors",
807
+ "model.layers.3.mamba.D": "model.safetensors",
808
+ "model.layers.3.mamba.conv1d.bias": "model.safetensors",
809
+ "model.layers.3.mamba.conv1d.weight": "model.safetensors",
810
+ "model.layers.3.mamba.dt_bias": "model.safetensors",
811
+ "model.layers.3.mamba.in_proj.biases": "model.safetensors",
812
+ "model.layers.3.mamba.in_proj.scales": "model.safetensors",
813
+ "model.layers.3.mamba.in_proj.weight": "model.safetensors",
814
+ "model.layers.3.mamba.out_proj.biases": "model.safetensors",
815
+ "model.layers.3.mamba.out_proj.scales": "model.safetensors",
816
+ "model.layers.3.mamba.out_proj.weight": "model.safetensors",
817
+ "model.layers.3.pre_ff_layernorm.weight": "model.safetensors",
818
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
819
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
820
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
821
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
822
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
823
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
824
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
825
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
826
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
827
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
828
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
829
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
830
+ "model.layers.30.feed_forward.down_proj.biases": "model.safetensors",
831
+ "model.layers.30.feed_forward.down_proj.scales": "model.safetensors",
832
+ "model.layers.30.feed_forward.down_proj.weight": "model.safetensors",
833
+ "model.layers.30.feed_forward.gate_proj.biases": "model.safetensors",
834
+ "model.layers.30.feed_forward.gate_proj.scales": "model.safetensors",
835
+ "model.layers.30.feed_forward.gate_proj.weight": "model.safetensors",
836
+ "model.layers.30.feed_forward.up_proj.biases": "model.safetensors",
837
+ "model.layers.30.feed_forward.up_proj.scales": "model.safetensors",
838
+ "model.layers.30.feed_forward.up_proj.weight": "model.safetensors",
839
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
840
+ "model.layers.30.mamba.A_log": "model.safetensors",
841
+ "model.layers.30.mamba.D": "model.safetensors",
842
+ "model.layers.30.mamba.conv1d.bias": "model.safetensors",
843
+ "model.layers.30.mamba.conv1d.weight": "model.safetensors",
844
+ "model.layers.30.mamba.dt_bias": "model.safetensors",
845
+ "model.layers.30.mamba.in_proj.biases": "model.safetensors",
846
+ "model.layers.30.mamba.in_proj.scales": "model.safetensors",
847
+ "model.layers.30.mamba.in_proj.weight": "model.safetensors",
848
+ "model.layers.30.mamba.out_proj.biases": "model.safetensors",
849
+ "model.layers.30.mamba.out_proj.scales": "model.safetensors",
850
+ "model.layers.30.mamba.out_proj.weight": "model.safetensors",
851
+ "model.layers.30.pre_ff_layernorm.weight": "model.safetensors",
852
+ "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
853
+ "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
854
+ "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
855
+ "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
856
+ "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
857
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
858
+ "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
859
+ "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
860
+ "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
861
+ "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
862
+ "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
863
+ "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
864
+ "model.layers.31.feed_forward.down_proj.biases": "model.safetensors",
865
+ "model.layers.31.feed_forward.down_proj.scales": "model.safetensors",
866
+ "model.layers.31.feed_forward.down_proj.weight": "model.safetensors",
867
+ "model.layers.31.feed_forward.gate_proj.biases": "model.safetensors",
868
+ "model.layers.31.feed_forward.gate_proj.scales": "model.safetensors",
869
+ "model.layers.31.feed_forward.gate_proj.weight": "model.safetensors",
870
+ "model.layers.31.feed_forward.up_proj.biases": "model.safetensors",
871
+ "model.layers.31.feed_forward.up_proj.scales": "model.safetensors",
872
+ "model.layers.31.feed_forward.up_proj.weight": "model.safetensors",
873
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
874
+ "model.layers.31.mamba.A_log": "model.safetensors",
875
+ "model.layers.31.mamba.D": "model.safetensors",
876
+ "model.layers.31.mamba.conv1d.bias": "model.safetensors",
877
+ "model.layers.31.mamba.conv1d.weight": "model.safetensors",
