Upload FlaxGemmaForCausalLM

README.md

@@ -0,0 +1,201 @@
+---
+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 +1,27 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 256000
+}

flax_model-00001-of-00004.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b306610d0a17f4f059652d13cd60e54068f05a6b745c0ec7b834887f2ef202fe
+size 4894835345

flax_model-00002-of-00004.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778bbf6e583457d67aacf0378ea313ff46ef64ca1fad857211f2764599e8c361
+size 4982947525

flax_model-00003-of-00004.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2491c1e151f06586b356d6b3f48ef7f9a9299d8bffa967a43519302eaed5d67
+size 4982947522

flax_model-00004-of-00004.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf9beb4ba9a949460e5d1850ad0ccf01586afbc0e3885290804a69d3b1402ea6
+size 2214643337

flax_model.msgpack.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 17075361792
+  },
+  "weight_map": {
+    "model/embed_tokens/embedding": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/input_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/mlp/down_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/mlp/gate_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/mlp/up_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/post_attention_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/self_attn/k_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/self_attn/o_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/self_attn/q_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/0/self_attn/v_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/input_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/mlp/down_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/mlp/gate_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/mlp/up_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/post_attention_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/self_attn/k_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/self_attn/o_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/self_attn/q_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/1/self_attn/v_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/input_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/mlp/down_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/mlp/gate_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/mlp/up_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/post_attention_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/self_attn/k_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/self_attn/o_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/self_attn/q_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/10/self_attn/v_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/input_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/mlp/down_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/mlp/gate_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/mlp/up_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/post_attention_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/self_attn/k_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/self_attn/o_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/self_attn/q_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/11/self_attn/v_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/input_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/mlp/down_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/mlp/gate_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/mlp/up_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/post_attention_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/self_attn/k_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/self_attn/o_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/self_attn/q_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/12/self_attn/v_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/input_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/mlp/down_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/mlp/gate_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/mlp/up_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/post_attention_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/self_attn/k_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/self_attn/o_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/self_attn/q_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/13/self_attn/v_proj/kernel": "flax_model-00001-of-00004.msgpack",
+    "model/layers/14/input_layernorm/weight": "flax_model-00001-of-00004.msgpack",
+    "model/layers/14/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/14/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/14/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/14/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/14/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/14/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/14/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/14/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/15/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/16/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/17/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/18/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/19/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/2/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/20/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/mlp/down_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/mlp/gate_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/mlp/up_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/post_attention_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/self_attn/k_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/self_attn/o_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/self_attn/q_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/21/self_attn/v_proj/kernel": "flax_model-00002-of-00004.msgpack",
+    "model/layers/22/input_layernorm/weight": "flax_model-00002-of-00004.msgpack",
+    "model/layers/22/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/22/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/22/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/22/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/22/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/22/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/22/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/22/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/23/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/24/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/25/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/26/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/27/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/3/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/4/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/mlp/down_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/mlp/gate_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/mlp/up_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/post_attention_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/self_attn/k_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/self_attn/o_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/self_attn/q_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/5/self_attn/v_proj/kernel": "flax_model-00003-of-00004.msgpack",
+    "model/layers/6/input_layernorm/weight": "flax_model-00003-of-00004.msgpack",
+    "model/layers/6/mlp/down_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/6/mlp/gate_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/6/mlp/up_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/6/post_attention_layernorm/weight": "flax_model-00004-of-00004.msgpack",
+    "model/layers/6/self_attn/k_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/6/self_attn/o_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/6/self_attn/q_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/6/self_attn/v_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/input_layernorm/weight": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/mlp/down_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/mlp/gate_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/mlp/up_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/post_attention_layernorm/weight": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/self_attn/k_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/self_attn/o_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/self_attn/q_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/7/self_attn/v_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/input_layernorm/weight": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/mlp/down_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/mlp/gate_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/mlp/up_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/post_attention_layernorm/weight": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/self_attn/k_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/self_attn/o_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/self_attn/q_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/8/self_attn/v_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/input_layernorm/weight": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/mlp/down_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/mlp/gate_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/mlp/up_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/post_attention_layernorm/weight": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/self_attn/k_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/self_attn/o_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/self_attn/q_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/layers/9/self_attn/v_proj/kernel": "flax_model-00004-of-00004.msgpack",
+    "model/norm/weight": "flax_model-00004-of-00004.msgpack"
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.1"
+}