Orion
commited on
Commit
•
12f21d0
1
Parent(s):
b4f6700
add: model files
Browse files- added_tokens.json +44 -0
- config.json +37 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +746 -0
- special_tokens_map.json +34 -0
- tokenization_inflm.py +292 -0
- tokenizer.model +3 -0
- tokenizer_config.json +394 -0
added_tokens.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<code_to_intermediate>": 96521,
|
3 |
+
"<empty_output>": 96520,
|
4 |
+
"<file_sep>": 96511,
|
5 |
+
"<fim_middle>": 96508,
|
6 |
+
"<fim_prefix>": 96507,
|
7 |
+
"<fim_suffix>": 96509,
|
8 |
+
"<intermediate_to_code>": 96522,
|
9 |
+
"<issue_closed>": 96514,
|
10 |
+
"<issue_comment>": 96513,
|
11 |
+
"<issue_start>": 96512,
|
12 |
+
"<jupyter_code>": 96517,
|
13 |
+
"<jupyter_output>": 96518,
|
14 |
+
"<jupyter_script>": 96519,
|
15 |
+
"<jupyter_start>": 96515,
|
16 |
+
"<jupyter_text>": 96516,
|
17 |
+
"<pr>": 96523,
|
18 |
+
"<pr_base>": 96526,
|
19 |
+
"<pr_base_code>": 96528,
|
20 |
+
"<pr_comment>": 96531,
|
21 |
+
"<pr_diff>": 96529,
|
22 |
+
"<pr_diff_hunk>": 96530,
|
23 |
+
"<pr_diff_hunk_comment_line>": 96538,
|
24 |
+
"<pr_event_id>": 96532,
|
25 |
+
"<pr_file>": 96527,
|
26 |
+
"<pr_in_reply_to_comment_id>": 96537,
|
27 |
+
"<pr_in_reply_to_review_id>": 96536,
|
28 |
+
"<pr_is_merged>": 96525,
|
29 |
+
"<pr_review>": 96533,
|
30 |
+
"<pr_review_comment>": 96535,
|
31 |
+
"<pr_review_state>": 96534,
|
32 |
+
"<pr_status>": 96524,
|
33 |
+
"<repo_name>": 96510,
|
34 |
+
"<|endoftext|>": 96506,
|
35 |
+
"<|end|>": 96500,
|
36 |
+
"<|im_end|>": 96539,
|
37 |
+
"<|im_start|>": 96540,
|
38 |
+
"<|message|>": 96501,
|
39 |
+
"<|pad|>": 96505,
|
40 |
+
"<|start|>": 96499,
|
41 |
+
"<|tool_end|>": 96504,
|
42 |
+
"<|tool_excute|>": 96503,
|
43 |
+
"<|tool_start|>": 96502
|
44 |
+
}
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/orion/ai/Models/opcode-8b",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 96540,
|
9 |
+
"eos_token_id": 96539,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"quantization_config": {
|
22 |
+
"bits": 4,
|
23 |
+
"group_size": 128,
|
24 |
+
"modules_to_not_convert": null,
|
25 |
+
"quant_method": "awq",
|
26 |
+
"version": "gemm",
|
27 |
+
"zero_point": true
|
28 |
+
},
|
29 |
+
"rms_norm_eps": 1e-05,
|
30 |
+
"rope_scaling": null,
|
31 |
+
"rope_theta": 500000.0,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"torch_dtype": "float16",
|
34 |
+
"transformers_version": "4.44.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 96640
|
37 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 96540,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 96539,
|
6 |
+
"transformers_version": "4.44.2"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e3dbd5eec90121fb3cbb4e4d9285968beee9c2e6c2fa280eda4f538f622eb51
|
3 |
+
size 4418267024
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08a5fba4953323ca1146243821afccb9ed25fb5202512590b5a23180a78b3eac
|
3 |
+
size 791675008
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,746 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 5209858048
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
7 |
+
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
8 |
+
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
9 |
+
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
10 |
+
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
11 |
+
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
13 |
+
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
16 |
+
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
17 |
+
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
20 |
+
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
22 |
+
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
25 |
+
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
26 |
+
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
31 |
+
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
34 |
+
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
35 |
+
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
38 |
+
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
40 |
+
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
43 |
+
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
44 |
+
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
47 |
+
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
49 |
+
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
52 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
56 |
+
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
58 |
+
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
61 |
+
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
62 |
+
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
65 |
+
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
67 |
+
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
70 |
+
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
71 |
+
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
72 |
+
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
73 |
+
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
74 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
76 |
+
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
79 |
+
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
82 |
+
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
83 |
+
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
85 |
+
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
86 |
+
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
88 |
+
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
89 |
+
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
90 |
+
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
93 |
+
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
94 |
+
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
95 |
+
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
96 |
+
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
97 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
98 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
100 |
+
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
101 |
+
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
102 |
+
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
103 |
+
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
104 |
+
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
105 |
+
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
106 |
+
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
107 |
+
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
108 |
+
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
109 |
+
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
110 |
+
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
111 |
+
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
112 |
+
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
113 |
+
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
114 |
+
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
115 |
+
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
116 |
+
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
117 |
+
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
118 |
+
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
119 |
+
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
120 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
121 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
122 |
+
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
123 |
+
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
124 |
+
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
125 |
+
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
126 |
+
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
127 |
+
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
128 |
+
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
129 |
+
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
130 |
+
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
131 |
+
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
132 |
+
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
133 |
+
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
134 |
+
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
135 |
+
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
136 |
+
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
137 |
+
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
138 |
+
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
139 |
+
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
140 |
+
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
141 |
+
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
142 |
+
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
143 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
144 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
145 |
+
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
146 |
+
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
147 |
+
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
148 |
+
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
149 |
+
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
151 |
+
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
152 |
+
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
153 |
+
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
154 |
+
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
155 |
+
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
156 |
+
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
157 |
+
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
158 |
+
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
159 |
+
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
160 |
+
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
161 |
+
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
162 |
+
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
163 |
+
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
164 |
+
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
166 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