878
+ "model.layers.31.mamba.dt_bias": "model.safetensors",
879
+ "model.layers.31.mamba.in_proj.biases": "model.safetensors",
880
+ "model.layers.31.mamba.in_proj.scales": "model.safetensors",
881
+ "model.layers.31.mamba.in_proj.weight": "model.safetensors",
882
+ "model.layers.31.mamba.out_proj.biases": "model.safetensors",
883
+ "model.layers.31.mamba.out_proj.scales": "model.safetensors",
884
+ "model.layers.31.mamba.out_proj.weight": "model.safetensors",
885
+ "model.layers.31.pre_ff_layernorm.weight": "model.safetensors",
886
+ "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
887
+ "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
888
+ "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
889
+ "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
890
+ "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
891
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
892
+ "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
893
+ "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
894
+ "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
895
+ "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
896
+ "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
897
+ "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
898
+ "model.layers.32.feed_forward.down_proj.biases": "model.safetensors",
899
+ "model.layers.32.feed_forward.down_proj.scales": "model.safetensors",
900
+ "model.layers.32.feed_forward.down_proj.weight": "model.safetensors",
901
+ "model.layers.32.feed_forward.gate_proj.biases": "model.safetensors",
902
+ "model.layers.32.feed_forward.gate_proj.scales": "model.safetensors",
903
+ "model.layers.32.feed_forward.gate_proj.weight": "model.safetensors",
904
+ "model.layers.32.feed_forward.up_proj.biases": "model.safetensors",
905
+ "model.layers.32.feed_forward.up_proj.scales": "model.safetensors",
906
+ "model.layers.32.feed_forward.up_proj.weight": "model.safetensors",
907
+ "model.layers.32.input_layernorm.weight": "model.safetensors",
908
+ "model.layers.32.mamba.A_log": "model.safetensors",
909
+ "model.layers.32.mamba.D": "model.safetensors",
910
+ "model.layers.32.mamba.conv1d.bias": "model.safetensors",
911
+ "model.layers.32.mamba.conv1d.weight": "model.safetensors",
912
+ "model.layers.32.mamba.dt_bias": "model.safetensors",
913
+ "model.layers.32.mamba.in_proj.biases": "model.safetensors",
914
+ "model.layers.32.mamba.in_proj.scales": "model.safetensors",
915
+ "model.layers.32.mamba.in_proj.weight": "model.safetensors",
916
+ "model.layers.32.mamba.out_proj.biases": "model.safetensors",
917
+ "model.layers.32.mamba.out_proj.scales": "model.safetensors",
918
+ "model.layers.32.mamba.out_proj.weight": "model.safetensors",
919
+ "model.layers.32.pre_ff_layernorm.weight": "model.safetensors",
920
+ "model.layers.32.self_attn.k_proj.biases": "model.safetensors",
921
+ "model.layers.32.self_attn.k_proj.scales": "model.safetensors",
922
+ "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
923
+ "model.layers.32.self_attn.o_proj.biases": "model.safetensors",
924
+ "model.layers.32.self_attn.o_proj.scales": "model.safetensors",
925
+ "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
926
+ "model.layers.32.self_attn.q_proj.biases": "model.safetensors",
927
+ "model.layers.32.self_attn.q_proj.scales": "model.safetensors",
928
+ "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
929
+ "model.layers.32.self_attn.v_proj.biases": "model.safetensors",
930
+ "model.layers.32.self_attn.v_proj.scales": "model.safetensors",
931
+ "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
932
+ "model.layers.33.feed_forward.down_proj.biases": "model.safetensors",
933
+ "model.layers.33.feed_forward.down_proj.scales": "model.safetensors",
934
+ "model.layers.33.feed_forward.down_proj.weight": "model.safetensors",
935
+ "model.layers.33.feed_forward.gate_proj.biases": "model.safetensors",
936
+ "model.layers.33.feed_forward.gate_proj.scales": "model.safetensors",
937
+ "model.layers.33.feed_forward.gate_proj.weight": "model.safetensors",
938
+ "model.layers.33.feed_forward.up_proj.biases": "model.safetensors",
939
+ "model.layers.33.feed_forward.up_proj.scales": "model.safetensors",
940
+ "model.layers.33.feed_forward.up_proj.weight": "model.safetensors",
941
+ "model.layers.33.input_layernorm.weight": "model.safetensors",
942
+ "model.layers.33.mamba.A_log": "model.safetensors",
943
+ "model.layers.33.mamba.D": "model.safetensors",
944
+ "model.layers.33.mamba.conv1d.bias": "model.safetensors",
945
+ "model.layers.33.mamba.conv1d.weight": "model.safetensors",
946
