Delete model
Browse files- model/Modelfile +0 -13
- model/added_tokens.json +0 -25
- model/config.json +0 -32
- model/generation_config.json +0 -15
- model/merges.txt +0 -0
- model/pytorch_model-00001-of-00004.bin +0 -3
- model/pytorch_model-00001-of-00004.safetensors +0 -3
- model/pytorch_model-00002-of-00004.bin +0 -3
- model/pytorch_model-00002-of-00004.safetensors +0 -3
- model/pytorch_model-00003-of-00004.bin +0 -3
- model/pytorch_model-00003-of-00004.safetensors +0 -3
- model/pytorch_model-00004-of-00004.bin +0 -3
- model/pytorch_model-00004-of-00004.safetensors +0 -3
- model/pytorch_model.bin +0 -3
- model/pytorch_model.bin.index.json +0 -346
- model/special_tokens_map.json +0 -16
- model/tokenizer.json +0 -3
- model/tokenizer_config.json +0 -196
- model/unsloth.F16.gguf +0 -3
- model/vocab.json +0 -0
model/Modelfile
DELETED
@@ -1,13 +0,0 @@
|
|
1 |
-
|
2 |
-
FROM /content/model/unsloth.F16.gguf
|
3 |
-
TEMPLATE """{{ if .System }}<|im_start|>system
|
4 |
-
{{ .System }}<|im_end|>
|
5 |
-
{{ end }}{{ if .Prompt }}<|im_start|>user
|
6 |
-
{{ .Prompt }}<|im_end|>
|
7 |
-
{{ end }}<|im_start|>assistant
|
8 |
-
{{ .Response }}<|im_end|>
|
9 |
-
"""
|
10 |
-
PARAMETER stop "<|im_start|>"
|
11 |
-
PARAMETER stop "<|im_end|>"
|
12 |
-
PARAMETER temperature 1.5
|
13 |
-
PARAMETER min_p 0.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/added_tokens.json
DELETED
@@ -1,25 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"</tool_call>": 151658,
|
3 |
-
"<tool_call>": 151657,
|
4 |
-
"<|PAD_TOKEN|>": 151665,
|
5 |
-
"<|box_end|>": 151649,
|
6 |
-
"<|box_start|>": 151648,
|
7 |
-
"<|endoftext|>": 151643,
|
8 |
-
"<|file_sep|>": 151664,
|
9 |
-
"<|fim_middle|>": 151660,
|
10 |
-
"<|fim_pad|>": 151662,
|
11 |
-
"<|fim_prefix|>": 151659,
|
12 |
-
"<|fim_suffix|>": 151661,
|
13 |
-
"<|im_end|>": 151645,
|
14 |
-
"<|im_start|>": 151644,
|
15 |
-
"<|image_pad|>": 151655,
|
16 |
-
"<|object_ref_end|>": 151647,
|
17 |
-
"<|object_ref_start|>": 151646,
|
18 |
-
"<|quad_end|>": 151651,
|
19 |
-
"<|quad_start|>": 151650,
|
20 |
-
"<|repo_name|>": 151663,
|
21 |
-
"<|video_pad|>": 151656,
|
22 |
-
"<|vision_end|>": 151653,
|
23 |
-
"<|vision_pad|>": 151654,
|
24 |
-
"<|vision_start|>": 151652
|
25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/config.json
DELETED
@@ -1,32 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "unsloth/qwen2.5-1.5b-instruct-bnb-4bit",
|
3 |
-
"architectures": [
|
4 |
-
"Qwen2ForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"bos_token_id": 151643,
|
8 |
-
"eos_token_id": 151645,
|
9 |
-
"hidden_act": "silu",
|
10 |
-
"hidden_size": 1536,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"intermediate_size": 8960,
|
13 |
-
"max_position_embeddings": 32768,
|
14 |
-
"max_window_layers": 21,
|
15 |
-
"model_type": "qwen2",
|
16 |
-
"num_attention_heads": 12,
|
17 |
-
"num_hidden_layers": 28,
|
18 |
-
"num_key_value_heads": 2,
|
19 |
-
"pad_token_id": 151665,
|
20 |
-
"rms_norm_eps": 1e-06,
|
21 |
-
"rope_scaling": null,
|
22 |
-
"rope_theta": 1000000.0,
|
23 |
-
"sliding_window": null,
|
24 |
-
"tie_word_embeddings": true,
|
25 |
-
"torch_dtype": "float16",
|
26 |
-
"transformers_version": "4.46.3",
|
27 |
-
"unsloth_fixed": true,
|
28 |
-
"unsloth_version": "2024.12.4",
|
29 |
-
"use_cache": true,
|
30 |
-
"use_sliding_window": false,
|
31 |
-
"vocab_size": 151936
|
32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/generation_config.json
DELETED
@@ -1,15 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token_id": 151643,
|
3 |
-
"do_sample": true,
|
4 |
-
"eos_token_id": [
|
5 |
-
151645,
|
6 |
-
151643
|
7 |
-
],
|
8 |
-
"max_length": 32768,
|
9 |
-
"pad_token_id": 151665,
|
10 |
-
"repetition_penalty": 1.1,
|
11 |
-
"temperature": 0.7,
|
12 |
-
"top_k": 20,
|
13 |
-
"top_p": 0.8,
|
14 |
-
"transformers_version": "4.46.3"
|
15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
model/pytorch_model-00001-of-00004.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:52f2ae8fc6cb584d02a7b1ac46a1e44d5258bc888854466771709b2ceeda9717
|
3 |
-
size 4877685654
|
|
|
|
|
|
|
|
model/pytorch_model-00001-of-00004.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:9e95bc530facc7c89ed822240f0a9ce756bd39809b62e101296ee87f26675453
|
3 |
-
size 4877660672
|
|
|
|
|
|
|
|
model/pytorch_model-00002-of-00004.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:3e02e07814beb1a968d316ad351bde80036521a5159b102316a1e3be4a834aef
|
3 |
-
size 4932780072
|
|
|
|
|
|
|
|
model/pytorch_model-00002-of-00004.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:cbdc12573f2acafbc941d0fdad43ff94d84bde5fd9c91852df8c914f6eb72b29
|
3 |
-
size 4932750888
|
|
|
|
|
|
|
|
model/pytorch_model-00003-of-00004.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:2f4e0f859ae883319419a4deb63661da476648e3a2f37ab4c4a0fad0dc37b3a0
|
3 |
-
size 4330891162
|
|
|
|
|
|
|
|
model/pytorch_model-00003-of-00004.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:ed3f6f87d4dd1ea86c40ca32a919acbae417ea695dc4aa3f1f0d654fa38a055d
|
3 |
-
size 4330865088
|
|
|
|
|
|
|
|
model/pytorch_model-00004-of-00004.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:6ee93278f6bc5238acd4212f195d69475f3b94329f01bfd49d94c560ff88ee1f
|
3 |
-
size 1089996165
|
|
|
|
|
|
|
|
model/pytorch_model-00004-of-00004.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:1cc871228222138b181ba19eda684bea4e779fe90cd5bf5c0592b72b31be4bb4
|
3 |
-
size 1089994880
|
|
|
|
|
|
|
|
model/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5d096631892ba7dd573be0b24a92c6dde048aa4302dd813584ac3790fd23b6e2
|
3 |
-
size 3087542290
|
|
|
|
|
|
|
|
model/pytorch_model.bin.index.json
DELETED
@@ -1,346 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"metadata": {
|
3 |
-
"total_size": 15231233024
|
4 |
-
},
|
5 |
-
"weight_map": {
|
6 |
-
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
7 |
-
"model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
|
8 |
-
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
9 |
-
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
10 |
-
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
11 |
-
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
12 |
-
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
13 |
-
"model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
14 |
-
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
15 |
-
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
16 |
-
"model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
17 |
-
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