169 |
+
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
170 |
+
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
171 |
+
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
172 |
+
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
173 |
+
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
174 |
+
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
176 |
+
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
178 |
+
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
180 |
+
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
181 |
+
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
182 |
+
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
183 |
+
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
184 |
+
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
185 |
+
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
188 |
+
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
189 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
190 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
192 |
+
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
193 |
+
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
194 |
+
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
195 |
+
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
196 |
+
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
197 |
+
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
198 |
+
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
199 |
+
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
200 |
+
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
201 |
+
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
202 |
+
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
203 |
+
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
204 |
+
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
205 |
+
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
206 |
+
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
207 |
+
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
208 |
+
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
209 |
+
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
210 |
+
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
211 |
+
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
212 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
213 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
214 |
+
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
215 |
+
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
216 |
+
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
217 |
+
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
218 |
+
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
219 |
+
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
220 |
+
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
221 |
+
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
222 |
+
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
223 |
+
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
224 |
+
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
225 |
+
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
226 |
+
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
227 |
+
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
228 |
+
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
229 |
+
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
230 |
+
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
231 |
+
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
232 |
+
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
233 |
+
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
234 |
+
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
235 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
236 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
237 |
+
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
238 |
+
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
239 |
+
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
240 |
+
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
241 |
+
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
242 |
+
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
243 |
+
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
244 |
+
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
245 |
+
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
246 |
+
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
247 |
+
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
248 |
+
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
249 |
+
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
250 |
+
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
251 |
+
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
252 |
+
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
253 |
+
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
254 |
+
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
255 |
+
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
256 |
+
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
257 |
+
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
258 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
259 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
260 |
+
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
261 |
+
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
262 |
+
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
263 |
+
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
264 |
+
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
265 |
+
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
266 |
+
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
267 |
+
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
268 |
+
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
269 |
+
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
270 |
+
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
271 |
+
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
272 |
+
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
273 |
+
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
274 |
+
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
275 |
+
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
276 |
+
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
277 |
+
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
278 |
+
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
279 |
+
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
280 |
+
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
281 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
282 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
283 |
+
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
284 |
+
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
285 |
+
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
286 |
+
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
287 |
+
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
288 |
+
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
289 |
+
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
290 |
+
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
291 |
+
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
292 |
+
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
293 |
+
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
294 |
+
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
295 |
+
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
296 |
+
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
297 |
+
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
298 |
+
"model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
299 |
+
"model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
300 |
+
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
301 |
+
"model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
302 |
+
"model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
303 |
+
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
304 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
305 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
306 |
+
"model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
307 |
+
"model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
308 |
+
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
309 |
+
"model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
310 |
+
"model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
311 |
+
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
312 |
+
"model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
313 |
+
"model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
314 |
+
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
315 |
+
"model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
316 |
+
"model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
317 |
+
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
318 |
+
"model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
319 |
+
"model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
320 |
+
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
321 |
+
"model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
322 |
+
"model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
323 |
+
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
324 |
+
"model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
325 |
+
"model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
326 |
+
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
327 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
328 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
329 |
+
"model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
330 |
+
"model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
331 |
+
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
332 |
+
"model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
333 |
+
"model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
334 |
+
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
335 |
+