+ "model.layers.33.mamba.dt_bias": "model.safetensors",
947
+ "model.layers.33.mamba.in_proj.biases": "model.safetensors",
948
+ "model.layers.33.mamba.in_proj.scales": "model.safetensors",
949
+ "model.layers.33.mamba.in_proj.weight": "model.safetensors",
950
+ "model.layers.33.mamba.out_proj.biases": "model.safetensors",
951
+ "model.layers.33.mamba.out_proj.scales": "model.safetensors",
952
+ "model.layers.33.mamba.out_proj.weight": "model.safetensors",
953
+ "model.layers.33.pre_ff_layernorm.weight": "model.safetensors",
954
+ "model.layers.33.self_attn.k_proj.biases": "model.safetensors",
955
+ "model.layers.33.self_attn.k_proj.scales": "model.safetensors",
956
+ "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
957
+ "model.layers.33.self_attn.o_proj.biases": "model.safetensors",
958
+ "model.layers.33.self_attn.o_proj.scales": "model.safetensors",
959
+ "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
960
+ "model.layers.33.self_attn.q_proj.biases": "model.safetensors",
961
+ "model.layers.33.self_attn.q_proj.scales": "model.safetensors",
962
+ "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
963
+ "model.layers.33.self_attn.v_proj.biases": "model.safetensors",
964
+ "model.layers.33.self_attn.v_proj.scales": "model.safetensors",
965
+ "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
966
+ "model.layers.34.feed_forward.down_proj.biases": "model.safetensors",
967
+ "model.layers.34.feed_forward.down_proj.scales": "model.safetensors",
968
+ "model.layers.34.feed_forward.down_proj.weight": "model.safetensors",
969
+ "model.layers.34.feed_forward.gate_proj.biases": "model.safetensors",
970
+ "model.layers.34.feed_forward.gate_proj.scales": "model.safetensors",
971
+ "model.layers.34.feed_forward.gate_proj.weight": "model.safetensors",
972
+ "model.layers.34.feed_forward.up_proj.biases": "model.safetensors",
973
+ "model.layers.34.feed_forward.up_proj.scales": "model.safetensors",
974
+ "model.layers.34.feed_forward.up_proj.weight": "model.safetensors",
975
+ "model.layers.34.input_layernorm.weight": "model.safetensors",
976
+ "model.layers.34.mamba.A_log": "model.safetensors",
977
+ "model.layers.34.mamba.D": "model.safetensors",
978
+ "model.layers.34.mamba.conv1d.bias": "model.safetensors",
979
+ "model.layers.34.mamba.conv1d.weight": "model.safetensors",
980
+ "model.layers.34.mamba.dt_bias": "model.safetensors",
981
+ "model.layers.34.mamba.in_proj.biases": "model.safetensors",
982
+ "model.layers.34.mamba.in_proj.scales": "model.safetensors",
983
+ "model.layers.34.mamba.in_proj.weight": "model.safetensors",
984
+ "model.layers.34.mamba.out_proj.biases": "model.safetensors",
985
+ "model.layers.34.mamba.out_proj.scales": "model.safetensors",
986
+ "model.layers.34.mamba.out_proj.weight": "model.safetensors",
987
+ "model.layers.34.pre_ff_layernorm.weight": "model.safetensors",
988
+ "model.layers.34.self_attn.k_proj.biases": "model.safetensors",
989
+ "model.layers.34.self_attn.k_proj.scales": "model.safetensors",
990
+ "model.layers.34.self_attn.k_proj.weight": "model.safetensors",
991
+ "model.layers.34.self_attn.o_proj.biases": "model.safetensors",
992
+ "model.layers.34.self_attn.o_proj.scales": "model.safetensors",
993
+ "model.layers.34.self_attn.o_proj.weight": "model.safetensors",
994
+ "model.layers.34.self_attn.q_proj.biases": "model.safetensors",
995
+ "model.layers.34.self_attn.q_proj.scales": "model.safetensors",
996
+ "model.layers.34.self_attn.q_proj.weight": "model.safetensors",
997
+ "model.layers.34.self_attn.v_proj.biases": "model.safetensors",
998
+ "model.layers.34.self_attn.v_proj.scales": "model.safetensors",
999
+ "model.layers.34.self_attn.v_proj.weight": "model.safetensors",
1000
+ "model.layers.35.feed_forward.down_proj.biases": "model.safetensors",
1001
+ "model.layers.35.feed_forward.down_proj.scales": "model.safetensors",
1002
+ "model.layers.35.feed_forward.down_proj.weight": "model.safetensors",
1003
+ "model.layers.35.feed_forward.gate_proj.biases": "model.safetensors",
1004
+ "model.layers.35.feed_forward.gate_proj.scales": "model.safetensors",
1005
+ "model.layers.35.feed_forward.gate_proj.weight": "model.safetensors",
1006
+ "model.layers.35.feed_forward.up_proj.biases": "model.safetensors",
1007
+ "model.layers.35.feed_forward.up_proj.scales": "model.safetensors",
1008
+ "model.layers.35.feed_forward.up_proj.weight": "model.safetensors",
1009
+ "model.layers.35.input_layernorm.weight": "model.safetensors",
1010
+ "model.layers.35.mamba.A_log": "model.safetensors",
1011
+ "model.layers.35.mamba.D": "model.safetensors",
1012
+ "model.layers.35.mamba.conv1d.bias": "model.safetensors",
