Upload MPTForCausalLM

README.md

@@ -0,0 +1,199 @@
+---
+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]

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "vinai/PhoGPT-4B-Chat",
+  "architectures": [
+    "MPTForCausalLM"
+  ],
+  "attn_config": {
+    "alibi": true,
+    "alibi_bias_max": 8,
+    "attn_impl": "torch",
+    "attn_pdrop": 0.0,
+    "attn_type": "multihead_attention",
+    "attn_uses_sequence_id": false,
+    "clip_qkv": null,
+    "prefix_lm": false,
+    "qk_gn": false,
+    "qk_ln": false,
+    "rope": false,
+    "rope_dail_config": {
+      "pos_idx_in_fp32": true,
+      "type": "original",
+      "xpos_scale_base": 512
+    },
+    "rope_hf_config": {
+      "factor": 1.0,
+      "type": "no_scaling"
+    },
+    "rope_impl": "dail",
+    "rope_theta": 10000,
+    "sliding_window_size": -1,
+    "softmax_scale": null
+  },
+  "auto_map": {
+    "AutoConfig": "vinai/PhoGPT-4B-Chat--configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "vinai/PhoGPT-4B-Chat--modeling_mpt.MPTForCausalLM"
+  },
+  "d_model": 3072,
+  "emb_pdrop": 0.0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "fc_type": "torch",
+  "ffn_config": {
+    "fc_type": "torch",
+    "ffn_type": "mptmlp"
+  },
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0.0,
+    "init_nonlinearity": "relu",
+    "init_std": null,
+    "name": "kaiming_normal_",
+    "verbose": 0
+  },
+  "init_device": "cpu",
+  "learned_pos_emb": false,
+  "logit_scale": null,
+  "max_seq_len": 8192,
+  "model_type": "mpt",
+  "n_heads": 24,
+  "n_layers": 32,
+  "no_bias": false,
+  "norm_type": "low_precision_layernorm",
+  "resid_pdrop": 0.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.3",
+  "use_cache": false,
+  "use_pad_tok_in_ffn": true,
+  "verbose": 0,
+  "vocab_size": 20480
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.43.3",
+  "use_cache": false
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ae0c43e0f2d2b2f7ba361166f1cb6fa0e8f95d3b862c80b421821ebd1085ab
+size 4958554400

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddede8714a86e3eb46f324a10c3ed97eca0901107e3f3906bdf6f997741e37ef
+size 4983726624

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e268faec959d438547a81e685f4b7df77d7f89cab95770f68182a9d1630c438
+size 4681674376

model.safetensors.index.json

@@ -0,0 +1,394 @@
+{
+  "metadata": {
+    "total_size": 14623911936
+  },
+  "weight_map": {
+    "transformer.blocks.0.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.0.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.1.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.10.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.10.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.10.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.11.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.11.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.12.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.13.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.14.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.15.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.16.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.17.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.18.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.19.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.2.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.2.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.20.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.ffn.down_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.20.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.attn.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.21.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.21.ffn.up_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.norm_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.norm_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.norm_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.blocks.21.norm_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.blocks.22.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.22.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.23.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.24.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.25.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.26.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.27.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.28.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.29.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.3.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.3.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.30.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.30.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.attn.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.ffn.down_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.ffn.up_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.norm_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.norm_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.norm_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.blocks.31.norm_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.blocks.4.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.4.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.5.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.6.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.7.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.8.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.attn.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.ffn.down_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.ffn.up_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.norm_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.norm_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.norm_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.blocks.9.norm_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.norm_f.bias": "model-00003-of-00003.safetensors",
+    "transformer.norm_f.weight": "model-00003-of-00003.safetensors",
+    "transformer.wte.weight": "model-00001-of-00003.safetensors"
+  }
+}