"model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
336 |
+
"model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
337 |
+
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
338 |
+
"model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
339 |
+
"model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
340 |
+
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
341 |
+
"model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
342 |
+
"model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
343 |
+
"model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
344 |
+
"model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
345 |
+
"model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
346 |
+
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
347 |
+
"model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
348 |
+
"model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
349 |
+
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
350 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
351 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
352 |
+
"model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
353 |
+
"model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
354 |
+
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
355 |
+
"model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
356 |
+
"model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
357 |
+
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
358 |
+
"model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
359 |
+
"model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
360 |
+
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
361 |
+
"model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
362 |
+
"model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
363 |
+
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
364 |
+
"model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
365 |
+
"model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
366 |
+
"model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
367 |
+
"model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
368 |
+
"model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
369 |
+
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
370 |
+
"model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
371 |
+
"model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
372 |
+
"model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
373 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
374 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
375 |
+
"model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
376 |
+
"model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
377 |
+
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
378 |
+
"model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
379 |
+
"model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
380 |
+
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
381 |
+
"model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
382 |
+
"model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
383 |
+
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
384 |
+
"model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
385 |
+
"model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
386 |
+
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
387 |
+
"model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
388 |
+
"model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
389 |
+
"model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
390 |
+
"model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
391 |
+
"model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
392 |
+
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
393 |
+
"model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
394 |
+
"model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
395 |
+
"model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
396 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
397 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
398 |
+
"model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
399 |
+
"model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
400 |
+
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
401 |
+
"model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
402 |
+
"model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
403 |
+
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
404 |
+
"model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
405 |
+
"model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
406 |
+
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
407 |
+
"model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
408 |
+
"model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
409 |
+
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
410 |
+
"model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
411 |
+
"model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
412 |
+
"model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
413 |
+
"model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
414 |
+
"model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
415 |
+
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
416 |
+
"model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
417 |
+
"model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
418 |
+
"model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
419 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
420 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
421 |
+
"model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
422 |
+
"model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
423 |
+
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
424 |
+
"model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
425 |
+
"model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
426 |
+
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
427 |
+
"model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
428 |
+
"model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
429 |
+
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
430 |
+
"model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
431 |
+
"model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
432 |
+
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
433 |
+
"model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
434 |
+
"model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
435 |
+
"model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
436 |
+
"model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
437 |
+
"model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
438 |
+
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
439 |
+
"model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
440 |
+
"model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
441 |
+
"model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
442 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
443 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
444 |
+
"model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
445 |
+
"model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
446 |
+
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
447 |
+
"model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
448 |
+
"model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
449 |
+
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
450 |
+
"model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
451 |
+
"model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
452 |
+
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
453 |
+
"model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
454 |
+
"model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
455 |
+
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
456 |
+
"model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
457 |
+
"model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
458 |
+
"model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
459 |
+
"model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
460 |
+
"model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
461 |
+
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
462 |
+
"model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
463 |
+
"model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
464 |
+
"model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
465 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
466 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
467 |
+
"model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
468 |
+
"model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
469 |
+
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
470 |
+
"model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
471 |
+
"model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
472 |
+
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
473 |
+
"model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
474 |
+
"model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
475 |
+
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
476 |
+
"model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
477 |
+
"model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
478 |
+
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
479 |
+
"model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
480 |
+
"model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
481 |
+
"model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
482 |
+
"model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
483 |
+
"model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
484 |
+
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
485 |
+
"model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
486 |
+
"model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
487 |
+
