step 500
Browse files- config.json +5 -5
- generation_config.json +2 -2
- model-00001-of-00006.safetensors +2 -2
- model-00002-of-00006.safetensors +2 -2
- model-00003-of-00006.safetensors +2 -2
- model-00004-of-00006.safetensors +2 -2
- model-00005-of-00006.safetensors +2 -2
- model-00006-of-00006.safetensors +2 -2
- model.safetensors.index.json +1 -1
- special_tokens_map.json +13 -25
- tokenizer.json +0 -0
- tokenizer_config.json +18 -144
config.json
CHANGED
|
@@ -4,14 +4,14 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
-
"eos_token_id":
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 5120,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 17920,
|
| 14 |
-
"max_position_embeddings":
|
| 15 |
"mlp_bias": false,
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 40,
|
|
@@ -20,10 +20,10 @@
|
|
| 20 |
"pretraining_tp": 1,
|
| 21 |
"rms_norm_eps": 1e-05,
|
| 22 |
"rope_scaling": null,
|
| 23 |
-
"rope_theta":
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.46.1",
|
| 27 |
"use_cache": true,
|
| 28 |
-
"vocab_size":
|
| 29 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 5120,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 17920,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
"mlp_bias": false,
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 40,
|
|
|
|
| 20 |
"pretraining_tp": 1,
|
| 21 |
"rms_norm_eps": 1e-05,
|
| 22 |
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.46.1",
|
| 27 |
"use_cache": true,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
-
"eos_token_id":
|
| 5 |
"transformers_version": "4.46.1"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
"transformers_version": "4.46.1"
|
| 6 |
}
|
model-00001-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca6bf4b7cda1cf116d33ccbfca4f65703b9d03c60c9e3ed9971314995d73a807
|
| 3 |
+
size 5326916768
|
model-00002-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d7ec6bbe356f560d382628bdf57ff93a3b75a1df12fe8ab9e7f31d45f50c9f5
|
| 3 |
+
size 5358395480
|
model-00003-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ae2f40ab046d1218b876f1575b6c2f48ae59c5d4338c18ee1f3b39f77b372cf
|
| 3 |
+
size 5216827256
|
model-00004-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69aeabaeb2cabcc36536b00f8bbcd35797269d8abc0b51d3a97b76902c375d07
|
| 3 |
+
size 5227323488
|
model-00005-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a0895f9f63f0927591d2d5e9fd726c8fd7b87f5b9c67e738922c775ec2d6ffd
|
| 3 |
+
size 5227323488
|
model-00006-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c2b94ec6e27950829e7f0b0735f55002c574cd5be1aae7684089846a737434a
|
| 3 |
+
size 2705412160
|
model.safetensors.index.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"metadata":{"total_size":29413427200},"weight_map":{"lm_head.weight":"model-00001-of-00006.safetensors","model.embed_tokens.weight":"model-00001-of-00006.safetensors","model.layers.0.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.0.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.0.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.0.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.1.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.1.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.1.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.10.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.10.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.10.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.11.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.11.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.11.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.12.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.12.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.12.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.13.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.mlp.up_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.post_attention_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.13.self_attn.k_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.self_attn.o_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.self_attn.q_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.self_attn.v_proj.weight":"model-00001-of-00006.safetensors","model.layers.14.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.14.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.14.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.14.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.15.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.15.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.15.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.16.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.16.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.16.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.17.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.17.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.17.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.18.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.18.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.18.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.19.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.19.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.19.mlp.up_proj.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-00002-of-00006.safetensors","model.layers.19.self_attn.q_proj.weight":"model-00002-of-00006.safetensors","model.layers.19.self_attn.v_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.2.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.mlp.up_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.post_attention_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.2.self_attn.k_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.self_attn.o_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.self_attn.q_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.self_attn.v_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.20.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.mlp.up_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.post_attention_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.20.self_attn.k_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.self_attn.o_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.self_attn.q_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.self_attn.v_proj.weight":"model-00002-of-00006.safetensors","model.layers.21.