Vikras: add HCT/YeAM Vikhr-NemoGemma-12B_plus_1B release + GGUF Q6

- Add GGUF quantizations:
- Vikhr-NemoGemma-12B_plus_1B Q6_K
- Smoke-tested llama.cpp inference for 12+1B GGUF Q6_0 model via llama-server (passed)

.gitattributes

@@ -39,3 +39,4 @@ Vikra-HCT-YeAM-LLaGemma-1B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Vikra-HCT-YeAM-LLaGemma-1B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Vikra-HCT-YeAM-PhiMma-1B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Vikra-HCT-YeAM-PhiMma-1B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4602a441fbf8196b67d81a195f23cd967449f7e8b7451daf92384955c3a8b5
+size 8727647264

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+base_model:
+- mistralai/Mistral-Nemo-Instruct-2407
+language:
+- en
+- ru
+---
+
+# Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B
+
+HCT architecture release. YeAM (Yet Another Merge) implementation invariant.
+
+## What it is
+
+A large (12B-class) checkpoint produced via HCT-compatible merging with 1B Gemma.
+Published in standard Hugging Face format (safetensors + sharded index) and intended to be convertible to GGUF.
+
+## YeAM summary
+
+YeAM performs a controlled merge in a real 4D geometric formulation with ray-intersection alignment in parameter space.
+It also supports targeted knowledge injection (distillation-style) into a chosen model while remaining HF-compatible.
+
+## Usage (Transformers)
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+m = "/path/to/Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B"
+
+tok = AutoTokenizer.from_pretrained(m, use_fast=False)
+model = AutoModelForCausalLM.from_pretrained(
+    m,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+).eval()
+
+inputs = tok("Привет!", return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=256)
+print(tok.decode(out[0], skip_special_tokens=True))
+```
+
+## GGUF (example)
+
+```bash
+python3 /path/to/llama.cpp/convert_hf_to_gguf.py /path/to/model --outtype bf16 --outfile model.bf16.gguf
+/path/to/llama.cpp/build/bin/llama-quantize model.bf16.gguf model.Q6_K.gguf Q6_K
+CUDA_VISIBLE_DEVICES=0,1 /path/to/llama.cpp/build/bin/llama-server -m model.Q6_K.gguf --n-gpu-layers 99 --split-mode layer --tensor-split 1,1

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-05-09-24",
+  "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": 14336,
+  "max_position_embeddings": 1024000,
+  "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": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 131074
+}

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.2"
+}

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00001-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed147b1bc8b485b72024ffeee6c75e9ab8dddd822a0e38c99ca61bff2d75f816
+size 1342197888

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00002-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a298abbf07c5711cde1f874e3bfd32b263b16d223fc21821a0745bb5d0226c2a
+size 1342197904

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00003-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d52f1a2cd0f2fd361e94c133cb1fa71630ce94f4c18ee65f8c23f641407e3ef
+size 1080076200

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00004-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0cf29e2759bfe4d7a96e195b408e1e0439ae19d402fcbcc600ad19607ff8ac
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00005-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c0007eab8fdf6546e65d74c497cf41e5877b094e73fc66b99e94f0dacbd50d
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00006-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe0b85cbbb3761cc06fb228e7e254e39d68f40c52a7e0ab4af6cb6685bceace
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00007-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d086036870e12cc363b568cc68c0f9cb4a2274ab5647eeba8fa52f4a16ed205b
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00008-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1a2bb26a1fdcc7bdc3d2b4a59732ffcd006ba170117fccd5700c58ad094935
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00009-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e42950814934bf8c89ef04d010029ea9297c87383ec264cfce598ae00e7059
+size 1090562096

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00010-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9c1b3aa004516a950fbc1a0dcd2aa4740f69e5b2045c64df7409551d392645
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00011-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eefb905db5bbaefb874ba5186a812597c3ae6eac02a72f02a7249c5f78eb17c5
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00012-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99b4d25309fb5359ec484d5288f8a43292929f142d35d958105896c12960818
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00013-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b28155a270f86fea50a5548fec83e27ca56f726e82067c083c9687edcb9a4e7
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00014-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc61ac1e876410edf757be8fe7f8b0af3f093b986b73ad0be059224617644c2
+size 1090562096

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00015-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c34fb4acc4ac436dd95fa96b8bb6b9c491af2361014eb695da2bfb013c237e
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00016-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fba941e9e6d6eacf945dbbd6d81f68018c25542d2b04add4b864d842ef99946
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00017-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b81af1b6d443f2b7130983d3b94a5e02daf44dd0e22b5d195833ad0afe502e
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00018-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e478473ed04add3945febdb599c6d46c9e7abe048fcff831281356336ff27a
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00019-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03964a3f635c9dbf39864ca29fc3608c62d4605f1c0e5c6b2c486a5853eefad9
+size 1090562104

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00020-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d58e325954a28fb12818d321fc95e65c0fba4539195afec61164dc42b3c3cc
+size 1090562088

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00021-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0354aad9a57376a83cb7e275381c1292deab8babfbadb93969639bd107cb7e1e
+size 1090562088

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00022-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596611f84d763180d95a36245271e2af2fb9e4ff6f1d307fafd5f5c942a0a107
+size 1090562088

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model-00023-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee234d3a8df1dd4c81bed0c5e2a886ca380347c62e4f64451d7ae79a4ee89fd
+size 10496240

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 24495648144}, "weight_map": {"lm_head.weight": "model-00001-of-00023.safetensors", "model.embed_tokens.weight": "model-00002-of-00023.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.norm.weight": "model-00023-of-00023.safetensors"}}

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/original_adapter/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-05-09-24
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/original_adapter/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-05-09-24",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 96,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 96,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/original_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e338736bfba1083e8e081c3d6ef857668843049a34d06e9e01bef06f7d57d74
+size 1368467752

Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>"
+  ],
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}