TroyDoesAI commited on
Commit
6ec6891
1 Parent(s): 2bd8e76

Pruned poor performing layers using my pruning method and the support of Team SBFG.

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bullerwins/Codestral-22B-v0.1-hf",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 6144,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 48,
16
+ "num_hidden_layers": 54,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.41.1",
24
+ "use_cache": true,
25
+ "vocab_size": 32768
26
+ }
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67844520aeb9aaae12b7eabed90e9ec97ab3babb5b6700ec2ca0f25ba475a51
3
+ size 4907476488
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60677d373c3f8b155ba5194dea6068124c14ac29587d32ad1c5593f0bc2cc191
3
+ size 4882323688
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25284420d075552a0d29b81ae3e91103c9713e827eca5fa4febf1915eb60337f
3
+ size 4970416696
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17259ef5be7112fb620234eef10a4c7e5d89f167295f70eeda521db783b9421c
3
+ size 4970416688
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35674044109fc331091216ecb2063e18fe6d349ca12c78026537f534c7d796cc
3
+ size 4882323696
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8641a6853305afeb8587b233098bfe5922f3f8559a163ca5c6e87a2a9c45eb6c
3
+ size 4970416704
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210b46b6b12c84c1f3425dc30090e5b67c7d5207ca36da8d8c30adf52c57a223
3
+ size 4970416696
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc21fb9ee7110e1b948f333dbbab23595f3e353a6ac06f6dd72b5513765b0a8
3
+ size 4882323680
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f9449fd59c15fa206a813cc75740c3d8fefaa12e01f5184ca72d0e6e2e413dc
3
+ size 3498177352
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 42934235136}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.51.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.52.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.53.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
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": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }