Hugging Face's logo

justindal
/
llama3.1-8b-instruct-mlx-leetcoder

Text Generation
MLX
Safetensors
PyTorch
llama
facebook
meta
llama-3
conversational
Model card Files
xet
 Community
justindal commited on
Commit
9d58f00
·
verified ·
1 Parent(s): 84e3e65

Cleanup: removing original model files

Browse files
Files changed (8) hide show
  1. chat_template.jinja +0 -109
  2. config.json +0 -48
  3. generation_config.json +0 -12
  4. model-00001-of-00002.safetensors +0 -3
  5. model-00002-of-00002.safetensors +0 -3
  6. model.safetensors.index.json +0 -751
  7. tokenizer.json +0 -3
  8. tokenizer_config.json +0 -13
chat_template.jinja DELETED
@@ -1,109 +0,0 @@
1
- {{- bos_token }}
2
- {%- if custom_tools is defined %}
3
- {%- set tools = custom_tools %}
4
- {%- endif %}
5
- {%- if not tools_in_user_message is defined %}
6
- {%- set tools_in_user_message = true %}
7
- {%- endif %}
8
- {%- if not date_string is defined %}
9
- {%- set date_string = "26 Jul 2024" %}
10
- {%- endif %}
11
- {%- if not tools is defined %}
12
- {%- set tools = none %}
13
- {%- endif %}
14
-
15
- {#- This block extracts the system message, so we can slot it into the right place. #}
16
- {%- if messages[0]['role'] == 'system' %}
17
- {%- set system_message = messages[0]['content']|trim %}
18
- {%- set messages = messages[1:] %}
19
- {%- else %}
20
- {%- set system_message = "" %}
21
- {%- endif %}
22
-
23
- {#- System message + builtin tools #}
24
- {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
- {%- if builtin_tools is defined or tools is not none %}
26
- {{- "Environment: ipython\n" }}
27
- {%- endif %}
28
- {%- if builtin_tools is defined %}
29
- {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
- {%- endif %}
31
- {{- "Cutting Knowledge Date: December 2023\n" }}
32
- {{- "Today Date: " + date_string + "\n\n" }}
33
- {%- if tools is not none and not tools_in_user_message %}
34
- {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
- {{- "Do not use variables.\n\n" }}
37
- {%- for t in tools %}
38
- {{- t | tojson(indent=4) }}
39
- {{- "\n\n" }}
40
- {%- endfor %}
41
- {%- endif %}
42
- {{- system_message }}
43
- {{- "<|eot_id|>" }}
44
-
45
- {#- Custom tools are passed in a user message with some extra guidance #}
46
- {%- if tools_in_user_message and not tools is none %}
47
- {#- Extract the first user message so we can plug it in here #}
48
- {%- if messages | length != 0 %}
49
- {%- set first_user_message = messages[0]['content']|trim %}
50
- {%- set messages = messages[1:] %}
51
- {%- else %}
52
- {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
- {%- endif %}
54
- {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
- {{- "Given the following functions, please respond with a JSON for a function call " }}
56
- {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
- {{- "Do not use variables.\n\n" }}
59
- {%- for t in tools %}
60
- {{- t | tojson(indent=4) }}
61
- {{- "\n\n" }}
62
- {%- endfor %}
63
