Upload DeepseekV4ForCausalLM

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 +1,105 @@
+{
+  "architectures": [
+    "DeepseekV4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "compress_rates": {
+    "compressed_sparse_attention": 4,
+    "heavily_compressed_attention": 128
+  },
+  "compress_rope_theta": 160000,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "expert_dtype": "fp4",
+  "hc_eps": 1e-06,
+  "hc_mult": 4,
+  "hc_sinkhorn_iters": 20,
+  "head_dim": 512,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "index_head_dim": 128,
+  "index_n_heads": 2,
+  "index_topk": 512,
+  "initializer_range": 0.02,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "compressed_sparse_attention",
+    "heavily_compressed_attention"
+  ],
+  "max_position_embeddings": 1048576,
+  "mlp_bias": false,
+  "mlp_layer_types": [
+    "hash_moe",
+    "hash_moe",
+    "hash_moe",
+    "moe"
+  ],
+  "model_type": "deepseek_v4",
+  "moe_intermediate_size": 2048,
+  "n_routed_experts": 4,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 4,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 1,
+  "num_nextn_predict_layers": 1,
+  "o_groups": 8,
+  "o_lora_rank": 1024,
+  "output_router_logits": false,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.125,
+  "q_lora_rank": 1024,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "scale_fmt": "ue8m0",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "compress": {
+      "beta_fast": 32,
+      "beta_slow": 1,
+      "factor": 16,
+      "original_max_position_embeddings": 65536,
+      "partial_rotary_factor": 0.125,
+      "rope_theta": 160000,
+      "rope_type": "yarn",
+      "type": "yarn"
+    },
+    "main": {
+      "beta_fast": 32,
+      "beta_slow": 1,
+      "factor": 16,
+      "original_max_position_embeddings": 65536,
+      "partial_rotary_factor": 0.125,
+      "rope_theta": 10000,
+      "rope_type": "yarn",
+      "type": "yarn"
+    },
+    "partial_rotary_factor": 0.125,
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 1.5,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "scoring_func": "sqrtsoftplus",
+  "sliding_window": 128,
+  "swiglu_limit": 10.0,
+  "tie_word_embeddings": false,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.8.0.dev0",
+  "use_cache": true,
+  "vocab_size": 129280
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.8.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c13c81ca7fe2142e8aeab0454d611672bd3c605d4b94ad3a05d1d110cb1973
+size 7035839980