Upload folder using huggingface_hub

#1
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: tiiuae/Falcon3-10B-Instruct
3
+ library_name: transformers
4
+ license: other
5
+ license_name: falcon-llm-license
6
+ license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
7
+ tags:
8
+ - falcon3
9
+ - mlx
10
+ model-index:
11
+ - name: Falcon3-10B-Instruct
12
+ results:
13
+ - task:
14
+ type: text-generation
15
+ name: Text Generation
16
+ dataset:
17
+ name: IFEval (0-Shot)
18
+ type: HuggingFaceH4/ifeval
19
+ args:
20
+ num_few_shot: 0
21
+ metrics:
22
+ - type: inst_level_strict_acc and prompt_level_strict_acc
23
+ value: 78.17
24
+ name: strict accuracy
25
+ source:
26
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct
27
+ name: Open LLM Leaderboard
28
+ - task:
29
+ type: text-generation
30
+ name: Text Generation
31
+ dataset:
32
+ name: BBH (3-Shot)
33
+ type: BBH
34
+ args:
35
+ num_few_shot: 3
36
+ metrics:
37
+ - type: acc_norm
38
+ value: 44.82
39
+ name: normalized accuracy
40
+ source:
41
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct
42
+ name: Open LLM Leaderboard
43
+ - task:
44
+ type: text-generation
45
+ name: Text Generation
46
+ dataset:
47
+ name: MATH Lvl 5 (4-Shot)
48
+ type: hendrycks/competition_math
49
+ args:
50
+ num_few_shot: 4
51
+ metrics:
52
+ - type: exact_match
53
+ value: 25.91
54
+ name: exact match
55
+ source:
56
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct
57
+ name: Open LLM Leaderboard
58
+ - task:
59
+ type: text-generation
60
+ name: Text Generation
61
+ dataset:
62
+ name: GPQA (0-shot)
63
+ type: Idavidrein/gpqa
64
+ args:
65
+ num_few_shot: 0
66
+ metrics:
67
+ - type: acc_norm
68
+ value: 10.51
69
+ name: acc_norm
70
+ source:
71
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct
72
+ name: Open LLM Leaderboard
73
+ - task:
74
+ type: text-generation
75
+ name: Text Generation
76
+ dataset:
77
+ name: MuSR (0-shot)
78
+ type: TAUR-Lab/MuSR
79
+ args:
80
+ num_few_shot: 0
81
+ metrics:
82
+ - type: acc_norm
83
+ value: 13.61
84
+ name: acc_norm
85
+ source:
86
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct
87
+ name: Open LLM Leaderboard
88
+ - task:
89
+ type: text-generation
90
+ name: Text Generation
91
+ dataset:
92
+ name: MMLU-PRO (5-shot)
93
+ type: TIGER-Lab/MMLU-Pro
94
+ config: main
95
+ split: test
96
+ args:
97
+ num_few_shot: 5
98
+ metrics:
99
+ - type: acc
100
+ value: 38.1
101
+ name: accuracy
102
+ source:
103
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct
104
+ name: Open LLM Leaderboard
105
+ ---
106
+
107
+ # TheBlueObserver/Falcon3-10B-Instruct-MLX
108
+
109
+ The Model [TheBlueObserver/Falcon3-10B-Instruct-MLX](https://huggingface.co/TheBlueObserver/Falcon3-10B-Instruct-MLX) was
110
+ converted to MLX format from [tiiuae/Falcon3-10B-Instruct](https://huggingface.co/tiiuae/Falcon3-10B-Instruct)
111
+ using mlx-lm version **0.20.2**.
112
+
113
+ ## Use with mlx
114
+
115
+ ```bash
116
+ pip install mlx-lm
117
+ ```
118
+
119
+ ```python
120
+ from mlx_lm import load, generate
121
+
122
+ model, tokenizer = load("TheBlueObserver/Falcon3-10B-Instruct-MLX")
123
+
124
+ prompt="hello"
125
+
126
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
127
+ messages = [{"role": "user", "content": prompt}]
128
+ prompt = tokenizer.apply_chat_template(
129
+ messages, tokenize=False, add_generation_prompt=True
130
+ )
131
+
132
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
133
+ ```
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 11,
8
+ "eos_token_id": 11,
9
+ "head_dim": 256,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "intermediate_size": 23040,
13
+ "max_position_embeddings": 32768,
14
+ "mlp_bias": false,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000042,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": true,
27
+ "vocab_size": 131072
28
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d224c3e5fcec90b7657f21d584cd7e9e3051e47485e1584e864e503db19d041b
3
+ size 5272360690
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d754f23e8c1cbcf2b5d1f29feb6983fb38e5f72485badb96df52a8d74dee9a1c
3
+ size 5366758703
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d144d784929844f59068636f46e00baf0f050ff65663525dc31a49ec895fc6
3
+ size 5366771224
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f8ca503c875115cace8e8f5d4a7a1587878e4f7a4bcce343534cbfff869c3e
3
+ size 4605458786
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 20611307520
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
368
+ "model.norm.weight": "model-00004-of-00004.safetensors"
369
+ }
370
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>EMAIL_ADDRESS<<",
12
+ ">>IP_ADDRESS<<",
13
+ "<|startoftext|>",
14
+ ">>IP_ADDRESS_0<<",
15
+ ">>IP_ADDRESS_1<<",
16
+ ">>IP_ADDRESS_2<<",
17
+ ">>IP_ADDRESS_3<<",
18
+ ">>IP_ADDRESS_4<<",
19
+ ">>IP_ADDRESS_5<<",
20
+ ">>IP_ADDRESS_6<<",
21
+ ">>IP_ADDRESS_7<<",
22
+ ">>IP_ADDRESS_8<<",
23
+ ">>IP_ADDRESS_9<<",
24
+ ">>PASSWORD<<",
25
+ ">>KEY<<"
26
+ ],
27
+ "eos_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<|pad|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
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