Upload folder using huggingface_hub

README.md

@@ -0,0 +1,50 @@
+---
+license: apache-2.0
+tags:
+- speculators
+- hass
+- eagle
+- speculative-decoding
+---
+
+# HASS Llama 3.1 8B with Layernorms
+
+This is a converted HASS (Eagle variant with layernorms) speculator checkpoint for Llama 3.1 8B, compatible with the [speculators](https://github.com/neuralmagic/speculators) library.
+
+## Model Details
+
+- **Original checkpoint**: [nm-testing/Eagle_Speculator_Llama_3_1_8B_TTT](https://huggingface.co/nm-testing/Eagle_Speculator_Llama_3_1_8B_TTT)
+- **Base model**: [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
+- **Architecture**: HASS (Eagle with layernorms enabled)
+- **Size**: 961MB (larger due to additional layernorm weights)
+
+## Usage
+
+```python
+from speculators.models.eagle import EagleSpeculator
+from transformers import AutoModelForCausalLM
+
+# Load the HASS speculator
+hass_model = EagleSpeculator.from_pretrained("nm-testing/hass-llama3.1-8b-layernorms")
+
+# Attach verifier model
+verifier = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
+hass_model.attach_verifier(verifier)
+
+# Use for speculative decoding
+# ... your speculative decoding code here ...
+```
+
+## Conversion Details
+
+This checkpoint was converted using:
+```bash
+speculators convert --eagle --layernorms \
+  nm-testing/Eagle_Speculator_Llama_3_1_8B_TTT \
+  ./hass-layernorms-converted \
+  meta-llama/Meta-Llama-3.1-8B-Instruct
+```
+
+## License
+
+Apache 2.0

config.json

@@ -17,21 +17,12 @@
       "name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
       "architectures": [
         "LlamaForCausalLM"
-      ],
-      "hidden_size": 4096,
-      "intermediate_size": 14336,
-      "vocab_size": 128256,
-      "max_position_embeddings": 131072,
-      "bos_token_id": 128000,
-      "eos_token_id": [
-        128001,
-        128008,
-        128009
       ]
     }
   },
   "architectures": [
-    "EagleSpeculator"
+    "EagleSpeculator",
+    "LlamaDecoderLayer"
   ],
   "transformer_layer_architecture": "LlamaDecoderLayer",
   "transformer_layer_config": {
@@ -59,76 +50,76 @@
     "attention_dropout": 0.0,
     "mlp_bias": false,
     "head_dim": 128,
-    "return_dict": true,
-    "output_hidden_states": false,
-    "output_attentions": false,
-    "torchscript": false,
-    "torch_dtype": null,
-    "use_bfloat16": false,
-    "tf_legacy_loss": false,
-    "pruned_heads": {},
     "tie_word_embeddings": false,
-    "chunk_size_feed_forward": 0,
-    "is_encoder_decoder": false,
-    "is_decoder": false,
-    "cross_attention_hidden_size": null,
-    "add_cross_attention": false,
-    "tie_encoder_decoder": false,
-    "max_length": 20,
-    "min_length": 0,
-    "do_sample": false,
-    "early_stopping": false,
-    "num_beams": 1,
-    "num_beam_groups": 1,
-    "diversity_penalty": 0.0,
-    "temperature": 1.0,
-    "top_k": 50,
-    "top_p": 1.0,
-    "typical_p": 1.0,
-    "repetition_penalty": 1.0,
-    "length_penalty": 1.0,
-    "no_repeat_ngram_size": 0,
-    "encoder_no_repeat_ngram_size": 0,
-    "bad_words_ids": null,
-    "num_return_sequences": 1,
-    "output_scores": false,
-    "return_dict_in_generate": false,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "remove_invalid_values": false,
-    "exponential_decay_length_penalty": null,
-    "suppress_tokens": null,
-    "begin_suppress_tokens": null,
-    "architectures": null,
-    "finetuning_task": null,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "tokenizer_class": null,
-    "prefix": null,
     "bos_token_id": 128000,
-    "pad_token_id": null,
     "eos_token_id": [
       128001,
       128008,
       128009
     ],
-    "sep_token_id": null,
-    "decoder_start_token_id": null,
-    "task_specific_params": null,
-    "problem_type": null,
-    "_name_or_path": "",
     "transformers_version": "4.52.4",
     "model_type": "llama"
   },
   "layernorms": true,
   "fusion_bias": false,
   "_name_or_path": "",
-  "model_type": "speculator_model",
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.52.4",
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": null,
+  "pad_token_id": null,
+  "eos_token_id": null,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "task_specific_params": null,
+  "problem_type": null
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa5cab90dfa53d5ca18bf2925b728c9315ed7f16965b2d99d1bb96928efedca
-size 3108046176
+oid sha256:4151564cb2c9bc7f762af53d68a94e5924f60848992c1814128bafce576a8704
+size 1006699768