"model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
488 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
489 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
490 |
+
"model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
491 |
+
"model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
492 |
+
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
493 |
+
"model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
494 |
+
"model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
495 |
+
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
496 |
+
"model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
497 |
+
"model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
498 |
+
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
499 |
+
"model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
500 |
+
"model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
501 |
+
"model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
502 |
+
"model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
503 |
+
"model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
504 |
+
"model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
505 |
+
"model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
506 |
+
"model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
507 |
+
"model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
508 |
+
"model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
509 |
+
"model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
510 |
+
"model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
511 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
512 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
513 |
+
"model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
514 |
+
"model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
515 |
+
"model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
516 |
+
"model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
517 |
+
"model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
518 |
+
"model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
519 |
+
"model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
520 |
+
"model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
521 |
+
"model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
522 |
+
"model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
523 |
+
"model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
524 |
+
"model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
525 |
+
"model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
526 |
+
"model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
527 |
+
"model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
528 |
+
"model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
529 |
+
"model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
530 |
+
"model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
531 |
+
"model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
532 |
+
"model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
533 |
+
"model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
534 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
535 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
536 |
+
"model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
537 |
+
"model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
538 |
+
"model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
539 |
+
"model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
540 |
+
"model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
541 |
+
"model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
542 |
+
"model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
543 |
+
"model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
544 |
+
"model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
545 |
+
"model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
546 |
+
"model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
547 |
+
"model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
548 |
+
"model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
549 |
+
"model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
550 |
+
"model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
551 |
+
"model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
552 |
+
"model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
553 |
+
"model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
554 |
+
"model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
555 |
+
"model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
556 |
+
"model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
557 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
558 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
559 |
+
"model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
560 |
+
"model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
561 |
+
"model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
562 |
+
"model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
563 |
+
"model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
564 |
+
"model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
565 |
+
"model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
566 |
+
"model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
567 |
+
"model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
568 |
+
"model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
569 |
+
"model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
570 |
+
"model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
571 |
+
"model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
572 |
+
"model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
573 |
+
"model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
574 |
+
"model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
575 |
+
"model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
576 |
+
"model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
577 |
+
"model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
578 |
+
"model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
579 |
+
"model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
580 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
581 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
582 |
+
"model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
583 |
+
"model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
584 |
+
"model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
585 |
+
"model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
586 |
+
"model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
587 |
+
"model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
588 |
+
"model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
589 |
+
"model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
590 |
+
"model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
591 |
+
"model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
592 |
+
"model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
593 |
+
"model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
594 |
+
"model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
595 |
+
"model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
596 |
+
"model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
597 |
+
"model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
598 |
+
"model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
599 |
+
"model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
600 |
+
"model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
601 |
+
"model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
602 |
+
"model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
603 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
604 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
605 |
+
"model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
606 |
+
"model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
607 |
+
"model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
608 |
+
"model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
609 |
+
"model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
610 |
+
"model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
611 |
+
"model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
612 |
+
"model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
613 |
+
"model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
614 |
+
"model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
615 |
+
"model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
616 |
+
"model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
617 |
+
"model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
618 |
+
"model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
619 |
+
"model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
620 |
+
"model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
621 |
+
"model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
622 |
+
"model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
623 |
+
"model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
624 |
+
"model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
625 |
+
"model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
626 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
627 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
628 |
+
"model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
629 |
+
"model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
630 |
+
"model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
631 |
+
"model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
632 |
+
"model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
633 |
+
"model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
634 |
+
"model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
635 |
+
"model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
636 |
+
"model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
637 |
+
