Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/config-checkpoint.json +35 -0
- config.json +35 -0
- mergekit_moe_config.yml +194 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +34 -0
- tokenizer.json +0 -0
- tokenizer_config.json +91 -0
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MrezaPRZ/codellama_high_quality_sft",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "mixtral",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_experts_per_tok": 2,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"num_key_value_heads": 32,
|
21 |
+
"num_local_experts": 3,
|
22 |
+
"output_router_logits": false,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 1000000,
|
27 |
+
"router_aux_loss_coef": 0.001,
|
28 |
+
"router_jitter_noise": 0.0,
|
29 |
+
"sliding_window": null,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.41.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 32016
|
35 |
+
}
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MrezaPRZ/codellama_high_quality_sft",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "mixtral",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_experts_per_tok": 2,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"num_key_value_heads": 32,
|
21 |
+
"num_local_experts": 3,
|
22 |
+
"output_router_logits": false,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 1000000,
|
27 |
+
"router_aux_loss_coef": 0.001,
|
28 |
+
"router_jitter_noise": 0.0,
|
29 |
+
"sliding_window": null,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.41.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 32016
|
35 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
base_model: MrezaPRZ/codellama_high_quality_sft
|
3 |
+
dtype: bfloat16
|
4 |
+
gate_mode: hidden
|
5 |
+
experts:
|
6 |
+
- source_model: MrezaPRZ/codellama_high_quality_sft
|
7 |
+
positive_prompts:
|
8 |
+
- "sqlite"
|
9 |
+
- "AUTOINCREMENT"
|
10 |
+
- "CONFLICT"
|
11 |
+
- "WITHOUT ROWID"
|
12 |
+
- "EXPLAIN"
|
13 |
+
- "PRAGMA"
|
14 |
+
- "RECURSIVE"
|
15 |
+
- "RAISE"
|
16 |
+
- "VIRTUAL"
|
17 |
+
- "TEMPORARY"
|
18 |
+
- "REGEXP"
|
19 |
+
- "sqlite_version()"
|
20 |
+
- "changes()"
|
21 |
+
- "last_insert_rowid()"
|
22 |
+
- "total_changes()"
|
23 |
+
- "random()"
|
24 |
+
- "ifnull()"
|
25 |
+
- "nullif()"
|
26 |
+
- "sqlite_compileoption_used()"
|
27 |
+
- "sqlite_compileoption_get()"
|
28 |
+
- "sqlite_source_id()"
|
29 |
+
- "sqlite_log()"
|
30 |
+
- "sqlite3_limit()"
|
31 |
+
- "json()"
|
32 |
+
- "json_array()"
|
33 |
+
- "json_array_length()"
|
34 |
+
- "json_extract()"
|
35 |
+
- "json_insert()"
|
36 |
+
- "json_object()"
|
37 |
+
- "json_patch()"
|
38 |
+
- "json_remove()"
|
39 |
+
- "json_replace()"
|
40 |
+
- "json_set()"
|
41 |
+
- "json_type()"
|
42 |
+
- "json_valid()"
|
43 |
+
- "fts3()"
|
44 |
+
- "fts4()"
|
45 |
+
- "fts5()"
|
46 |
+
- "printf()"
|
47 |
+
- "soundex()"
|
48 |
+
- "typeof()"
|
49 |
+
- source_model: MrezaPRZ/codellama_high_quality_sft_postgres
|
50 |
+
