commit 95a90d4e08b73741b9f299bab76d546f1f8f7794 Author: ModelHub XC Date: Wed May 13 13:40:29 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: In2Training/FILM-7B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c05ebe1 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +license: apache-2.0 +language: +- en +--- + +# FILM-7B + +

+ 💻 [Github Repo] • 📃 [Paper] • ⚓ [VaLProbing-32K] +

+ +**FILM-7B is a 32K-context LLM that overcomes the lost-in-the-middle problem.** +It is trained from Mistral-7B-Instruct-v0.2 by applying Information-Intensie (In2) Training. +FILM-7B achieves near-perfect performance on probing tasks, SOTA-level performance on real-world long-context tasks among ~7B size LLMs, and does not compromise the short-context performance. + +## Model Usage + +The system tempelate for FILM-7B: +```text +'''[INST] Below is a context and an instruction. Based on the information provided in the context, write a response for the instruction. + +### Context: +{YOUR LONG CONTEXT} + +### Instruction: +{YOUR QUESTION & INSTRUCTION} [/INST] +''' +``` + +## Probing Results + +To reproduce the results on our VaL Probing, see the guidance in [https://github.com/microsoft/FILM/tree/main/VaLProbing](https://github.com/microsoft/FILM/tree/main/VaLProbing). + +

+ +
+

+ +## Real-World Long-Context Tasks + +To reproduce the results on real-world long-context tasks, see the guidance in [https://github.com/microsoft/FILM/tree/main/real_world_long](https://github.com/microsoft/FILM/tree/main/real_world_long). + +

+ +
+

+ +## Short-Context Tasks + +To reproduce the results on short-context tasks, see the guidance in [https://github.com/microsoft/FILM/tree/main/short_tasks](https://github.com/microsoft/FILM/tree/main/short_tasks). + +

+ +
+

+ +## 📝 Citation +``` +@misc{an2024make, + title={Make Your LLM Fully Utilize the Context}, + author={Shengnan An and Zexiong Ma and Zeqi Lin and Nanning Zheng and Jian-Guang Lou}, + year={2024}, + eprint={2404.16811}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` + +Disclaimer: This model is strictly for research purposes, and not an official product or service from Microsoft. diff --git a/config.json b/config.json new file mode 100644 index 0000000..07e6391 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "In2Training/FILM-7B", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.37.1", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/figures/probing_results.png b/figures/probing_results.png new file mode 100644 index 0000000..318d431 Binary files /dev/null and b/figures/probing_results.png differ diff --git a/figures/probing_results_new.png b/figures/probing_results_new.png new file mode 100644 index 0000000..cda6ae2 Binary files /dev/null and b/figures/probing_results_new.png differ diff --git a/figures/real_world_long.png b/figures/real_world_long.png new file mode 100644 index 0000000..12fb96d Binary files /dev/null and b/figures/real_world_long.png differ diff --git a/figures/short.png b/figures/short.png new file mode 100644 index 0000000..503c219 Binary files /dev/null and b/figures/short.png differ diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2209466 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.37.1" +} diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..c71c913 --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:921ec14da1b7586c8532374cefea96f87e378eb0eb03e43ef2c64096b96fe3d2 +size 4987196936 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..3d896cc --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b2157f2a3bccddf188ec6ab6a31e680fad95f97bf08791182ae51b1ee53e23 +size 4899116440 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..50053c4 --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60cafca5cc04c1d36fe48f67ed0aab9b00be1d165f2583a9f250417c9e56c9d2 +size 4999813120 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..fae49bb --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2173505c7d771d00f0c55735143953e73f037a05e280ff23820707ab0c309f4a +size 4999813128 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..d223fce --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:075b62387c6d6397e7aef93cc2bd041c0383008315936a959e45093fd796ad73 +size 4832007496 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..3b13600 --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c969ed61acc35e9fbc314ffd8d1729d24b4057684e3dff619349b36f5e32cd +size 4249014896 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..39ca3d3 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 28966928384 + }, + "weight_map": { + "lm_head.weight": "model-00006-of-00006.safetensors", + "model.embed_tokens.weight": "model-00001-of-00006.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.norm.weight": "model-00006-of-00006.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..14761dc --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..094333c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 32768, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}