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.21.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.21.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.21.mlp.up_proj.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.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.22.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.22.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.22.mlp.up_proj.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.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.23.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.23.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.23.mlp.up_proj.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.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.24.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.24.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.24.mlp.up_proj.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.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.25.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.mlp.up_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.post_attention_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.25.self_attn.k_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.self_attn.o_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.self_attn.q_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.self_attn.v_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.26.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.mlp.up_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.post_attention_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.26.self_attn.k_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.self_attn.o_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.self_attn.q_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.self_attn.v_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.27.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.mlp.up_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.post_attention_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.27.self_attn.k_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.self_attn.o_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.self_attn.q_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.self_attn.v_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.28.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.mlp.up_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.post_attention_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.28.self_attn.k_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.self_attn.o_proj.weight":"model-00003-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.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.29.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.29.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.29.mlp.up_proj.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.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.3.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.3.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.3.mlp.up_proj.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.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.30.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.30.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.31.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.31.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.32.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.32.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.33.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.33.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.34.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.34.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.35.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.35.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.35.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.35.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.36.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.36.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.37.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.37.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.38.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.38.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.39.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.39.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.4.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.4.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.4.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.4.mlp.up_proj.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.40.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.40.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.40.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.41.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.41.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.5.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.5.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.5.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.5.mlp.up_proj.weight":"model-00006-of-00006.safetensors","model.layers.5.post_attention_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.5.self_attn.k_proj.weight":"model-00006-of-00006.safetensors","model.layers.5.self_attn.o_proj.weight":"model-00006-of-00006.safetensors","model.layers.5.self_attn.q_proj.weight":"model-00006-of-00006.safetensors","model.layers.5.self_attn.v_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.input_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.6.mlp.down_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.mlp.gate_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.mlp.up_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.post_attention_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.6.self_attn.k_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.self_attn.o_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.self_attn.q_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.self_attn.v_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.input_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.7.mlp.down_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.mlp.gate_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.mlp.up_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.post_attention_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.7.self_attn.k_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.self_attn.o_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.self_attn.q_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.self_attn.v_proj.weight":"model-00006-of-00006.safetensors","model.layers.8.input_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.8.mlp.down_proj.weight":"model-00006-of-00006.safetensors","model.layers.8.mlp.gate_proj.weight":"model-00006-of-00006.safetensors","model.layers.8.mlp.up_proj.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.input_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.9.mlp.down_proj.weight":"model-00006-of-00006.safetensors","model.layers.9.mlp.gate_proj.weight":"model-00006-of-00006.safetensors","model.layers.9.mlp.up_proj.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"}}