- {{- first_user_message + "<|eot_id|>"}}
64
- {%- endif %}
65
-
66
- {%- for message in messages %}
67
- {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
- {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
- {%- elif 'tool_calls' in message %}
70
- {%- if not message.tool_calls|length == 1 %}
71
- {{- raise_exception("This model only supports single tool-calls at once!") }}
72
- {%- endif %}
73
- {%- set tool_call = message.tool_calls[0].function %}
74
- {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
- {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
- {%- for arg_name, arg_val in tool_call.arguments | items %}
78
- {{- arg_name + '="' + arg_val + '"' }}
79
- {%- if not loop.last %}
80
- {{- ", " }}
81
- {%- endif %}
82
- {%- endfor %}
83
- {{- ")" }}
84
- {%- else %}
85
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
- {{- '{"name": "' + tool_call.name + '", ' }}
87
- {{- '"parameters": ' }}
88
- {{- tool_call.arguments | tojson }}
89
- {{- "}" }}
90
- {%- endif %}
91
- {%- if builtin_tools is defined %}
92
- {#- This means we're in ipython mode #}
93
- {{- "<|eom_id|>" }}
94
- {%- else %}
95
- {{- "<|eot_id|>" }}
96
- {%- endif %}
97
- {%- elif message.role == "tool" or message.role == "ipython" %}
98
- {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
- {%- if message.content is mapping or message.content is iterable %}
100
- {{- message.content | tojson }}
101
- {%- else %}
102
- {{- message.content }}
103
- {%- endif %}
104
- {{- "<|eot_id|>" }}
105
- {%- endif %}
106
- {%- endfor %}
107
- {%- if add_generation_prompt %}
108
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,48 +0,0 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
- "eos_token_id": [
9
- 128001,
10
- 128008,
11
- 128009
12
- ],
13
- "hidden_act": "silu",
14
- "hidden_size": 4096,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 14336,
17
- "max_position_embeddings": 131072,
18
- "mlp_bias": false,
19
- "model_type": "llama",
20
- "num_attention_heads": 32,
21
- "num_hidden_layers": 32,
22
- "num_key_value_heads": 8,
23
- "pretraining_tp": 1,
24
- "quantization": {
25
- "group_size": 32,
26
- "bits": 8,
27
- "mode": "affine"
28
- },
29
- "quantization_config": {
30
- "group_size": 32,
31
- "bits": 8,
32
- "mode": "affine"
33
- },
34
- "rms_norm_eps": 1e-05,
35
- "rope_scaling": {
36
- "factor": 8.0,
37
- "low_freq_factor": 1.0,
38
- "high_freq_factor": 4.0,
39
- "original_max_position_embeddings": 8192,
40
- "rope_type": "llama3"
41
- },
42
- "rope_theta": 500000.0,
43
- "tie_word_embeddings": false,
44
- "torch_dtype": "bfloat16",
45
- "transformers_version": "4.42.3",
46
- "use_cache": true,
47
- "vocab_size": 128256
48
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
- "temperature": 0.6,
10
- "top_p": 0.9,
11
- "transformers_version": "4.42.3"
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:96b0b212a9eea51fbfdcb1eb2d33ef2a6abe7f281368ce834d8277dc7315efa1
3
- size 5366582299
 