1013
+ "model.layers.35.mamba.conv1d.weight": "model.safetensors",
1014
+ "model.layers.35.mamba.dt_bias": "model.safetensors",
1015
+ "model.layers.35.mamba.in_proj.biases": "model.safetensors",
1016
+ "model.layers.35.mamba.in_proj.scales": "model.safetensors",
1017
+ "model.layers.35.mamba.in_proj.weight": "model.safetensors",
1018
+ "model.layers.35.mamba.out_proj.biases": "model.safetensors",
1019
+ "model.layers.35.mamba.out_proj.scales": "model.safetensors",
1020
+ "model.layers.35.mamba.out_proj.weight": "model.safetensors",
1021
+ "model.layers.35.pre_ff_layernorm.weight": "model.safetensors",
1022
+ "model.layers.35.self_attn.k_proj.biases": "model.safetensors",
1023
+ "model.layers.35.self_attn.k_proj.scales": "model.safetensors",
1024
+ "model.layers.35.self_attn.k_proj.weight": "model.safetensors",
1025
+ "model.layers.35.self_attn.o_proj.biases": "model.safetensors",
1026
+ "model.layers.35.self_attn.o_proj.scales": "model.safetensors",
1027
+ "model.layers.35.self_attn.o_proj.weight": "model.safetensors",
1028
+ "model.layers.35.self_attn.q_proj.biases": "model.safetensors",
1029
+ "model.layers.35.self_attn.q_proj.scales": "model.safetensors",
1030
+ "model.layers.35.self_attn.q_proj.weight": "model.safetensors",
1031
+ "model.layers.35.self_attn.v_proj.biases": "model.safetensors",
1032
+ "model.layers.35.self_attn.v_proj.scales": "model.safetensors",
1033
+ "model.layers.35.self_attn.v_proj.weight": "model.safetensors",
1034
+ "model.layers.4.feed_forward.down_proj.biases": "model.safetensors",
1035
+ "model.layers.4.feed_forward.down_proj.scales": "model.safetensors",
1036
+ "model.layers.4.feed_forward.down_proj.weight": "model.safetensors",
1037
+ "model.layers.4.feed_forward.gate_proj.biases": "model.safetensors",
1038
+ "model.layers.4.feed_forward.gate_proj.scales": "model.safetensors",
1039
+ "model.layers.4.feed_forward.gate_proj.weight": "model.safetensors",
1040
+ "model.layers.4.feed_forward.up_proj.biases": "model.safetensors",
1041
+ "model.layers.4.feed_forward.up_proj.scales": "model.safetensors",
1042
+ "model.layers.4.feed_forward.up_proj.weight": "model.safetensors",
1043
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
1044
+ "model.layers.4.mamba.A_log": "model.safetensors",
1045
+ "model.layers.4.mamba.D": "model.safetensors",
1046
+ "model.layers.4.mamba.conv1d.bias": "model.safetensors",
1047
+ "model.layers.4.mamba.conv1d.weight": "model.safetensors",
1048
+ "model.layers.4.mamba.dt_bias": "model.safetensors",
1049
+ "model.layers.4.mamba.in_proj.biases": "model.safetensors",
1050
+ "model.layers.4.mamba.in_proj.scales": "model.safetensors",
1051
+ "model.layers.4.mamba.in_proj.weight": "model.safetensors",
1052
+ "model.layers.4.mamba.out_proj.biases": "model.safetensors",
1053
+ "model.layers.4.mamba.out_proj.scales": "model.safetensors",
1054
+ "model.layers.4.mamba.out_proj.weight": "model.safetensors",
1055
+ "model.layers.4.pre_ff_layernorm.weight": "model.safetensors",
1056
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
1057
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
1058
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
1059
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
1060
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
1061
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
1062
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
1063
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
1064
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
1065
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
1066
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
1067
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
1068
+ "model.layers.5.feed_forward.down_proj.biases": "model.safetensors",
1069
+ "model.layers.5.feed_forward.down_proj.scales": "model.safetensors",
1070
+ "model.layers.5.feed_forward.down_proj.weight": "model.safetensors",
1071
+ "model.layers.5.feed_forward.gate_proj.biases": "model.safetensors",
1072
+ "model.layers.5.feed_forward.gate_proj.scales": "model.safetensors",
1073
+ "model.layers.5.feed_forward.gate_proj.weight": "model.safetensors",
1074
+ "model.layers.5.feed_forward.up_proj.biases": "model.safetensors",
1075
+ "model.layers.5.feed_forward.up_proj.scales": "model.safetensors",
1076
+ "model.layers.5.feed_forward.up_proj.weight": "model.safetensors",
1077
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
1078
+ "model.layers.5.mamba.A_log": "model.safetensors",
1079
+ "model.layers.5.mamba.D": "model.safetensors",
1080
+ "model.layers.5.mamba.conv1d.bias": "model.safetensors",