"model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
638 |
+
"model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
639 |
+
"model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
640 |
+
"model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
641 |
+
"model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
642 |
+
"model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
643 |
+
"model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
644 |
+
"model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
645 |
+
"model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
646 |
+
"model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
647 |
+
"model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
648 |
+
"model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
649 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
650 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
651 |
+
"model.layers.28.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
652 |
+
"model.layers.28.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
653 |
+
"model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
654 |
+
"model.layers.28.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
655 |
+
"model.layers.28.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
656 |
+
"model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
657 |
+
"model.layers.28.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
658 |
+
"model.layers.28.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
659 |
+
"model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
660 |
+
"model.layers.28.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
661 |
+
"model.layers.28.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
662 |
+
"model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
663 |
+
"model.layers.28.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
664 |
+
"model.layers.28.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
665 |
+
"model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
666 |
+
"model.layers.28.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
667 |
+
"model.layers.28.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
668 |
+
"model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
669 |
+
"model.layers.28.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
670 |
+
"model.layers.28.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
671 |
+
"model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
672 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
673 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
674 |
+
"model.layers.29.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
675 |
+
"model.layers.29.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
676 |
+
"model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
677 |
+
"model.layers.29.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
678 |
+
"model.layers.29.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
679 |
+
"model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
680 |
+
"model.layers.29.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
681 |
+
"model.layers.29.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
682 |
+
"model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
683 |
+
"model.layers.29.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
684 |
+
"model.layers.29.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
685 |
+
"model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
686 |
+
"model.layers.29.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
687 |
+
"model.layers.29.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
688 |
+
"model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
689 |
+
"model.layers.29.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
690 |
+
"model.layers.29.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
691 |
+
"model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
692 |
+
"model.layers.29.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
693 |
+
"model.layers.29.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
694 |
+
"model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
695 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
696 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
697 |
+
"model.layers.30.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
698 |
+
"model.layers.30.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
699 |
+
"model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
700 |
+
"model.layers.30.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
701 |
+
"model.layers.30.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
702 |
+
"model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
703 |
+
"model.layers.30.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
704 |
+
"model.layers.30.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
705 |
+
"model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
706 |
+
"model.layers.30.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
707 |
+
"model.layers.30.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
708 |
+
"model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
709 |
+
"model.layers.30.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
710 |
+
"model.layers.30.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
711 |
+
"model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
712 |
+
"model.layers.30.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
713 |
+
"model.layers.30.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
714 |
+
"model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
715 |
+
"model.layers.30.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
716 |
+
"model.layers.30.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
717 |
+
"model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
718 |
+
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
719 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
720 |
+
"model.layers.31.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
721 |
+
"model.layers.31.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
722 |
+
"model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
723 |
+
"model.layers.31.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
724 |
+
"model.layers.31.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
725 |
+
"model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
726 |
+
"model.layers.31.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
727 |
+
"model.layers.31.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
728 |
+
"model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
729 |
+
"model.layers.31.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
730 |
+
"model.layers.31.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
731 |
+
"model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
732 |
+
"model.layers.31.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
733 |
+
"model.layers.31.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
734 |
+
"model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
735 |
+
"model.layers.31.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
736 |
+
"model.layers.31.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
737 |
+
"model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
738 |
+
"model.layers.31.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
739 |
+
"model.layers.31.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
740 |
+
"model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
741 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
742 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
743 |
+
"model.norm.weight": "model-00001-of-00002.safetensors",
|
744 |
+
"lm_head.weight": "model-00002-of-00002.safetensors"
|
745 |
+
}
|
746 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_end|>",
|
4 |
+
"<|im_start|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|im_start|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenization_inflm.py
ADDED
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
|
5 |
+
# and OPT implementations in this library. It has been modified from its
|
6 |
+
# original forms to accommodate minor architectural differences compared
|
7 |
+
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
|
8 |
+
#
|
9 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
10 |
+
# you may not use this file except in compliance with the License.
|
11 |
+
# You may obtain a copy of the License at
|
12 |
+
#
|
13 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
14 |
+
#
|
15 |
+
# Unless required by applicable law or agreed to in writing, software
|
16 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
17 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
18 |
+
# See the License for the specific language governing permissions and
|
19 |
+
# limitations under the License.
|
20 |
+
|
21 |
+
"""Tokenization classes for INFLMTokenizer."""
|
22 |
+
import os
|
23 |
+
from shutil import copyfile
|
24 |
+
from typing import Any, Dict, List, Optional, Tuple
|
25 |
+
|
26 |
+
import sentencepiece as spm
|
27 |
+
|
28 |
+
from transformers.tokenization_utils import PreTrainedTokenizer
|
29 |
+
from transformers.utils import logging
|
30 |
+
|
31 |
+
from tokenizers import pre_tokenizers,Regex,decoders
|
32 |
+
from tokenizers.pre_tokenizers import Digits, Split, ByteLevel
|
33 |
+
import os
|
34 |
+
|
35 |
+
# same as gpt4 cl-base-100k
|
36 |
+
PATTERN = Regex("(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+\s+(\S)+")
|
37 |
+
|
38 |
+
logger = logging.get_logger(__name__)
|
39 |
+
|
40 |
+
VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
|
41 |
+
|
42 |
+
PRETRAINED_VOCAB_FILES_MAP = {}
|
43 |
+
|
44 |
+
|
45 |
+
class INFLMTokenizer(PreTrainedTokenizer):
|
46 |
+
"""
|
47 |
+
Construct a INFLMTokenizer tokenizer based on sentence-piece
|
48 |
+
|
49 |
+
Args:
|
50 |
+
vocab_file (`str`):
|
51 |
+
Path to the vocabulary file.
