Upload folder using huggingface_hub
Browse files- added_tokens.json +4 -0
- config.json +31 -0
- mergekit_moe_config.yml +9 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +62 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 32000,
|
| 3 |
+
"<|im_start|>": 32001
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 32000,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"model_type": "mixtral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_experts_per_tok": 2,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"num_local_experts": 2,
|
| 20 |
+
"output_router_logits": false,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"router_aux_loss_coef": 0.001,
|
| 24 |
+
"router_jitter_noise": 0.0,
|
| 25 |
+
"sliding_window": null,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 32002
|
| 31 |
+
}
|
mergekit_moe_config.yml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
base_model: teknium/OpenHermes-2.5-Mistral-7B
|
| 3 |
+
dtype: float16
|
| 4 |
+
gate_mode: cheap_embed
|
| 5 |
+
experts:
|
| 6 |
+
- source_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
| 7 |
+
positive_prompts: ["You are a helpful text summarization assistant."]
|
| 8 |
+
- source_model: HuggingFaceH4/zephyr-7b-beta
|
| 9 |
+
positive_prompts: ["You are assistant for question answering from text."]
|
model-00001-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a791ab051c0972a6625d0c5db8b2f40c9c8127840e1b3cb964be696725fee17
|
| 3 |
+
size 1992603536
|
model-00002-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9253b7fef3079b5eec14eff305292beabeec5f543c0231cf9028ee89df0066d4
|
| 3 |
+
size 1937771336
|
model-00003-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62bea8fc83c9cab2a98a2197638c928843f52855112bdf136366a03a16817a6b
|
| 3 |
+
size 1937771344
|
model-00004-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0cd31da26009e631a49b667516df4fe44bac6a627f14f5bd57c96f0b80879b2
|
| 3 |
+
size 1937771320
|
model-00005-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9cd131530c4a11f0d40c7f82d7c3204cd0a7680162a47001154d00235f18f0f
|
| 3 |
+
size 1937771336
|
model-00006-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ba100942afe52df43aee699c95e13f61ed5dbba4106f2abbd89c336bae67e93
|
| 3 |
+
size 1937771344
|
model-00007-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f8e3f53aa3fff82f24d60af9ab1a657e0be97a445775c21e0872bbb04a44433
|
| 3 |
+
size 1937771320
|
model-00008-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76f347dccf669aec5ae9a149bb9ef8e6ecc917f4225cccc8287dc5d54480ed24
|
| 3 |
+
size 1937771344
|
model-00009-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b2c58eb0a3740ef7a9f962054a6c4654b4cf271ee5949f0601225c380e03c7f
|
| 3 |
+
size 1979980496
|
model-00010-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a9ba5957af741769791575275e4a2dc3487b6822d6f5aaadec2b35382bf3bd
|
| 3 |
+
size 1979723880
|
model-00011-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b60be49d20af72c07dc7217061fcb9aa22aaf891dd4763dce8af96d8cce21dee
|
| 3 |
+
size 604509840
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.norm.weight": "model-00001-of-00011.safetensors", "lm_head.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors"}}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"32000": {
|
| 31 |
+
"content": "<|im_end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|im_start|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"additional_special_tokens": [],
|
| 48 |
+
"bos_token": "<s>",
|
| 49 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 50 |
+
"clean_up_tokenization_spaces": false,
|
| 51 |
+
"eos_token": "<|im_end|>",
|
| 52 |
+
"legacy": true,
|
| 53 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 54 |
+
"pad_token": "<s>",
|
| 55 |
+
"sp_model_kwargs": {},
|
| 56 |
+
"spaces_between_special_tokens": false,
|
| 57 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 58 |
+
"trust_remote_code": false,
|
| 59 |
+
"unk_token": "<unk>",
|
| 60 |
+
"use_default_system_prompt": true,
|
| 61 |
+
"use_fast": true
|
| 62 |
+
}
|