18 |
-
"model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
19 |
-
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
20 |
-
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
21 |
-
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
22 |
-
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
23 |
-
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
24 |
-
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
25 |
-
"model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
26 |
-
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
27 |
-
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
28 |
-
"model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
29 |
-
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
30 |
-
"model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
31 |
-
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
32 |
-
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
33 |
-
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
34 |
-
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
35 |
-
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
36 |
-
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
37 |
-
"model.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
38 |
-
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
39 |
-
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
40 |
-
"model.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
41 |
-
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
42 |
-
"model.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
43 |
-
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
44 |
-
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
45 |
-
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
46 |
-
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
47 |
-
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
48 |
-
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
49 |
-
"model.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
50 |
-
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
51 |
-
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
52 |
-
"model.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
53 |
-
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
54 |
-
"model.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
55 |
-
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
56 |
-
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
57 |
-
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
58 |
-
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
59 |
-
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
60 |
-
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
61 |
-
"model.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
62 |
-
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
63 |
-
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
64 |
-
"model.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
65 |
-
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
66 |
-
"model.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
67 |
-
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
68 |
-
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
69 |
-
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
70 |
-
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
71 |
-
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
72 |
-
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
73 |
-
"model.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
74 |
-
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
75 |
-
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
76 |
-
"model.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
77 |
-
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
78 |
-
"model.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
79 |
-
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
80 |
-
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
81 |
-
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
82 |
-
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
83 |
-
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
84 |
-
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
85 |
-
"model.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
86 |
-
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
87 |
-
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
88 |
-
"model.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
89 |
-
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
90 |
-
"model.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
91 |
-
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
92 |
-
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
93 |
-
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
94 |
-
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
95 |
-
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
96 |
-
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
97 |
-
"model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
98 |
-
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
99 |
-
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
100 |
-
"model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
101 |
-
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
102 |
-
"model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
103 |
-
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
104 |
-
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
105 |
-
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
106 |
-
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
107 |
-
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
108 |
-
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
109 |
-
"model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
110 |
-
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
111 |
-
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
112 |
-
"model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
113 |
-
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
114 |
-
"model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
115 |
-
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
116 |
-
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
117 |
-
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
118 |
-
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
119 |
-
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
120 |
-
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
121 |
-
"model.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
122 |
-
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
123 |
-
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
124 |
-
"model.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
125 |
-
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
126 |
-
"model.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
127 |
-
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
128 |
-
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
129 |
-
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
130 |
-
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
131 |
-
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
132 |
-
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
133 |
-
"model.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
134 |
-
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
135 |
-
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
136 |
-
"model.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
137 |
-
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
138 |
-
"model.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
139 |
-
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
140 |
-
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
141 |
-
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
142 |
-
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
143 |
-
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
144 |
-
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
145 |
-
"model.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
146 |
-
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
147 |
-
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
148 |
-
"model.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
149 |
-
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
150 |
-
"model.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
151 |
-
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
152 |
-
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
153 |
-
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
154 |
-
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
155 |
-
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
156 |
-
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
157 |
-
"model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
158 |
-
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
159 |
-
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
160 |
-
"model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
161 |
-
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
162 |
-
"model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
163 |
-
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
164 |
-
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
165 |
-
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
166 |
-
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
167 |
-
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
168 |
-
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
169 |
-
"model.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
170 |
-
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
171 |
-
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
172 |
-
"model.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
173 |
-
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
174 |
-
"model.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
175 |
-
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
176 |
-
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
177 |
-
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
178 |
-
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
179 |
-
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
180 |
-
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
181 |
-
"model.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
182 |
-
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
183 |
-
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
184 |
-
"model.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
185 |
-
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
186 |
-
"model.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
187 |
-
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
188 |
-
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
189 |
-
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
190 |
-
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
191 |
-
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
192 |
-
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
193 |
-
"model.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
194 |
-
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
195 |
-
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
196 |
-
"model.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
197 |
-
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
198 |
-
"model.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
199 |
-
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
200 |
-
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
201 |
-
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
202 |
-
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
203 |
-
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
204 |
-
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
205 |
-
"model.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
206 |
-
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
207 |
-
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
208 |
-
"model.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
209 |
-
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
210 |
-
"model.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
211 |
-
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
212 |
-
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
213 |
-
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
214 |
-
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
215 |
-
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
216 |
-
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
217 |
-
"model.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
218 |
-
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
219 |
-
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
220 |
-
"model.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
221 |
-
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
222 |
-
"model.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
223 |
-
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