1081
+ "model.layers.5.mamba.conv1d.weight": "model.safetensors",
1082
+ "model.layers.5.mamba.dt_bias": "model.safetensors",
1083
+ "model.layers.5.mamba.in_proj.biases": "model.safetensors",
1084
+ "model.layers.5.mamba.in_proj.scales": "model.safetensors",
1085
+ "model.layers.5.mamba.in_proj.weight": "model.safetensors",
1086
+ "model.layers.5.mamba.out_proj.biases": "model.safetensors",
1087
+ "model.layers.5.mamba.out_proj.scales": "model.safetensors",
1088
+ "model.layers.5.mamba.out_proj.weight": "model.safetensors",
1089
+ "model.layers.5.pre_ff_layernorm.weight": "model.safetensors",
1090
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
1091
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
1092
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
1093
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
1094
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
1095
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
1096
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
1097
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
1098
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
1099
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
1100
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
1101
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
1102
+ "model.layers.6.feed_forward.down_proj.biases": "model.safetensors",
1103
+ "model.layers.6.feed_forward.down_proj.scales": "model.safetensors",
1104
+ "model.layers.6.feed_forward.down_proj.weight": "model.safetensors",
1105
+ "model.layers.6.feed_forward.gate_proj.biases": "model.safetensors",
1106
+ "model.layers.6.feed_forward.gate_proj.scales": "model.safetensors",
1107
+ "model.layers.6.feed_forward.gate_proj.weight": "model.safetensors",
1108
+ "model.layers.6.feed_forward.up_proj.biases": "model.safetensors",
1109
+ "model.layers.6.feed_forward.up_proj.scales": "model.safetensors",
1110
+ "model.layers.6.feed_forward.up_proj.weight": "model.safetensors",
1111
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
1112
+ "model.layers.6.mamba.A_log": "model.safetensors",
1113
+ "model.layers.6.mamba.D": "model.safetensors",
1114
+ "model.layers.6.mamba.conv1d.bias": "model.safetensors",
1115
+ "model.layers.6.mamba.conv1d.weight": "model.safetensors",
1116
+ "model.layers.6.mamba.dt_bias": "model.safetensors",
1117
+ "model.layers.6.mamba.in_proj.biases": "model.safetensors",
1118
+ "model.layers.6.mamba.in_proj.scales": "model.safetensors",
1119
+ "model.layers.6.mamba.in_proj.weight": "model.safetensors",
1120
+ "model.layers.6.mamba.out_proj.biases": "model.safetensors",
1121
+ "model.layers.6.mamba.out_proj.scales": "model.safetensors",
1122
+ "model.layers.6.mamba.out_proj.weight": "model.safetensors",
1123
+ "model.layers.6.pre_ff_layernorm.weight": "model.safetensors",
1124
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
1125
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
1126
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
1127
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
1128
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
1129
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
1130
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
1131
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
1132
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
1133
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
1134
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
1135
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
1136
+ "model.layers.7.feed_forward.down_proj.biases": "model.safetensors",
1137
+ "model.layers.7.feed_forward.down_proj.scales": "model.safetensors",
1138
+ "model.layers.7.feed_forward.down_proj.weight": "model.safetensors",
1139
+ "model.layers.7.feed_forward.gate_proj.biases": "model.safetensors",
1140
+ "model.layers.7.feed_forward.gate_proj.scales": "model.safetensors",
1141
+ "model.layers.7.feed_forward.gate_proj.weight": "model.safetensors",
1142
+ "model.layers.7.feed_forward.up_proj.biases": "model.safetensors",
1143
+ "model.layers.7.feed_forward.up_proj.scales": "model.safetensors",
1144
+ "model.layers.7.feed_forward.up_proj.weight": "model.safetensors",
1145
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
1146
+ "model.layers.7.mamba.A_log": "model.safetensors",
1147
+ "model.layers.7.mamba.D": "model.safetensors",
1148
+ "model.layers.7.mamba.conv1d.bias": "model.safetensors",
1149
+ "model.layers.7.mamba.conv1d.weight": "model.safetensors",
1150
+ "model.layers.7.mamba.dt_bias": "model.safetensors",
1151
