Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+base_model:
+- Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# nemo-asstr
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the Passthrough merge method using [Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML](https://huggingface.co/Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML) + /home/mango/Trainers/unsloth/outputs-pretrain/checkpoint-1053 as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML+/home/mango/Trainers/unsloth/outputs-pretrain/checkpoint-1053
+dtype: bfloat16
+merge_method: passthrough
+models:
+  - model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML+/home/mango/Trainers/unsloth/outputs-pretrain/checkpoint-1053
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML",
+  "activation": "silu",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11520,
+  "max_position_embeddings": 8192,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,5 @@
+base_model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML+/home/mango/Trainers/unsloth/outputs-pretrain/checkpoint-1053
+dtype: bfloat16
+merge_method: passthrough
+models:
+  - model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML+/home/mango/Trainers/unsloth/outputs-pretrain/checkpoint-1053

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0139343f172a968beceb467536f1b3647c4eccfb6c52929f6ef80e0747039c01
+size 4947320904

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8a010a1a78cd7ed317ff2ffe9eadf94763ef1d1e4cdcc41064a4b2ee1a0dc4
+size 4968380080

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e4952a6a3ad0c37acdd570a0545fa3c2c5a1860ec98d6364aa57b275217044
+size 4907570952

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abc18bb5ad5f05560fbc47e281c85c20fadcc51587225337651da97eb49eb11
+size 2004981488

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "lm_head.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c323e23875139dce13b6e6eeb3c31e2f1d259d590cee328ba4793bd8b053cc
+size 17078334