|
52 |
+
"""
|
53 |
+
|
54 |
+
vocab_files_names = VOCAB_FILES_NAMES
|
55 |
+
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
|
56 |
+
model_input_names = ["input_ids", "attention_mask"]
|
57 |
+
_auto_class = "AutoTokenizer"
|
58 |
+
|
59 |
+
def __init__(
|
60 |
+
self,
|
61 |
+
vocab_file,
|
62 |
+
unk_token="<unk>",
|
63 |
+
bos_token="<s>",
|
64 |
+
eos_token="</s>",
|
65 |
+
pad_token="<pad>",
|
66 |
+
sp_model_kwargs: Optional[Dict[str, Any]] = None,
|
67 |
+
add_bos_token=False,
|
68 |
+
add_eos_token=False,
|
69 |
+
decode_with_prefix_space=False,
|
70 |
+
clean_up_tokenization_spaces=False,
|
71 |
+
spaces_between_special_tokens=False,
|
72 |
+
**kwargs,
|
73 |
+
):
|
74 |
+
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
|
75 |
+
self.vocab_file = vocab_file
|
76 |
+
self.add_bos_token = add_bos_token
|
77 |
+
self.add_eos_token = add_eos_token
|
78 |
+
self.decode_with_prefix_space = decode_with_prefix_space
|
79 |
+
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
80 |
+
self.sp_model.Load(vocab_file)
|
81 |
+
self._no_prefix_space_tokens = None
|
82 |
+
self.pre_tokenizer = pre_tokenizers.Sequence([Split(pattern =PATTERN,behavior = "isolated", invert = False)])
|
83 |
+
super().__init__(
|
84 |
+
bos_token=bos_token,
|
85 |
+
eos_token=eos_token,
|
86 |
+
unk_token=unk_token,
|
87 |
+
pad_token=pad_token,
|
88 |
+
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
89 |
+
spaces_between_special_tokens=spaces_between_special_tokens,
|
90 |
+
**kwargs,
|
91 |
+
)
|
92 |
+
|
93 |
+
""" Initialisation"""
|
94 |
+
|
95 |
+
@property
|
96 |
+
def no_prefix_space_tokens(self):
|
97 |
+
if self._no_prefix_space_tokens is None:
|
98 |
+
vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
|
99 |
+
self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
|
100 |
+
return self._no_prefix_space_tokens
|
101 |
+
|
102 |
+
@property
|
103 |
+
def vocab_size(self):
|
104 |
+
"""Returns vocab size"""
|
105 |
+
return self.sp_model.get_piece_size()
|
106 |
+
|
107 |
+
@property
|
108 |
+
def bos_token_id(self) -> Optional[int]:
|
109 |
+
return self.sp_model.bos_id()
|
110 |
+
|
111 |
+
@property
|
112 |
+
def eos_token_id(self) -> Optional[int]:
|
113 |
+
return self.sp_model.eos_id()
|
114 |
+
|
115 |
+
def get_vocab(self):
|
116 |
+
"""Returns vocab as a dict"""
|
117 |
+
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
|
118 |
+
vocab.update(self.added_tokens_encoder)
|
119 |
+
return vocab
|
120 |
+
|
121 |
+
def _tokenize(self, text):
|
122 |
+
"""Returns a tokenized string."""
|
123 |
+
|
124 |
+
splits = self.pre_tokenizer.pre_tokenize_str(text)
|
125 |
+
texts=[]
|
126 |
+
|
127 |
+
for split in splits:
|
128 |
+
texts.extend(self.sp_model.encode(split[0], out_type=str))
|
129 |
+
return texts
|
130 |
+
|
131 |
+
def _convert_token_to_id(self, token):
|
132 |
+
"""Converts a token (str) in an id using the vocab."""
|
133 |
+
|
134 |
+
return self.sp_model.piece_to_id(token)
|
135 |
+
|
136 |
+
def _convert_id_to_token(self, index):
|
137 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
138 |
+
token = self.sp_model.IdToPiece(index)
|
139 |
+
return token
|
140 |
+
|
141 |
+
def _maybe_add_prefix_space(self, tokens, decoded):
|
142 |
+
if tokens and tokens[0] not in self.no_prefix_space_tokens:
|
143 |
+
return " " + decoded
|
144 |
+
else:
|
145 |
+
return decoded
|
146 |
+
|
147 |
+
def convert_tokens_to_string(self, tokens):
|
148 |
+
"""Converts a sequence of tokens (string) in a single string."""
|
149 |
+
current_sub_tokens = []
|
150 |
+
out_string = ""
|
151 |
+
prev_is_special = False
|
152 |
+
for token in tokens:
|
153 |
+
# make sure that special tokens are not decoded using sentencepiece model
|
154 |
+
if token in self.all_special_tokens:
|
155 |
+
out_string += self.sp_model.decode(current_sub_tokens) + token
|
156 |
+
prev_is_special = True
|
157 |
+
current_sub_tokens = []
|
158 |
+
else:
|
159 |
+
current_sub_tokens.append(token)
|
160 |
+
prev_is_special = False
|
161 |
+
out_string += self.sp_model.decode(current_sub_tokens)
|
162 |
+
|
163 |
+
return out_string
|
164 |
+
|
165 |
+
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
166 |
+
"""
|
167 |
+
Save the vocabulary and special tokens file to a directory.
|
168 |
+
|
169 |
+
Args:
|
170 |
+
save_directory (`str`):
|
171 |
+
The directory in which to save the vocabulary.
|
172 |
+
|
173 |
+
Returns:
|
174 |
+
`Tuple(str)`: Paths to the files saved.
|
175 |
+
"""
|
176 |
+
if not os.path.isdir(save_directory):
|
177 |
+
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
|
178 |
+
return
|
179 |
+
out_vocab_file = os.path.join(
|
180 |
+
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
|
181 |
+
)
|
182 |
+
|
183 |
+
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
|
184 |
+
copyfile(self.vocab_file, out_vocab_file)
|
185 |
+
elif not os.path.isfile(self.vocab_file):
|
186 |
+
with open(out_vocab_file, "wb") as fi:
|
187 |
+
content_spiece_model = self.sp_model.serialized_model_proto()
|
188 |
+
fi.write(content_spiece_model)
|
189 |
+
|
190 |
+
return (out_vocab_file,)
|
191 |
+
|
192 |
+
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
193 |
+
if self.add_bos_token:
|
194 |
+
bos_token_ids = [self.bos_token_id]
|
195 |
+
else:
|
196 |
+
bos_token_ids = []
|
197 |
+
|
198 |
+
output = bos_token_ids + token_ids_0
|
199 |
+
|
200 |
+
if token_ids_1 is not None:
|
201 |
+
output = output + token_ids_1
|
202 |
+
|
203 |
+
if self.add_eos_token:
|
204 |
+
output = output + [self.eos_token_id]
|
205 |
+
|
206 |
+
return output
|
207 |
+
|
208 |
+
def get_special_tokens_mask(
|
209 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
|
210 |
+
) -> List[int]:
|
211 |
+
"""
|
212 |
+
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
|
213 |
+
special tokens using the tokenizer `prepare_for_model` method.
|
214 |
+
|
215 |
+
Args:
|
216 |
+
token_ids_0 (`List[int]`):
|
217 |
+
List of IDs.
|
218 |
+
token_ids_1 (`List[int]`, *optional*):
|
219 |
+
Optional second list of IDs for sequence pairs.
|
220 |
+
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
|
221 |
+
Whether or not the token list is already formatted with special tokens for the model.
|
222 |
+
|
223 |
+
Returns:
|
224 |
+
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
|
225 |
+
"""
|
226 |
+
if already_has_special_tokens:
|
227 |
+
return super().get_special_tokens_mask(
|
228 |
+
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
|
229 |
+
)
|
230 |
+
|
231 |
+
eos_token_id = [1] if self.add_eos_token else []
|
232 |
+
if token_ids_1 is None:
|
233 |
+
return ([0] * len(token_ids_0)) + eos_token_id
|
234 |
+
return ([0] * len(token_ids_0)) + eos_token_id + ([0] * len(token_ids_1)) + eos_token_id
|
235 |
+
|
236 |
+
|
237 |
+
def create_token_type_ids_from_sequences(
|
238 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
239 |
+
) -> List[int]:
|
240 |
+
"""
|
241 |
+
Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
|
242 |
+
sequence pair mask has the following format:
|
243 |
+
|
244 |
+
```
|
245 |
+
0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
|
246 |
+
| first sequence | second sequence |
|
247 |
+
```
|
248 |
+
|
249 |
+
if token_ids_1 is None, only returns the first portion of the mask (0s).
|
250 |
+
|
251 |
+
Note this is only used for back compatiblity, thus list of zero is returned.
|
252 |
+
|
253 |
+
Args:
|
254 |
+
token_ids_0 (`List[int]`):
|
255 |
+
List of ids.
|
256 |
+
token_ids_1 (`List[int]`, *optional*):
|
257 |
+
Optional second list of IDs for sequence pairs.
|
258 |
+
|
259 |
+
Returns:
|
260 |
+
`List[int]`: List of zeros.
|
261 |
+
"""
|
262 |
+
eos = [self.eos_token_id]
|
263 |
+
|
264 |
+
if token_ids_1 is None:
|
265 |
+
return len(token_ids_0 + eos) * [0]
|
266 |
+
return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
|
267 |
+
|
268 |
+
|
269 |
+
@property
|
270 |
+
def default_chat_template(self):
|
271 |
+
return None
|
272 |
+
|
273 |
+
|
274 |
+
def decode(
|
275 |
+
self,
|
276 |
+
token_ids,
|
277 |
+
skip_special_tokens: bool = False,
|
278 |
+
clean_up_tokenization_spaces: Optional[bool] = False,
|
279 |
+
spaces_between_special_tokens: bool = False,
|
280 |
+
**kwargs,
|
281 |
+
) -> str:
|
282 |
+
# default spaces_between_special_tokens should be false.
|
283 |
+
if spaces_between_special_tokens:
|
284 |
+
logger.warning_once('spaces_between_special_tokens is set. \
|
285 |
+
It has no effect for bos,eos,pad,unk when transformers<=4.38.')