|
|
|
|
| 1 |
+
{"metadata":{"total_size":29062154240},"weight_map":{"lm_head.weight":"model-00001-of-00006.safetensors","model.embed_tokens.weight":"model-00001-of-00006.safetensors","model.layers.0.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.0.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.0.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.0.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.1.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.1.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.1.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.10.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.10.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.10.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.11.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.11.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.11.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.12.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.12.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.12.mlp.up_proj.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.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.13.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.mlp.up_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.post_attention_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.13.self_attn.k_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.self_attn.o_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.self_attn.q_proj.weight":"model-00001-of-00006.safetensors","model.layers.13.self_attn.v_proj.weight":"model-00001-of-00006.safetensors","model.layers.14.input_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.14.mlp.down_proj.weight":"model-00001-of-00006.safetensors","model.layers.14.mlp.gate_proj.weight":"model-00001-of-00006.safetensors","model.layers.14.mlp.up_proj.weight":"model-00001-of-00006.safetensors","model.layers.14.post_attention_layernorm.weight":"model-00001-of-00006.safetensors","model.layers.14.self_attn.k_proj.weight":"model-00001-of-00006.safetensors","model.layers.14.self_attn.o_proj.weight":"model-00001-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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.15.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.15.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.15.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.16.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.16.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.16.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.17.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.17.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.17.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.18.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.18.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.18.mlp.up_proj.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.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.19.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.19.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.19.mlp.up_proj.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-00002-of-00006.safetensors","model.layers.19.self_attn.q_proj.weight":"model-00002-of-00006.safetensors","model.layers.19.self_attn.v_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.2.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.mlp.up_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.post_attention_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.2.self_attn.k_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.self_attn.o_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.self_attn.q_proj.weight":"model-00002-of-00006.safetensors","model.layers.2.self_attn.v_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.20.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.mlp.up_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.post_attention_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.20.self_attn.k_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.self_attn.o_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.self_attn.q_proj.weight":"model-00002-of-00006.safetensors","model.layers.20.self_attn.v_proj.weight":"model-00002-of-00006.safetensors","model.layers.21.input_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.21.mlp.down_proj.weight":"model-00002-of-00006.safetensors","model.layers.21.mlp.gate_proj.weight":"model-00002-of-00006.safetensors","model.layers.21.mlp.up_proj.weight":"model-00002-of-00006.safetensors","model.layers.21.post_attention_layernorm.weight":"model-00002-of-00006.safetensors","model.layers.21.self_attn.k_proj.weight":"model-00002-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.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.22.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.22.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.22.mlp.up_proj.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.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.23.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.23.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.23.mlp.up_proj.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.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.24.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.24.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.24.mlp.up_proj.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.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.25.