224 |
-
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
225 |
-
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
226 |
-
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
227 |
-
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
228 |
-
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
229 |
-
"model.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
230 |
-
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
231 |
-
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
232 |
-
"model.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
233 |
-
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
234 |
-
"model.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
235 |
-
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
236 |
-
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
237 |
-
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
238 |
-
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
239 |
-
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
240 |
-
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
241 |
-
"model.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
242 |
-
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
243 |
-
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
244 |
-
"model.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
245 |
-
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
246 |
-
"model.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
247 |
-
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
248 |
-
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
249 |
-
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
250 |
-
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
251 |
-
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
252 |
-
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
253 |
-
"model.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
254 |
-
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
255 |
-
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
256 |
-
"model.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
257 |
-
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
258 |
-
"model.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
259 |
-
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
260 |
-
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
261 |
-
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
262 |
-
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
263 |
-
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
264 |
-
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
265 |
-
"model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
266 |
-
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
267 |
-
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
268 |
-
"model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
269 |
-
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
270 |
-
"model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
271 |
-
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
272 |
-
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
273 |
-
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
274 |
-
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
275 |
-
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
276 |
-
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
277 |
-
"model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
278 |
-
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
279 |
-
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
280 |
-
"model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
281 |
-
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
282 |
-
"model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
283 |
-
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
284 |
-
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
285 |
-
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
286 |
-
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
287 |
-
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
288 |
-
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
289 |
-
"model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
290 |
-
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
291 |
-
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
292 |
-
"model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
293 |
-
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
294 |
-
"model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
295 |
-
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
296 |
-
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
297 |
-
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
298 |
-
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
299 |
-
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
300 |
-
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
301 |
-
"model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
302 |
-
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
303 |
-
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
304 |
-
"model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
305 |
-
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
306 |
-
"model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
307 |
-
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
308 |
-
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
309 |
-
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
310 |
-
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
311 |
-
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
312 |
-
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
313 |
-
"model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
314 |
-
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
315 |
-
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
316 |
-
"model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
317 |
-
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
318 |
-
"model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
319 |
-
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
320 |
-
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
321 |
-
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
322 |
-
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
323 |
-
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
324 |
-
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
325 |
-
"model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
326 |
-
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