+ "model.layers.7.mamba.in_proj.biases": "model.safetensors",
1152
+ "model.layers.7.mamba.in_proj.scales": "model.safetensors",
1153
+ "model.layers.7.mamba.in_proj.weight": "model.safetensors",
1154
+ "model.layers.7.mamba.out_proj.biases": "model.safetensors",
1155
+ "model.layers.7.mamba.out_proj.scales": "model.safetensors",
1156
+ "model.layers.7.mamba.out_proj.weight": "model.safetensors",
1157
+ "model.layers.7.pre_ff_layernorm.weight": "model.safetensors",
1158
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
1159
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
1160
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
1161
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
1162
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
1163
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
1164
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
1165
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
1166
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
1167
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
1168
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
1169
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
1170
+ "model.layers.8.feed_forward.down_proj.biases": "model.safetensors",
1171
+ "model.layers.8.feed_forward.down_proj.scales": "model.safetensors",
1172
+ "model.layers.8.feed_forward.down_proj.weight": "model.safetensors",
1173
+ "model.layers.8.feed_forward.gate_proj.biases": "model.safetensors",
1174
+ "model.layers.8.feed_forward.gate_proj.scales": "model.safetensors",
1175
+ "model.layers.8.feed_forward.gate_proj.weight": "model.safetensors",
1176
+ "model.layers.8.feed_forward.up_proj.biases": "model.safetensors",
1177
+ "model.layers.8.feed_forward.up_proj.scales": "model.safetensors",
1178
+ "model.layers.8.feed_forward.up_proj.weight": "model.safetensors",
1179
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
1180
+ "model.layers.8.mamba.A_log": "model.safetensors",
1181
+ "model.layers.8.mamba.D": "model.safetensors",
1182
+ "model.layers.8.mamba.conv1d.bias": "model.safetensors",
1183
+ "model.layers.8.mamba.conv1d.weight": "model.safetensors",
1184
+ "model.layers.8.mamba.dt_bias": "model.safetensors",
1185
+ "model.layers.8.mamba.in_proj.biases": "model.safetensors",
1186
+ "model.layers.8.mamba.in_proj.scales": "model.safetensors",
1187
+ "model.layers.8.mamba.in_proj.weight": "model.safetensors",
1188
+ "model.layers.8.mamba.out_proj.biases": "model.safetensors",
1189
+ "model.layers.8.mamba.out_proj.scales": "model.safetensors",
1190
+ "model.layers.8.mamba.out_proj.weight": "model.safetensors",
1191
+ "model.layers.8.pre_ff_layernorm.weight": "model.safetensors",
1192
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
1193
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
1194
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
1195
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
1196
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
1197
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
1198
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
1199
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
1200
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
1201
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
1202
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
1203
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
1204
+ "model.layers.9.feed_forward.down_proj.biases": "model.safetensors",
1205
+ "model.layers.9.feed_forward.down_proj.scales": "model.safetensors",
1206
+ "model.layers.9.feed_forward.down_proj.weight": "model.safetensors",
1207
+ "model.layers.9.feed_forward.gate_proj.biases": "model.safetensors",
1208
+ "model.layers.9.feed_forward.gate_proj.scales": "model.safetensors",
1209
+ "model.layers.9.feed_forward.gate_proj.weight": "model.safetensors",
1210
+ "model.layers.9.feed_forward.up_proj.biases": "model.safetensors",
1211
+ "model.layers.9.feed_forward.up_proj.scales": "model.safetensors",
1212
+ "model.layers.9.feed_forward.up_proj.weight": "model.safetensors",
1213
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
1214
+ "model.layers.9.mamba.A_log": "model.safetensors",
1215
+ "model.layers.9.mamba.D": "model.safetensors",
1216
+ "model.layers.9.mamba.conv1d.bias": "model.safetensors",
1217
+ "model.layers.9.mamba.conv1d.weight": "model.safetensors",
1218
+ "model.layers.9.mamba.dt_bias": "model.safetensors",
1219
+ "model.layers.9.mamba.in_proj.biases": "model.safetensors",
1220
+ "model.layers.9.mamba.in_proj.scales": "model.safetensors",
1221
+ "model.layers.9.mamba.in_proj.weight": "model.safetensors",
