remove model

app.py

@@ -229,4 +229,4 @@ iface = gr.Interface(
 )
 
 # Launch the interface
-iface.launch()
+iface.launch()

repllama-instruct-hard-positives-v2-joint-full-weights/.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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

repllama-instruct-hard-positives-v2-joint-full-weights/README.md

@@ -1,199 +0,0 @@
----
-library_name: transformers
-tags: []
----
-
-# 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. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **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]

repllama-instruct-hard-positives-v2-joint-full-weights/config.json

@@ -1,29 +0,0 @@
-{
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
-  "architectures": [
-    "LlamaModel"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
-  "use_cache": true,
-  "vocab_size": 32000
-}

repllama-instruct-hard-positives-v2-joint-full-weights/model-00001-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7bde1bc1cbdf9b2c4518c0162fc68ac4537f0050a91d95a2aa0d07da1090898c
-size 4840396112

repllama-instruct-hard-positives-v2-joint-full-weights/model-00002-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2283f86d973d94a4269bf4cfb6fecdef4d9291715c560f5d1a7f748ec102fd16
-size 4857206528

repllama-instruct-hard-positives-v2-joint-full-weights/model-00003-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de1e51d467d19f8dd6c205875199fff4a8bbe57fc61f48e5aa8f1df6dbff8cc9
-size 4857206576

repllama-instruct-hard-positives-v2-joint-full-weights/model-00004-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6ce960be6d452e3861a1c131172b61b00a63ace3de0320b8a289d7e164eb794
-size 4857206576

repllama-instruct-hard-positives-v2-joint-full-weights/model-00005-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bf583366f1e8a383c04c1be7495e8b75a7457e33e8cafc990c6bbc9c7e8dd5f7
-size 4857206576

repllama-instruct-hard-positives-v2-joint-full-weights/model-00006-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:86c4cb7331c5d18cdbbce5581f3b31126d8a0bd0f6d3bd4fe2a5aae35a6e91d3
-size 2160183864

repllama-instruct-hard-positives-v2-joint-full-weights/model.safetensors.index.json

@@ -1,297 +0,0 @@
-{
-  "metadata": {
-    "total_size": 26429374464
-  },
-  "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "norm.weight": "model-00006-of-00006.safetensors"
-  }
-}