|
286 |
+
return super().decode(
|
287 |
+
token_ids,
|
288 |
+
skip_special_tokens=skip_special_tokens,
|
289 |
+
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
290 |
+
spaces_between_special_tokens=spaces_between_special_tokens,
|
291 |
+
**kwargs,
|
292 |
+
)
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76d43d618fc0c5a7c79dc4e72579f9f29bb803b36e4a4d709d1233626fd8fe2a
|
3 |
+
size 1535725
|
tokenizer_config.json
ADDED
@@ -0,0 +1,394 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<unk>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<pad>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"96499": {
|
37 |
+
"content": "<|start|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"96500": {
|
45 |
+
"content": "<|end|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"96501": {
|
53 |
+
"content": "<|message|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"96502": {
|
61 |
+
"content": "<|tool_start|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"96503": {
|
69 |
+
"content": "<|tool_excute|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"96504": {
|
77 |
+
"content": "<|tool_end|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"96505": {
|
85 |
+
"content": "<|pad|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"96506": {
|
93 |
+
"content": "<|endoftext|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"96507": {
|
101 |
+
"content": "<fim_prefix>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"96508": {
|
109 |
+
"content": "<fim_middle>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"96509": {
|
117 |
+
"content": "<fim_suffix>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"96510": {
|
125 |
+
"content": "<repo_name>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"96511": {
|
133 |
+
"content": "<file_sep>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"96512": {
|
141 |
+
"content": "<issue_start>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"96513": {
|
149 |
+
"content": "<issue_comment>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"96514": {
|
157 |
+
"content": "<issue_closed>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"96515": {
|
165 |
+
"content": "<jupyter_start>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"96516": {
|
173 |
+
"content": "<jupyter_text>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"96517": {
|
181 |
+
"content": "<jupyter_code>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"96518": {
|
189 |
+
"content": "<jupyter_output>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"96519": {
|
197 |
+
"content": "<jupyter_script>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"96520": {
|
205 |
+
"content": "<empty_output>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"96521": {
|
213 |
+
"content": "<code_to_intermediate>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"96522": {
|
221 |
+
"content": "<intermediate_to_code>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"96523": {
|
229 |
+
"content": "<pr>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"96524": {
|
237 |
+
"content": "<pr_status>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"96525": {
|
245 |
+
"content": "<pr_is_merged>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"96526": {
|
253 |
+
"content": "<pr_base>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"96527": {
|
261 |
+
"content": "<pr_file>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"96528": {
|
269 |
+
"content": "<pr_base_code>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"96529": {
|
277 |
+
"content": "<pr_diff>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"96530": {
|
285 |
+
"content": "<pr_diff_hunk>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"96531": {
|
293 |
+
"content": "<pr_comment>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"96532": {
|
301 |
+
"content": "<pr_event_id>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"96533": {
|
309 |
+
"content": "<pr_review>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"96534": {
|
317 |
+
"content": "<pr_review_state>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"96535": {
|
325 |
+
"content": "<pr_review_comment>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"96536": {
|
333 |
+
"content": "<pr_in_reply_to_review_id>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"96537": {
|
341 |
+
"content": "<pr_in_reply_to_comment_id>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"96538": {
|
349 |
+
"content": "<pr_diff_hunk_comment_line>",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"96539": {
|
357 |
+
"content": "<|im_end|>",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": true
|
363 |
+
},
|
364 |
+
"96540": {
|
365 |
+
"content": "<|im_start|>",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": true
|
371 |
+
}
|
372 |
+
},
|
373 |
+
"additional_special_tokens": [
|
374 |
+
"<|im_end|>",
|
375 |
+
"<|im_start|>"
|
376 |
+
],
|
377 |
+
"auto_map": {
|
378 |
+
"AutoTokenizer": [
|
379 |
+
"tokenization_inflm.INFLMTokenizer",
|
380 |
+
null
|
381 |
+
]
|
382 |
+
},
|
383 |
+
"bos_token": "<|im_start|>",
|
384 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are OpenCoder, created by OpenCoder Team.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
385 |
+
"clean_up_tokenization_spaces": false,
|
386 |
+
"eos_token": "<|im_end|>",
|
387 |
+
"model_max_length": 1300,
|
388 |
+
"pad_token": "<pad>",
|
389 |
+
"padding_side": "right",
|
390 |
+
"return_tensors": true,
|
391 |
+
"spaces_between_special_tokens": false,
|
392 |
+
"tokenizer_class": "INFLMTokenizer",
|
393 |
+
"unk_token": "<unk>"
|
394 |
+
}
|