 
 
 
model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0c8fa96f492977787d8d779b055feb40bbed79f995536a17bdf5b548adf097d
3
- size 3667779901
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,751 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 9034276864,
4
- "total_parameters": 8030261248
5
- },
6
- "weight_map": {
7
- "lm_head.biases": "model-00002-of-00002.safetensors",
8
- "lm_head.scales": "model-00002-of-00002.safetensors",
9
- "lm_head.weight": "model-00002-of-00002.safetensors",
10
- "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
11
- "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
12
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
15
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
16
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
18
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
19
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
21
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
22
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
25
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
26
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
28
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
29
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
31
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
32
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
34
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
35
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
38
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
39
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
41
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
42
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
44
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
45
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
48
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
49
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
51
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
52
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
54
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
55
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
57
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
58
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
61
- "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
62
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
64
- "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
65
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
- "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
67
- "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
68
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
71
- "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
72
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
74
- "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
75
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
77
- "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
78
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
80
- "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
81
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
83
- "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
84
- "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
85
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
87
- "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
88
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
90
- "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
91
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
94
- "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
95
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
97
- "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
98
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
- "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
100
- "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
101
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
103
- "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
104
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
106
- "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
107
- "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
108
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
110
- "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
111
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
113
- "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
114
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
116
- "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
117
- "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
118
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
- "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
120
- "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
121
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
- "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
123
- "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
124
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
126
- "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
127
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
- "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
130
- "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
131
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
133
- "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
134
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
135
- "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
136
- "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
137
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
- "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
140
- "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
141
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
142
- "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
143
- "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
144
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
145
- "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
146
- "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
147
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
149
- "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
150
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
- "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
153
- "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
154
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
- "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
156
- "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
157
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
158
- "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
159
- "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
160
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
161
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
162
- "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
163
- "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
164
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
165
- "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
166
- "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
167
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
- "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
169
- "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
170
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
171
- "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
172
- "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
173
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
174
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
175
- "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
176
- "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
177
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
- "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
179
- "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
180
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
181
- "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
182
- "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
183
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
184
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
- "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
186
- "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
187
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
188
- "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
189
- "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
190
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
191
- "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
192
- "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
193
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
194
- "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
195
- "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
196
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
197
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
- "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
199
- "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
200
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
201
- "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
202
- "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
203
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
204
- "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
205
- "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
206
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
208
- "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
209
- "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
210
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
- "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
212
- "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
213
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
214
- "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
215
- "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
216
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
218
- "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
219
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
220
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
222
- "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
223
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
224
- "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
225
- "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
226
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
- "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
228
- "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
229
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
231
- "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
232
- "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
233
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
234
- "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
235
- "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
236
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
237
- "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
238
- "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
239
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
240
- "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
241
- "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
242
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
245
- "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
246
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
248
- "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
249
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
251
- "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
252
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
254
- "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
255
- "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
256
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
258
- "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
259
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
260
- "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
261
- "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
262
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
263
- "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
264
- "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
265
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
266
- "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
267
- "model.layers.19.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
268
- "model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
269
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
270
- "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
271
- "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
272
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
273
- "model.layers.19.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
274
- "model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
275
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
- "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
278
- "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
279
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
- "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
281
- "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
282
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
283
- "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
284
- "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
285
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
- "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
287
- "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
288
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
289
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
290
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
291
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
292
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
293
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
294
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
295
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
296
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
297
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
298
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
299
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
300
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
301
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
302
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
303
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
304
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
305
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
306
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
307
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
308
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
309
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
310
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
311
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
312
- "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
313
- "model.layers.20.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
314
- "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
315
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
316
- "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
317
- "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
318
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
- "model.layers.20.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
320
- "model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
321
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
322
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
323
- "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
324
- "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
325
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
326
- "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
327
- "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
328
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
329
- "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
330
- "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
331
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
332
- "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
333
- "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
334
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
335
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
336
- "model.layers.21.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
337
- "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
338
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
339
- "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
340
- "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
341
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
342
- "model.layers.21.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
343
- "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
344
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
345
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
346
- "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
347
- "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
348
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
349
- "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
350
- "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
351
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
352
- "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
353
- "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
354
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
355
- "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
356
- "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
357
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
358
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
359
- "model.layers.22.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
360
- "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
361
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
362
- "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
363
- "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
364
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
365
- "model.layers.22.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
366
- "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
367
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
368
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
369
- "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
370
- "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
371
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
372
- "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
373
- "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
374
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
375
- "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
376
- "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
377
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
378
- "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
379
- "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
380
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
381
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
382
- "model.layers.23.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
383
- "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
384
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
385
- "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
386
- "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
387
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
388
- "model.layers.23.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
389
- "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
390
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
391
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
392
- "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
393
- "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
394
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
395
- "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
396
- "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
397
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
398
- "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
399
- "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
400
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
401
- "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
402
- "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
403
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
404
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
405
