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 +1,42 @@
+---
+base_model:
+- Gryphe/Codex-24B-Small-3.2
+- mrfakename/mistral-small-3.1-24b-base-2503-hf
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- mergekit
+- merge
+license: apache-2.0
+---
+# demi-Codex-24B-Small-3.2b
+
+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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Gryphe/Codex-24B-Small-3.2](https://huggingface.co/Gryphe/Codex-24B-Small-3.2)
+* [mrfakename/mistral-small-3.1-24b-base-2503-hf](https://huggingface.co/mrfakename/mistral-small-3.1-24b-base-2503-hf)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: mrfakename/mistral-small-3.1-24b-base-2503-hf
+  - model: Gryphe/Codex-24B-Small-3.2
+merge_method: slerp
+base_model: mrfakename/mistral-small-3.1-24b-base-2503-hf
+parameters:
+  t:
+   - value: 0.5
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+models:
+  - model: mrfakename/mistral-small-3.1-24b-base-2503-hf
+  - model: Gryphe/Codex-24B-Small-3.2
+merge_method: slerp
+base_model: mrfakename/mistral-small-3.1-24b-base-2503-hf
+parameters:
+  t:
+   - value: 0.5
+dtype: bfloat16

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd974a0a74f54fb0e53f0d09e4e547daa1f26dadf78caf6ef2a8425a467ca885
+size 4907389312

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250df649547c6ae1cd7076d1ac0617185bd94079530a2c9e0f255a4fdd6909f4
+size 4781592832

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db33e1ea1e838c3c175e435c1083b4bc1cff6239633c4a84532a9157b492643
+size 4781592816

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e192422134497649e3d3def6b7c94b1753d45da589693409564115d89ea3050
+size 4886471592

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2719fc4ca3702b2a661f767b2f8be4cea48d5b3a96201d471cd46963bb518262
+size 4781592832

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a012c0a53f4ba328fd35a871a34e88a236d588bccc7294980fa260a266fae19a
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad410bf6a320a723d4e5f573841a3316b60ffc9fb9cfe309ba73bddfdddb5b2
+size 4886471592

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3976402f95ead8853507d043fac61c7e480d7e5b1bbd09fbb6dc30f9de34ce
+size 4781592832

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa5a56324e66e5a54ca751657c548a7d7cfe6d4f2b9c0425d69f6b0417e6119
+size 4781592800

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55cafa7addaf6cf5bbefc36154ca24ebd3ea2b14e32ee5bfb3767efa68c569ab
+size 3774959456

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors"}}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037