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.mlp.up_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.post_attention_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.25.self_attn.k_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.self_attn.o_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.self_attn.q_proj.weight":"model-00003-of-00006.safetensors","model.layers.25.self_attn.v_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.26.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.mlp.up_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.post_attention_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.26.self_attn.k_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.self_attn.o_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.self_attn.q_proj.weight":"model-00003-of-00006.safetensors","model.layers.26.self_attn.v_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.27.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.mlp.up_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.post_attention_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.27.self_attn.k_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.self_attn.o_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.self_attn.q_proj.weight":"model-00003-of-00006.safetensors","model.layers.27.self_attn.v_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.28.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.mlp.up_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.post_attention_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.28.self_attn.k_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.self_attn.o_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.self_attn.q_proj.weight":"model-00003-of-00006.safetensors","model.layers.28.self_attn.v_proj.weight":"model-00003-of-00006.safetensors","model.layers.29.input_layernorm.weight":"model-00003-of-00006.safetensors","model.layers.29.mlp.down_proj.weight":"model-00003-of-00006.safetensors","model.layers.29.mlp.gate_proj.weight":"model-00003-of-00006.safetensors","model.layers.29.mlp.up_proj.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.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.3.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.3.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.3.mlp.up_proj.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.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.30.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.30.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.30.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.31.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.31.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.31.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.32.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.32.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.32.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.33.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.33.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.33.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.34.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.34.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.34.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.35.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.mlp.gate_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.mlp.up_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.post_attention_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.35.self_attn.k_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.self_attn.o_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.self_attn.q_proj.weight":"model-00004-of-00006.safetensors","model.layers.35.self_attn.v_proj.weight":"model-00004-of-00006.safetensors","model.layers.36.input_layernorm.weight":"model-00004-of-00006.safetensors","model.layers.36.mlp.down_proj.weight":"model-00004-of-00006.safetensors","model.layers.36.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.36.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.36.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.37.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.37.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.37.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.38.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.38.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.38.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.39.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.39.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.39.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.4.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.4.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.4.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.4.mlp.up_proj.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.40.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.40.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.40.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.40.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.41.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.mlp.up_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.post_attention_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.41.self_attn.k_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.self_attn.o_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.self_attn.q_proj.weight":"model-00005-of-00006.safetensors","model.layers.41.self_attn.v_proj.weight":"model-00005-of-00006.safetensors","model.layers.5.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.5.mlp.down_proj.weight":"model-00005-of-00006.safetensors","model.layers.5.mlp.gate_proj.weight":"model-00005-of-00006.safetensors","model.layers.5.mlp.up_proj.