positive_prompts:
|
51 |
+
- "postgres"
|
52 |
+
- "DO"
|
53 |
+
- "RETURNING"
|
54 |
+
- "TABLESAMPLE"
|
55 |
+
- "WITH ORDINALITY"
|
56 |
+
- "SERIAL"
|
57 |
+
- "BIGSERIAL"
|
58 |
+
- "SMALLSERIAL"
|
59 |
+
- "TSQUERY"
|
60 |
+
- "TSVECTOR"
|
61 |
+
- "JSONB"
|
62 |
+
- "GIN"
|
63 |
+
- "GIST"
|
64 |
+
- "REGCLASS"
|
65 |
+
- "HSTORE"
|
66 |
+
- "LATERAL"
|
67 |
+
- "UNLOGGED"
|
68 |
+
- "CTID"
|
69 |
+
- "XMIN"
|
70 |
+
- "XMAX"
|
71 |
+
- "CUBE"
|
72 |
+
- "RANGE"
|
73 |
+
- "TO_TSVECTOR()"
|
74 |
+
- "TO_TSQUERY()"
|
75 |
+
- "PLPGSQL()"
|
76 |
+
- "TS_RANK()"
|
77 |
+
- "TS_RANK_CD()"
|
78 |
+
- "WEBSEARCH_TO_TSQUERY()"
|
79 |
+
- "SETWEIGHT()"
|
80 |
+
- "ARRAY_TO_STRING()"
|
81 |
+
- "STRING_TO_ARRAY()"
|
82 |
+
- "ARRAY_APPEND()"
|
83 |
+
- "ARRAY_PREPEND()"
|
84 |
+
- "ARRAY_REMOVE()"
|
85 |
+
- "ARRAY_REPLACE()"
|
86 |
+
- "STRING_AGG()"
|
87 |
+
- "JSON_BUILD_OBJECT()"
|
88 |
+
- "JSONB_BUILD_OBJECT()"
|
89 |
+
- "JSONB_SET()"
|
90 |
+
- "JSONB_INSERT()"
|
91 |
+
- "JSONB_PRETTY()"
|
92 |
+
- "TO_JSON()"
|
93 |
+
- "TO_JSONB()"
|
94 |
+
- "JSON_OBJECT()"
|
95 |
+
- "JSONB_OBJECT()"
|
96 |
+
- "JSON_AGG()"
|
97 |
+
- "JSONB_AGG()"
|
98 |
+
- "ROW_TO_JSON()"
|
99 |
+
- "XMLEXISTS()"
|
100 |
+
- "XMLCONCAT()"
|
101 |
+
- "XMLFOREST()"
|
102 |
+
- "XMLPARSE()"
|
103 |
+
- "XMLPI()"
|
104 |
+
- "XMLROOT()"
|
105 |
+
- "XMLSERIALIZE()"
|
106 |
+
- "PLV8()"
|
107 |
+
- "HSTORE()"
|
108 |
+
- "LQUERY()"
|
109 |
+
- "LTREE()"
|
110 |
+
- "LTXTQUERY()"
|
111 |
+
- source_model: MrezaPRZ/codellama_high_quality_sft_bigquery
|
112 |
+
positive_prompts:
|
113 |
+
- "bigquery"
|
114 |
+
- "ARRAY"
|
115 |
+
- "STRUCT"
|
116 |
+
- "UNNEST"
|
117 |
+
- "WITHIN"
|
118 |
+
- "QUALIFY"
|
119 |
+
- "WINDOW"
|
120 |
+
- "OVER"
|
121 |
+
- "ANY_VALUE"
|
122 |
+
- "APPROX_COUNT_DISTINCT"
|
123 |
+
- "APPROX_QUANTILES"
|
124 |
+
- "APPROX_TOP_COUNT"
|
125 |
+
- "ARRAY_AGG"
|
126 |
+
- "ARRAY_CONCAT_AGG"
|
127 |
+
- "ARRAY_LENGTH"
|
128 |
+
- "ARRAY_TO_STRING"
|
129 |
+
- "SAFE_CAST"
|
130 |
+
- "SAFE_DIVIDE"
|
131 |
+
- "SAFE_MULTIPLY"
|
132 |
+
- "SAFE_OFFSET"
|
133 |
+
- "SAFE_ORDINAL"
|
134 |
+
- "BIT_XOR"
|
135 |
+
- "CORR"
|
136 |
+
- "COVAR_POP"
|
137 |
+
- "COVAR_SAMP"
|
138 |
+
- "CUME_DIST"
|
139 |
+
- "DENSE_RANK"
|
140 |
+
- "DISTINCT"
|
141 |
+
- "FIRST_VALUE"
|
142 |
+
- "LAG"
|
143 |
+
- "LAST_VALUE"
|
144 |
+
- "LEAD"
|
145 |
+
- "NTH_VALUE"
|
146 |
+
- "NTILE"
|
147 |
+
- "PERCENT_RANK"
|
148 |
+
- "PERCENTILE_CONT"
|
149 |
+
- "PERCENTILE_DISC"
|
150 |
+
- "RANK"
|
151 |
+
- "RATIO_TO_REPORT"
|
152 |
+
- "REGR_INTERCEPT"
|
153 |
+
- "REGR_SLOPE"
|
154 |
+
- "ST_GEOGPOINT"
|
155 |
+
- "ST_GEOGFROMTEXT"
|
156 |
+
- "ST_GEOGFROMWKB"
|
157 |
+
- "ST_ASGEOJSON"
|
158 |
+
- "ST_ASTEXT"
|
159 |
+
- "ST_DISTANCE"
|
160 |
+
- "ST_INTERSECTS"
|
161 |
+
- "ST_UNION_AGG"
|
162 |
+
- "TIMESTAMP_TRUNC"
|
163 |
+
- "TIMESTAMP_DIFF"
|
164 |
+
- "TIMESTAMP_SUB"
|
165 |
+
- "TIMESTAMP_ADD"
|
166 |
+
- "TIMESTAMP_SECONDS"
|
167 |
+
- "TIMESTAMP_MILLIS"
|
168 |
+
- "TIMESTAMP_MICROS"
|
169 |
+
- "UNNEST"
|
170 |
+
- "ARRAY()"
|
171 |
+
- "ARRAY_AGG()"
|
172 |
+
- "ARRAY_TO_STRING()"
|
173 |
+
- "STRUCT()"
|
174 |
+
- "SAFE_CAST()"
|
175 |
+
- "SAFE_DIVIDE()"
|
176 |
+
- "SAFE_MULTIPLY()"
|
177 |
+
- "SAFE_OFFSET()"
|
178 |
+
- "SAFE_ORDINAL()"
|
179 |
+
- "BIT_XOR()"
|
180 |
+
- "ST_GEOGPOINT()"
|
181 |
+
- "ST_GEOGFROMTEXT()"
|
182 |
+
- "ST_GEOGFROMWKB()"
|
183 |
+
- "ST_ASGEOJSON()"
|
184 |
+
- "ST_ASTEXT()"
|
185 |
+
- "ST_DISTANCE()"
|
186 |
+
- "ST_INTERSECTS()"
|
187 |
+
- "ST_UNION_AGG()"
|
188 |
+
- "TIMESTAMP_TRUNC()"
|
189 |
+
- "TIMESTAMP_DIFF()"
|
190 |
+
- "TIMESTAMP_SUB()"
|
191 |
+
- "TIMESTAMP_ADD()"
|
192 |
+
- "TIMESTAMP_SECONDS()"
|
193 |
+
- "TIMESTAMP_MILLIS()"
|
194 |
+
- "TIMESTAMP_MICROS()"
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f896ea5904784540cc2a23cce886e2ef438ff34ac8741d853c34a57def2cf67
|
3 |
+
size 9945025816
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1cc139e694f3413ad4752adb605e8a470282eaf1a4622e0d31cf8596923705e
|
3 |
+
size 9999404312
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f637084c897c50c393726e0219b19dbeef25a9b39ae202f205760cefcd625a7a
|
3 |
+
size 9953283784
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72c8640b26c8f39a2a5dafdd35d8a6a01e1c1803b7b42ed4fcfc682105d56905
|
3 |
+
size 894317344
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 30791966720}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>",
|
7 |
+
"β<PRE>",
|
8 |
+
"β<MID>",
|
9 |
+
"β<SUF>",
|
10 |
+
"β<EOT>"
|
11 |
+
],
|
12 |
+
"bos_token": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"pad_token": "<s>",
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32007": {
|
30 |
+
"content": "β<PRE>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32008": {
|
38 |
+
"content": "β<SUF>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32009": {
|
46 |
+
"content": "β<MID>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32010": {
|
54 |
+
"content": "β<EOT>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"additional_special_tokens": [
|
63 |
+
"β<PRE>",
|
64 |
+
"β<MID>",
|
65 |
+
"β<SUF>",
|
66 |
+
"β<EOT>",
|
67 |
+
"β<PRE>",
|
68 |
+
"β<MID>",
|
69 |
+
"β<SUF>",
|
70 |
+
"β<EOT>"
|
71 |
+
],
|
72 |
+
"bos_token": "<s>",
|
73 |
+
"clean_up_tokenization_spaces": false,
|
74 |
+
"eos_token": "</s>",
|
75 |
+
"eot_token": "β<EOT>",
|
76 |
+
"fill_token": "<FILL_ME>",
|
77 |
+
"legacy": null,
|
78 |
+
"max_length": 1978,
|
79 |
+
"middle_token": "β<MID>",
|
80 |
+
"model_max_length": 1000000000000000019884624838656,
|
81 |
+
"pad_token": "<s>",
|
82 |
+
"prefix_token": "β<PRE>",
|
83 |
+
"sp_model_kwargs": {},
|
84 |
+
"stride": 0,
|
85 |
+
"suffix_token": "β<SUF>",
|
86 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
87 |
+
"truncation_side": "right",
|
88 |
+
"truncation_strategy": "longest_first",
|
89 |
+
"unk_token": "<unk>",
|
90 |
+
"use_default_system_prompt": false
|
91 |
+
}
|