Upload folder using huggingface_hub

README.md

@@ -0,0 +1,22 @@
+---
+license: apache-2.0
+tags:
+- mergekit
+- lazymergekit
+- jiayihao03/mistral-7b-instruct-Javascript-4bit
+- akameswa/mistral-7b-instruct-java-4bit
+- akameswa/mistral-7b-instruct-go-4bit
+- jiayihao03/mistral-7b-instruct-python-4bit
+---
+
+# mixtral-4x7b-instruct-code
+
+mixtral-4x7b-instruct-code is a MoE of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [jiayihao03/mistral-7b-instruct-Javascript-4bit](https://huggingface.co/jiayihao03/mistral-7b-instruct-Javascript-4bit)
+* [akameswa/mistral-7b-instruct-java-4bit](https://huggingface.co/akameswa/mistral-7b-instruct-java-4bit)
+* [akameswa/mistral-7b-instruct-go-4bit](https://huggingface.co/akameswa/mistral-7b-instruct-go-4bit)
+* [jiayihao03/mistral-7b-instruct-python-4bit](https://huggingface.co/jiayihao03/mistral-7b-instruct-python-4bit)
+
+## 🧩 Configuration
+
+```yaml```

config.json

@@ -0,0 +1,43 @@
+{
+ "_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
+ "architectures": [
+ "MixtralForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 14336,
+ "max_position_embeddings": 32768,
+ "model_type": "mixtral",
+ "num_attention_heads": 32,
+ "num_experts_per_tok": 2,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 8,
+ "num_local_experts": 4,
+ "output_router_logits": false,
+ "pad_token_id": 0,
+ "quantization_config": {
+ "bnb_4bit_compute_dtype": "bfloat16",
+ "bnb_4bit_quant_type": "nf4",
+ "bnb_4bit_use_double_quant": true,
+ "llm_int8_enable_fp32_cpu_offload": false,
+ "llm_int8_has_fp16_weight": false,
+ "llm_int8_skip_modules": null,
+ "llm_int8_threshold": 6.0,
+ "load_in_4bit": true,
+ "load_in_8bit": false,
+ "quant_method": "bitsandbytes"
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "router_aux_loss_coef": 0.001,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.39.3",
+ "use_cache": true,
+ "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,13 @@
+
+base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
+gate_mode: hidden
+dtype: float16
+experts:
+ - source_model: jiayihao03/mistral-7b-instruct-Javascript-4bit
+ positive_prompts: ["You are helpful a coding assistant good at javascript"]
+ - source_model: akameswa/mistral-7b-instruct-java-4bit
+ positive_prompts: ["You are helpful a coding assistant good at java"]
+ - source_model: akameswa/mistral-7b-instruct-go-4bit
+ positive_prompts: ["You are helpful a coding assistant good at go"]
+ - source_model: jiayihao03/mistral-7b-instruct-python-4bit
+ positive_prompts: ["You are helpful a coding assistant good at python"]

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909ba72d51db44cf082d9d63890d4c3bf203bbe8b664ba8278d9ac8239cebca6
+size 1992571808

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a78a4aaf97a1fa638cd545087ffac736600a8fd07cb4c85a24456f36d94fda
+size 1996493144

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f432a1d0b037795689bda9c78b018aecb147e554c6c7705cd73bed9470c282c1
+size 1996493160

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008ea263ef33bf36084fbd1c2858966dac7aa7117dec53b5f5d3c548cc3b14cd
+size 1996493160

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4688feec0d64010da25a697adfed7311db211fe2b44293ea9f4e796c6d31d3eb
+size 1996493120

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239c55ce9e0ad8d590ab43a8f70fc73857a18db5ade7fab44b08957c944ba909
+size 1996493152

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffca63a92e859bb5db451464db467bb18472e3508d814d7d6e6268fad185ebe
+size 1996493160

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c85bc8fa8a336c3cd4b9980da48f7d055d88849867fde6ab4790063d644fd931
+size 1996493152

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4566e303fe43fcd8f675690fb27878ba003c43d5bcdccad9c9721da7cbaa526
+size 1996493120

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771e27bb9dec4fcc4741d3eca0f89641b15987412cf87a292e22950babea34b1
+size 1996493160

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7200259c429214be6456ddc1a1de334bf2be456a139cd032e34f3d2b74f8194
+size 1996493160

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea84b782668d673a7a0f55f26d6b95a4253883026da81c146fde33f68e575d40
+size 1988380032

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce48445bd81cb2d4e51bc0b42a43e475ef5b2b5248b7cf862d31bb8f12bb7676
+size 470817560

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.norm.weight": "model-00001-of-00013.safetensors", "lm_head.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<s>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [],
+ "bos_token": "<s>",
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": true,
+ "model_max_length": 32768,
+ "pad_token": "<s>",
+ "padding_side": "left",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": false
+}