Upload model
Browse files- config.json +31 -0
- generation_config.json +6 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +53 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/model2",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 2,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"router_jitter_noise": 0.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.42.4",
|
29 |
+
"use_cache": false,
|
30 |
+
"vocab_size": 32000
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f36d44444b8ad92e13e6da7c27213ffa4bd3da4a9f53ebc0df3152b1427a616
|
3 |
+
size 4936868456
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b129314e7d144f1ec2366b0b5c1112f45922ce4978b4abb484e3ecdf213c770
|
3 |
+
size 4974684360
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bd6fdf375d8f967f3a7ce88753a68d7304ad5ebe85670192d8de9b48da57436
|
3 |
+
size 4924319672
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08aa3e1bcb0cb2924e7330253ed35935ca73adb7e54a5fd1e80a31577fedcd51
|
3 |
+
size 4966262504
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55edf89b9db80d1cee9531419d42b0178747c78f8424f6eaadd6595f367e9881
|
3 |
+
size 4966262456
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4152b4569b1bf2a6c475ae9a22a4d966795e6fab886b9468314c3ff0b1d6f54e
|
3 |
+
size 989932104
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 25758277632}, "weight_map": {"lm_head.weight": "model-00001-of-00006.safetensors", "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "<s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"clean_up_tokenization_spaces": false,
|
37 |
+
"eos_token": "</s>",
|
38 |
+
"legacy": true,
|
39 |
+
"max_length": null,
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_to_multiple_of": null,
|
42 |
+
"pad_token": "<s>",
|
43 |
+
"pad_token_type_id": 0,
|
44 |
+
"padding_side": "left",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"stride": 0,
|
48 |
+
"tokenizer_class": "LlamaTokenizer",
|
49 |
+
"truncation_side": "right",
|
50 |
+
"truncation_strategy": "longest_first",
|
51 |
+
"unk_token": "<unk>",
|
52 |
+
"use_default_system_prompt": true
|
53 |
+
}
|