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.input_layernorm.weight":"model-00005-of-00006.safetensors","model.layers.6.mlp.down_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.mlp.gate_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.mlp.up_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.post_attention_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.6.self_attn.k_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.self_attn.o_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.self_attn.q_proj.weight":"model-00006-of-00006.safetensors","model.layers.6.self_attn.v_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.input_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.7.mlp.down_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.mlp.gate_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.mlp.up_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.post_attention_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.7.self_attn.k_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.self_attn.o_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.self_attn.q_proj.weight":"model-00006-of-00006.safetensors","model.layers.7.self_attn.v_proj.weight":"model-00006-of-00006.safetensors","model.layers.8.input_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.8.mlp.down_proj.weight":"model-00006-of-00006.safetensors","model.layers.8.mlp.gate_proj.weight":"model-00006-of-00006.safetensors","model.layers.8.mlp.up_proj.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.input_layernorm.weight":"model-00006-of-00006.safetensors","model.layers.9.mlp.down_proj.weight":"model-00006-of-00006.safetensors","model.layers.9.mlp.gate_proj.weight":"model-00006-of-00006.safetensors","model.layers.9.mlp.up_proj.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
CHANGED
|
@@ -1,41 +1,29 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|endoftext|>",
|
| 4 |
-
"<|im_start|>",
|
| 5 |
-
"<|im_end|>",
|
| 6 |
-
"<repo_name>",
|
| 7 |
-
"<reponame>",
|
| 8 |
-
"<file_sep>",
|
| 9 |
-
"<filename>",
|
| 10 |
-
"<gh_stars>",
|
| 11 |
-
"<issue_start>",
|
| 12 |
-
"<issue_comment>",
|
| 13 |
-
"<issue_closed>",
|
| 14 |
-
"<jupyter_start>",
|
| 15 |
-
"<jupyter_text>",
|
| 16 |
-
"<jupyter_code>",
|
| 17 |
-
"<jupyter_output>",
|
| 18 |
-
"<jupyter_script>",
|
| 19 |
-
"<empty_output>"
|
| 20 |
-
],
|
| 21 |
"bos_token": {
|
| 22 |
-
"content": "<
|
| 23 |
"lstrip": false,
|
| 24 |
-
"normalized":
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false
|
| 27 |
},
|
| 28 |
"eos_token": {
|
| 29 |
-
"content": "<
|
| 30 |
"lstrip": false,
|
| 31 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false
|
| 34 |
},
|
| 35 |
"unk_token": {
|
| 36 |
-
"content": "<
|
| 37 |
"lstrip": false,
|
| 38 |
-
"normalized":
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false
|
| 41 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,167 +1,41 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
-
"content": "<
|
| 6 |
"lstrip": false,
|
| 7 |
-
"normalized":
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
"1": {
|
| 13 |
-
"content": "<
|
| 14 |
"lstrip": false,
|
| 15 |
-
"normalized":
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
| 19 |
},
|
| 20 |
"2": {
|
| 21 |
-
"content": "<
|
| 22 |
"lstrip": false,
|
| 23 |
-
"normalized":
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"3": {
|
| 29 |
-
"content": "<repo_name>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"4": {
|
| 37 |
-
"content": "<reponame>",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"5": {
|
| 45 |
-
"content": "<file_sep>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": true
|
| 51 |
-
},
|
| 52 |
-
"6": {
|
| 53 |
-
"content": "<filename>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
"7": {
|
| 61 |
-
"content": "<gh_stars>",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": false,
|
| 64 |
-
"rstrip": false,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": true
|
| 67 |
-
},
|
| 68 |
-
"8": {
|
| 69 |
-
"content": "<issue_start>",
|
| 70 |
-
"lstrip": false,
|
| 71 |
-
"normalized": false,
|
| 72 |
-
"rstrip": false,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": true
|
| 75 |
-
},
|
| 76 |
-
"9": {
|
| 77 |
-
"content": "<issue_comment>",
|
| 78 |
-
"lstrip": false,
|
| 79 |
-
"normalized": false,
|
| 80 |
-
"rstrip": false,
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"special": true
|
| 83 |
-
},
|
| 84 |
-
"10": {
|
| 85 |
-
"content": "<issue_closed>",
|
| 86 |
-
"lstrip": false,
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"rstrip": false,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": true
|
| 91 |
-
},
|
| 92 |
-
"11": {
|
| 93 |
-
"content": "<jupyter_start>",
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"normalized": false,
|
| 96 |
-
"rstrip": false,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": true
|
| 99 |
-
},
|
| 100 |
-
"12": {
|
| 101 |
-
"content": "<jupyter_text>",
|
| 102 |
-
"lstrip": false,
|
| 103 |
-
"normalized": false,
|
| 104 |
-
"rstrip": false,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": true
|
| 107 |
-
},
|
| 108 |
-
"13": {
|
| 109 |
-
"content": "<jupyter_code>",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": false,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": true
|
| 115 |
-
},
|
| 116 |
-
"14": {
|
| 117 |
-
"content": "<jupyter_output>",
|
| 118 |
-
"lstrip": false,
|
| 119 |
-
"normalized": false,
|
| 120 |
-
"rstrip": false,
|
| 121 |
-
"single_word": false,
|
| 122 |
-
"special": true
|
| 123 |
-
},
|
| 124 |
-
"15": {
|
| 125 |
-
"content": "<jupyter_script>",
|
| 126 |
-
"lstrip": false,
|
| 127 |
-
"normalized": false,
|
| 128 |
-
"rstrip": false,
|
| 129 |
-
"single_word": false,
|
| 130 |
-
"special": true
|
| 131 |
-
},
|
| 132 |
-
"16": {
|
| 133 |
-
"content": "<empty_output>",
|
| 134 |
-
"lstrip": false,
|
| 135 |
-
"normalized": false,
|
| 136 |
"rstrip": false,
|
| 137 |
"single_word": false,
|
| 138 |
"special": true
|
| 139 |
}
|
| 140 |
},
|
| 141 |
-
"
|
| 142 |
-
"<|endoftext|>",
|
| 143 |
-
"<|im_start|>",
|
| 144 |
-
"<|im_end|>",
|
| 145 |
-
"<repo_name>",
|
| 146 |
-
"<reponame>",
|
| 147 |
-
"<file_sep>",
|
| 148 |
-
"<filename>",
|
| 149 |
-
"<gh_stars>",
|
| 150 |
-
"<issue_start>",
|
| 151 |
-
"<issue_comment>",
|
| 152 |
-
"<issue_closed>",
|
| 153 |
-
"<jupyter_start>",
|
| 154 |
-
"<jupyter_text>",
|
| 155 |
-
"<jupyter_code>",
|
| 156 |
-
"<jupyter_output>",
|
| 157 |
-
"<jupyter_script>",
|
| 158 |
-
"<empty_output>"
|
| 159 |
-
],
|
| 160 |
-
"bos_token": "<|endoftext|>",
|
| 161 |
"clean_up_tokenization_spaces": false,
|
| 162 |
-
"eos_token": "<
|
| 163 |
-
"
|
| 164 |
-
"
|
| 165 |
-
"
|
| 166 |
-
"
|
|
|
|
|
|
|
|
|
|
| 167 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false,
|
| 20 |
"special": true
|
| 21 |
},
|
| 22 |
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
| 29 |
}
|
| 30 |
},
|
| 31 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "<unk>",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
+
"unk_token": "<unk>",
|
| 40 |
+
"use_default_system_prompt": false
|
| 41 |
}
|