327 |
-
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
328 |
-
"model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
329 |
-
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
330 |
-
"model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
331 |
-
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
332 |
-
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
333 |
-
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
334 |
-
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
335 |
-
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
336 |
-
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
337 |
-
"model.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
338 |
-
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
339 |
-
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
340 |
-
"model.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
341 |
-
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
342 |
-
"model.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
343 |
-
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
344 |
-
"model.norm.weight": "pytorch_model-00003-of-00004.bin"
|
345 |
-
}
|
346 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/special_tokens_map.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"eos_token": {
|
3 |
-
"content": "<|im_end|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"pad_token": {
|
10 |
-
"content": "<|PAD_TOKEN|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
}
|
16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/tokenizer.json
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
|
3 |
-
size 11422086
|
|
|
|
|
|
|
|
model/tokenizer_config.json
DELETED
@@ -1,196 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"151643": {
|
4 |
-
"content": "<|endoftext|>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"151644": {
|
12 |
-
"content": "<|im_start|>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"151645": {
|
20 |
-
"content": "<|im_end|>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"151646": {
|
28 |
-
"content": "<|object_ref_start|>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"151647": {
|
36 |
-
"content": "<|object_ref_end|>",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"151648": {
|
44 |
-
"content": "<|box_start|>",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
"151649": {
|
52 |
-
"content": "<|box_end|>",
|
53 |
-
"lstrip": false,
|
54 |
-
"normalized": false,
|
55 |
-
"rstrip": false,
|
56 |
-
"single_word": false,
|
57 |
-
"special": true
|
58 |
-
},
|
59 |
-
"151650": {
|
60 |
-
"content": "<|quad_start|>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false,
|
65 |
-
"special": true
|
66 |
-
},
|
67 |
-
"151651": {
|
68 |
-
"content": "<|quad_end|>",
|
69 |
-
"lstrip": false,
|
70 |
-
"normalized": false,
|
71 |
-
"rstrip": false,
|
72 |
-
"single_word": false,
|
73 |
-
"special": true
|
74 |
-
},
|
75 |
-
"151652": {
|
76 |
-
"content": "<|vision_start|>",
|
77 |
-
"lstrip": false,
|
78 |
-
"normalized": false,
|
79 |
-
"rstrip": false,
|
80 |
-
"single_word": false,
|
81 |
-
"special": true
|
82 |
-
},
|
83 |
-
"151653": {
|
84 |
-
"content": "<|vision_end|>",
|
85 |
-
"lstrip": false,
|
86 |
-
"normalized": false,
|
87 |
-
"rstrip": false,
|
88 |
-
"single_word": false,
|
89 |
-
"special": true
|
90 |
-
},
|
91 |
-
"151654": {
|
92 |
-
"content": "<|vision_pad|>",
|
93 |
-
"lstrip": false,
|
94 |
-
"normalized": false,
|
95 |
-
"rstrip": false,
|
96 |
-
"single_word": false,
|
97 |
-
"special": true
|
98 |
-
},
|
99 |
-
"151655": {
|
100 |
-
"content": "<|image_pad|>",
|
101 |
-
"lstrip": false,
|
102 |
-
"normalized": false,
|
103 |
-
"rstrip": false,
|
104 |
-
"single_word": false,
|
105 |
-
"special": true
|
106 |
-
},
|
107 |
-
"151656": {
|
108 |
-
"content": "<|video_pad|>",
|
109 |
-
"lstrip": false,
|
110 |
-
"normalized": false,
|
111 |
-
"rstrip": false,
|
112 |
-
"single_word": false,
|
113 |
-
"special": true
|
114 |
-
},
|
115 |
-
"151657": {
|
116 |
-
"content": "<tool_call>",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false,
|
121 |
-
"special": false
|
122 |
-
},
|
123 |
-
"151658": {
|
124 |
-
"content": "</tool_call>",
|
125 |
-
"lstrip": false,
|
126 |
-
"normalized": false,
|
127 |
-
"rstrip": false,
|
128 |
-
"single_word": false,
|
129 |
-
"special": false
|
130 |
-
},
|
131 |
-
"151659": {
|
132 |
-
"content": "<|fim_prefix|>",
|
133 |
-
"lstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"rstrip": false,
|
136 |
-
"single_word": false,
|
137 |
-
"special": false
|
138 |
-
},
|
139 |
-
"151660": {
|
140 |
-
"content": "<|fim_middle|>",
|
141 |
-
"lstrip": false,
|
142 |
-
"normalized": false,
|
143 |
-
"rstrip": false,
|
144 |
-
"single_word": false,
|
145 |
-
"special": false
|
146 |
-
},
|
147 |
-
"151661": {
|
148 |
-
"content": "<|fim_suffix|>",
|
149 |
-
"lstrip": false,
|
150 |
-
"normalized": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"single_word": false,
|
153 |
-
"special": false
|
154 |
-
},
|
155 |
-
"151662": {
|
156 |
-
"content": "<|fim_pad|>",
|
157 |
-
"lstrip": false,
|
158 |
-
"normalized": false,
|
159 |
-
"rstrip": false,
|
160 |
-
"single_word": false,
|
161 |
-
"special": false
|
162 |
-
},
|
163 |
-
"151663": {
|
164 |
-
"content": "<|repo_name|>",
|
165 |
-
"lstrip": false,
|
166 |
-
"normalized": false,
|
167 |
-
"rstrip": false,
|
168 |
-
"single_word": false,
|
169 |
-
"special": false
|
170 |
-
},
|
171 |
-
"151664": {
|
172 |
-
"content": "<|file_sep|>",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": false,
|
177 |
-
"special": false
|
178 |
-
},
|
179 |
-
"151665": {
|
180 |
-
"content": "<|PAD_TOKEN|>",
|
181 |
-
"lstrip": false,
|
182 |
-
"normalized": false,
|
183 |
-
"rstrip": false,
|
184 |
-
"single_word": false,
|
185 |
-
"special": true
|
186 |
-
}
|
187 |
-
},
|
188 |
-
"bos_token": null,
|
189 |
-
"chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
|
190 |
-
"clean_up_tokenization_spaces": false,
|
191 |
-
"eos_token": "<|im_end|>",
|
192 |
-
"model_max_length": 1000000000000000019884624838656,
|
193 |
-
"pad_token": "<|PAD_TOKEN|>",
|
194 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
195 |
-
"unk_token": null
|
196 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/unsloth.F16.gguf
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f34a2a2fa5bb2df9b4fc5ea14bc7b79c1207f90019464483d9fff2852f04d679
|
3 |
-
size 3093667200
|
|
|
|
|
|
|
|
model/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|