1222
+ "model.layers.9.mamba.out_proj.biases": "model.safetensors",
1223
+ "model.layers.9.mamba.out_proj.scales": "model.safetensors",
1224
+ "model.layers.9.mamba.out_proj.weight": "model.safetensors",
1225
+ "model.layers.9.pre_ff_layernorm.weight": "model.safetensors",
1226
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
1227
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
1228
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
1229
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
1230
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
1231
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
1232
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
1233
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
1234
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
1235
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
1236
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
1237
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors"
1238
+ }
1239
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,356 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|pad|>",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<",
14
+ "<|finetune_right_pad_id|>",
15
+ "<|start_header_id|>",
16
+ "<|end_header_id|>",
17
+ "<|eom_id|>",
18
+ "<|eot_id|>",
19
+ "<|begin_of_text|>",
20
+ ">>TITLE<<",
21
+ "<tool_response>",
22
+ "</tool_response>",
23
+ "<tool_call>",
24
+ "</tool_call>",
25
+ "<schema>",
26
+ "</schema>",
27
+ "<scratch_pad>",
28
+ "</scratch_pad>",
29
+ "<thinking>",
30
+ "</thinking>",
31
+ "<explanation>",
32
+ "</explanation>",
33
+ "<file_sep>",
34
+ "<repo_name>",
35
+ "<|im_end|>",
36
+ "<|im_start|>",
37
+ ">>UNUSED_119<<",
38
+ ">>UNUSED_120<<",
39
+ "<|system|>",
40
+ ">>UNUSED_218<<",
41
+ ">>UNUSED_219<<",
42
+ ">>UNUSED_220<<",
43
+ ">>UNUSED_221<<",
44
+ ">>UNUSED_222<<",
45
+ ">>UNUSED_223<<",
46
+ ">>UNUSED_224<<",
47
+ ">>UNUSED_225<<",
48
+ ">>UNUSED_226<<",
49
+ ">>UNUSED_227<<",
50
+ ">>UNUSED_228<<",
51
+ ">>UNUSED_229<<",
52
+ ">>UNUSED_230<<",
53
+ ">>UNUSED_231<<",
54
+ ">>UNUSED_232<<",
55
+ ">>UNUSED_233<<",
56
+ ">>UNUSED_234<<",
57
+ ">>UNUSED_235<<",
58
+ ">>UNUSED_236<<",
59
+ ">>UNUSED_237<<",
60
+ ">>UNUSED_238<<",
61
+ ">>UNUSED_239<<",
62
+ ">>UNUSED_240<<",
63
+ ">>UNUSED_241<<",
64
+ ">>UNUSED_242<<",
65
+ ">>UNUSED_243<<",
66
+ ">>UNUSED_244<<",
67
+ ">>UNUSED_245<<",
68
+ ">>UNUSED_246<<",
69
+ ">>UNUSED_247<<",
70
+ ">>UNUSED_248<<",
71
+ ">>UNUSED_249<<",
72
+ ">>UNUSED_250<<",
73
+ ">>UNUSED_251<<",
74
+ ">>UNUSED_252<<",
75
+ ">>UNUSED_253<<",
76
+ ">>UNUSED_254<<",
77
+ ">>UNUSED_255<<",
78
+ ">>UNUSED_256<<",
79
+ ">>UNUSED_257<<",
80
+ ">>UNUSED_258<<",
81
+ ">>UNUSED_259<<",
82
+ ">>UNUSED_260<<",
83
+ ">>UNUSED_261<<",
84
+ ">>UNUSED_262<<",
85
+ ">>UNUSED_263<<",
86
+ ">>UNUSED_264<<",
87
+ ">>UNUSED_265<<",
88
+ ">>UNUSED_266<<",
89
+ ">>UNUSED_267<<",
90
+ ">>UNUSED_268<<",
91
+ ">>UNUSED_269<<",
92
+ ">>UNUSED_270<<",
93
+ ">>UNUSED_271<<",
94
+ ">>UNUSED_272<<",
95
+ ">>UNUSED_273<<",
96
+ ">>UNUSED_274<<",
97
+ ">>UNUSED_275<<",
98
+ ">>UNUSED_276<<",
99
+ ">>UNUSED_277<<",
100
+ ">>UNUSED_278<<",
101
+ ">>UNUSED_279<<",
102
+ ">>UNUSED_280<<",
103
+ ">>UNUSED_281<<",
104
+ ">>UNUSED_282<<",
105
+ ">>UNUSED_283<<",
106
+ ">>UNUSED_284<<",
107
+ ">>UNUSED_285<<",
108
+ ">>UNUSED_286<<",
109
+ ">>UNUSED_287<<",
110
+ ">>UNUSED_288<<",
111
+ ">>UNUSED_289<<",
112
+ ">>UNUSED_290<<",
113
+ ">>UNUSED_291<<",
114
+ ">>UNUSED_292<<",
115
+ ">>UNUSED_293<<",
116
+ ">>UNUSED_294<<",
117
+ ">>UNUSED_295<<",
118
+ ">>UNUSED_296<<",
119
+ ">>UNUSED_297<<",
120
+ ">>UNUSED_298<<",
121
+ ">>UNUSED_299<<",
122
+ ">>UNUSED_300<<",
123
+ ">>UNUSED_301<<",
124
+ ">>UNUSED_302<<",
125
+ ">>UNUSED_303<<",
126
+ ">>UNUSED_304<<",
127
+ ">>UNUSED_305<<",
128
+ ">>UNUSED_306<<",
129
+ ">>UNUSED_307<<",
130
+ ">>UNUSED_308<<",
131
+ ">>UNUSED_309<<",
132
+ ">>UNUSED_310<<",
133
+ ">>UNUSED_311<<",
134
+ ">>UNUSED_312<<",
135
+ ">>UNUSED_313<<",
136
+ ">>UNUSED_314<<",
137
+ ">>UNUSED_315<<",
138
+ ">>UNUSED_316<<",
139
+ ">>UNUSED_317<<",
140
+ ">>UNUSED_318<<",
141
+ ">>UNUSED_319<<",
142
+ ">>UNUSED_320<<",
143
+ ">>UNUSED_321<<",
144
+ ">>UNUSED_322<<",
145
+ ">>UNUSED_323<<",
146
+ ">>UNUSED_324<<",
147
+ ">>UNUSED_325<<",
148
+ ">>UNUSED_326<<",
149
+ ">>UNUSED_327<<",
150
+ ">>UNUSED_328<<",
151
+ ">>UNUSED_329<<",
152
+ ">>UNUSED_330<<",
153
+ ">>UNUSED_331<<",
154
+ ">>UNUSED_332<<",
155
+ ">>UNUSED_333<<",
156
+ ">>UNUSED_334<<",
157
+ ">>UNUSED_335<<",
158
+ ">>UNUSED_336<<",
159
+ ">>UNUSED_337<<",
160
+ ">>UNUSED_338<<",
161