- "model.layers.24.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
406
- "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
407
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
408
- "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
409
- "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
410
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
411
- "model.layers.24.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
412
- "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
413
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
414
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
415
- "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
416
- "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
417
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
418
- "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
419
- "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
420
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
421
- "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
422
- "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
423
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
424
- "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
425
- "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
426
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
427
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
428
- "model.layers.25.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
429
- "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
430
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
431
- "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
432
- "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
433
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
434
- "model.layers.25.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
435
- "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
436
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
437
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
438
- "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
439
- "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
440
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
441
- "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
442
- "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
443
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
444
- "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
445
- "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
446
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
447
- "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
448
- "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
449
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
450
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
451
- "model.layers.26.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
452
- "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
453
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
454
- "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
455
- "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
456
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
457
- "model.layers.26.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
458
- "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
459
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
460
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
461
- "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
462
- "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
463
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
464
- "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
465
- "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
466
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
467
- "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
468
- "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
469
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
470
- "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
471
- "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
472
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
473
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
474
- "model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
475
- "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
476
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
477
- "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
478
- "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
479
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
480
- "model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
481
- "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
482
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
483
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
484
- "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
485
- "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
486
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
487
- "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
488
- "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
489
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
490
- "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
491
- "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
492
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
493
- "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
494
- "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
495
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
496
- "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
497
- "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
498
- "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
499
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
500
- "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
501
- "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
502
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
503
- "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
504
- "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
505
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
506
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
507
- "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
508
- "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
509
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
510
- "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
511
- "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
512
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
513
- "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
514
- "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
515
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
516
- "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
517
- "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
518
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
519
- "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
520
- "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
521
- "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
522
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
523
- "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
524
- "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
525
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
526
- "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
527
- "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
528
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
529
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
530
- "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
531
- "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
532
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
533
- "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
534
- "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
535
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
536
- "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
537
- "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
538
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
539
- "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
540
- "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
541
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
542
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
543
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
544
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
545
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
546
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
547
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
548
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
549
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
550
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
551
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
552
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
553
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
554
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
555
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
556
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
557
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
558
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
559
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
560
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
561
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
562
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
563
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
564
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
565
- "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
566
- "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
567
- "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
568
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
569
- "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
570
- "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
571
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
572
- "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
573
- "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
574
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
575
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
576
- "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
577
- "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
578
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
579
- "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
580
- "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
581
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
582
- "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
583
- "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
584
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
585
- "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
586
- "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
587
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
588
- "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
589
- "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
590
- "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
591
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
592
- "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
593
- "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
594
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
595
- "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
596
- "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
597
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
598
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
599
- "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
600
- "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
601
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
602
- "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
603
- "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
604
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
605
- "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
606
- "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
607
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
608
- "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
609
- "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
610
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
611
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
612
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
613
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
614
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
615
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
616
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
617
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
618
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
619
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
620
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
621
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
622
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
623
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
624
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
625
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
626
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
627
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
628
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
629
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
630
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
631
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
632
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
633
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
634
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
635
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
636
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
637
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
638
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
639
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
640
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
641
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
642
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
643
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
644
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
645
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
646
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
647
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
648
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
649
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
650
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
651
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
652
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
653
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
654
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
655
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
656
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
657
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
658
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
659
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
660
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
661
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
662
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
663
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
664
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
665
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
666
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
667
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
668
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
669
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
670
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
671
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
672
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
673
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
674
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
675
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
676
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
677
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
678
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
679
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
680
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
681
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
682
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
683
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
684
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
685
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
686
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
687
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
688
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
689
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
690
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
691
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
692
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
693
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
694
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
695
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
696
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
697
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
698
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
699
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
700
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
701
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
702
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
703
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
704
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
705
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
706
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
707
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
708
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
709
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
710
- "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
711
- "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
712
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
713
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
714
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
715
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
716
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
717
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
718
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
719
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
720
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
721
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
722
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
723
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
724
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
725
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
726
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
727
- "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
728
- "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
729
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
730
- "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
731
- "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
732
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
733
- "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
734
- "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
735
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
736
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
737
- "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
738
- "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
739
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
740
- "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
741
- "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
742
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
743
- "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
744
- "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
745
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
746
- "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
747
- "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
748
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
749
- "model.norm.weight": "model-00002-of-00002.safetensors"
750
- }
751
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
 
 
 
tokenizer_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "bos_token": "<|begin_of_text|>",
4
- "clean_up_tokenization_spaces": true,
5
- "eos_token": "<|eot_id|>",
6
- "is_local": true,
7
- "model_input_names": [
8
- "input_ids",
9
- "attention_mask"
10
- ],
11
- "model_max_length": 131072,
12
- "tokenizer_class": "TokenizersBackend"
13
- }