Upload HymbaForCausalLM

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 +1,143 @@
+{
+  "architectures": [
+    "HymbaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_hidden_size": -1,
+  "attn_implementation": "flash_attention_2",
+  "attn_implementation_new": "flash_attention_2",
+  "attn_only_wo_proj": true,
+  "auto_map": {
+    "AutoConfig": "configuration_hymba.HymbaConfig",
+    "AutoModelForCausalLM": "modeling_hymba.HymbaForCausalLM"
+  },
+  "bos_token_id": 128000,
+  "calc_logits_for_entire_prompt": false,
+  "conv_dim": {
+    "0": 3200,
+    "1": 3200,
+    "10": 3200,
+    "11": 3200,
+    "12": 3200,
+    "13": 3200,
+    "14": 3200,
+    "15": 3200,
+    "16": 3200,
+    "17": 3200,
+    "18": 3200,
+    "19": 3200,
+    "2": 3200,
+    "20": 3200,
+    "21": 3200,
+    "22": 3200,
+    "23": 3200,
+    "24": 3200,
+    "25": 3200,
+    "26": 3200,
+    "27": 3200,
+    "28": 3200,
+    "29": 3200,
+    "3": 3200,
+    "30": 3200,
+    "31": 3200,
+    "4": 3200,
+    "5": 3200,
+    "6": 3200,
+    "7": 3200,
+    "8": 3200,
+    "9": 3200
+  },
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "global_attn_idx": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "kq_head_dim": 64,
+  "kq_norm": "none",
+  "kv_reuse_every_i_layer": -1,
+  "kv_reuse_group": null,
+  "kv_weight_reuse": false,
+  "layer_type": [
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h",
+    "h"
+  ],
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 100,
+  "mamba_expand": 1,
+  "mamba_inner_layernorms": true,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 131072,
+  "memory_tokens_interspersed_every": 0,
+  "mlp_hidden_act": "silu",
+  "model_type": "hymba",
+  "num_attention_heads": 32,
+  "num_experts": 1,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "num_mamba": 1,
+  "num_memory_tokens": 0,
+  "orig_max_position_embeddings": 2048,
+  "output_router_logits": false,
+  "pad_token_id": null,
+  "pure_attn": true,
+  "rms_norm_eps": 1e-05,
+  "rope": true,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "rope_type": "ntk",
+  "router_aux_loss_coef": 0.001,
+  "seq_length": 8192,
+  "sliding_window": 1024,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "use_mamba_kernels": true,
+  "v_head_dim": 64,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.53.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ba47a55841e9deef83dbd3d329d5767f2a9598aa80d43b829d8c8784beef1c
+size 2471777104