+ ">>UNUSED_339<<",
162
+ ">>UNUSED_340<<",
163
+ ">>UNUSED_341<<",
164
+ ">>UNUSED_342<<",
165
+ ">>UNUSED_343<<",
166
+ ">>UNUSED_344<<",
167
+ ">>UNUSED_345<<",
168
+ ">>UNUSED_346<<",
169
+ ">>UNUSED_347<<",
170
+ ">>UNUSED_348<<",
171
+ ">>UNUSED_349<<",
172
+ ">>UNUSED_350<<",
173
+ ">>UNUSED_351<<",
174
+ ">>UNUSED_352<<",
175
+ ">>UNUSED_353<<",
176
+ ">>UNUSED_354<<",
177
+ ">>UNUSED_355<<",
178
+ ">>UNUSED_356<<",
179
+ ">>UNUSED_357<<",
180
+ ">>UNUSED_358<<",
181
+ ">>UNUSED_359<<",
182
+ ">>UNUSED_360<<",
183
+ ">>UNUSED_361<<",
184
+ ">>UNUSED_362<<",
185
+ ">>UNUSED_363<<",
186
+ ">>UNUSED_364<<",
187
+ ">>UNUSED_365<<",
188
+ ">>UNUSED_366<<",
189
+ ">>UNUSED_367<<",
190
+ ">>UNUSED_368<<",
191
+ ">>UNUSED_369<<",
192
+ ">>UNUSED_370<<",
193
+ ">>UNUSED_371<<",
194
+ ">>UNUSED_372<<",
195
+ ">>UNUSED_373<<",
196
+ ">>UNUSED_374<<",
197
+ ">>UNUSED_375<<",
198
+ ">>UNUSED_376<<",
199
+ ">>UNUSED_377<<",
200
+ ">>UNUSED_378<<",
201
+ ">>UNUSED_379<<",
202
+ ">>UNUSED_380<<",
203
+ ">>UNUSED_381<<",
204
+ ">>UNUSED_382<<",
205
+ ">>UNUSED_383<<",
206
+ ">>UNUSED_384<<",
207
+ ">>UNUSED_385<<",
208
+ ">>UNUSED_386<<",
209
+ ">>UNUSED_387<<",
210
+ ">>UNUSED_388<<",
211
+ ">>UNUSED_389<<",
212
+ ">>UNUSED_390<<",
213
+ ">>UNUSED_391<<",
214
+ ">>UNUSED_392<<",
215
+ ">>UNUSED_393<<",
216
+ ">>UNUSED_394<<",
217
+ ">>UNUSED_395<<",
218
+ ">>UNUSED_396<<",
219
+ ">>UNUSED_397<<",
220
+ ">>UNUSED_398<<",
221
+ ">>UNUSED_399<<",
222
+ ">>UNUSED_400<<",
223
+ ">>UNUSED_401<<",
224
+ ">>UNUSED_402<<",
225
+ ">>UNUSED_403<<",
226
+ ">>UNUSED_404<<",
227
+ ">>UNUSED_405<<",
228
+ ">>UNUSED_406<<",
229
+ ">>UNUSED_407<<",
230
+ ">>UNUSED_408<<",
231
+ ">>UNUSED_409<<",
232
+ ">>UNUSED_410<<",
233
+ ">>UNUSED_411<<",
234
+ ">>UNUSED_412<<",
235
+ ">>UNUSED_413<<",
236
+ ">>UNUSED_414<<",
237
+ ">>UNUSED_415<<",
238
+ ">>UNUSED_416<<",
239
+ ">>UNUSED_417<<",
240
+ ">>UNUSED_418<<",
241
+ ">>UNUSED_419<<",
242
+ ">>UNUSED_420<<",
243
+ ">>UNUSED_421<<",
244
+ ">>UNUSED_422<<",
245
+ ">>UNUSED_423<<",
246
+ ">>UNUSED_424<<",
247
+ ">>UNUSED_425<<",
248
+ ">>UNUSED_426<<",
249
+ ">>UNUSED_427<<",
250
+ ">>UNUSED_428<<",
251
+ ">>UNUSED_429<<",
252
+ ">>UNUSED_430<<",
253
+ ">>UNUSED_431<<",
254
+ ">>UNUSED_432<<",
255
+ ">>UNUSED_433<<",
256
+ ">>UNUSED_434<<",
257
+ ">>UNUSED_435<<",
258
+ ">>UNUSED_436<<",
259
+ ">>UNUSED_437<<",
260
+ ">>UNUSED_438<<",
261
+ ">>UNUSED_439<<",
262
+ ">>UNUSED_440<<",
263
+ ">>UNUSED_441<<",
264
+ ">>UNUSED_442<<",
265
+ ">>UNUSED_443<<",
266
+ ">>UNUSED_444<<",
267
+ ">>UNUSED_445<<",
268
+ ">>UNUSED_446<<",
269
+ ">>UNUSED_447<<",
270
+ ">>UNUSED_448<<",
271
+ ">>UNUSED_449<<",
272
+ ">>UNUSED_450<<",
273
+ ">>UNUSED_451<<",
274
+ ">>UNUSED_452<<",
275
+ ">>UNUSED_453<<",
276
+ ">>UNUSED_454<<",
277
+ ">>UNUSED_455<<",
278
+ ">>UNUSED_456<<",
279
+ ">>UNUSED_457<<",
280
+ ">>UNUSED_458<<",
281
+ ">>UNUSED_459<<",
282
+ ">>UNUSED_460<<",
283
+ ">>UNUSED_461<<",
284
+ ">>UNUSED_462<<",
285
+ ">>UNUSED_463<<",
286
+ ">>UNUSED_464<<",
287
+ ">>UNUSED_465<<",
288
+ ">>UNUSED_466<<",
289
+ ">>UNUSED_467<<",
290
+ ">>UNUSED_468<<",
291
+ ">>UNUSED_469<<",
292
+ ">>UNUSED_470<<",
293
+ ">>UNUSED_471<<",
294
+ ">>UNUSED_472<<",
295
+ ">>UNUSED_473<<",
296
+ ">>UNUSED_474<<",
297
+ ">>UNUSED_475<<",
298
+ ">>UNUSED_476<<",
299
+ ">>UNUSED_477<<",
300
+ ">>UNUSED_478<<",
301
+ ">>UNUSED_479<<",
302
+ ">>UNUSED_480<<",
303
+ ">>UNUSED_481<<",
304
+ ">>UNUSED_482<<",
305
+ ">>UNUSED_483<<",
306
+ ">>UNUSED_484<<",
307
+ ">>UNUSED_485<<",
308
+ ">>UNUSED_486<<",
309
+ ">>UNUSED_487<<",
310
+ ">>UNUSED_488<<",
311
+ ">>UNUSED_489<<",
312
+ ">>UNUSED_490<<",
313
+ ">>UNUSED_491<<",
314
+ ">>UNUSED_492<<",
315
+ ">>UNUSED_493<<",
316
+ ">>UNUSED_494<<",
317
+ ">>UNUSED_495<<",
318
+ ">>UNUSED_496<<",
319
+ ">>UNUSED_497<<",
320
+ ">>UNUSED_498<<",
321
+ ">>UNUSED_499<<",
322
+ ">>UNUSED_500<<",
323
+ ">>UNUSED_501<<",
324
+ ">>UNUSED_502<<",
325
+ ">>UNUSED_503<<",
326
+ ">>UNUSED_504<<",
327
+ ">>UNUSED_505<<",
328
+ ">>UNUSED_506<<",
329
+ ">>UNUSED_507<<",
330
+ ">>UNUSED_508<<",
331
+ ">>UNUSED_509<<",
332
+ ">>UNUSED_510<<",
333
+ ">>UNUSED_511<<"
334
+ ],
335
+ "bos_token": {
336
+ "content": "<|begin_of_text|>",
337
+ "lstrip": false,
338
+ "normalized": false,
339
+ "rstrip": false,
340
+ "single_word": false
341
+ },
342
+ "eos_token": {
343
+ "content": "<|end_of_text|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false
348
+ },
349
+ "pad_token": {
350
+ "content": "<pad>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false
355
+ }
356
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff