Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,222 @@
+{#- ----------‑‑‑ special token variables ‑‑‑---------- -#}
+{%- set HYTK = ':opensource' %}
+{%- set eos_token = '<｜hy_eos{}｜>'.format(HYTK) %}
+{%- set bos_token = '<｜hy_begin_of_sentence{}｜>'.format(HYTK) %}
+{%- set pad_token = '<｜hy_pad{}｜>'.format(HYTK) %}
+{%- set user_token = '<｜hy_User{}｜>'.format(HYTK) %}
+{%- set assistant_token = '<｜hy_Assistant{}｜>'.format(HYTK) %}
+{%- set think_begin_token = '<think{}>'.format(HYTK) %}
+{%- set think_end_token = '</think{}>'.format(HYTK) %}
+{%- set toolcalls_begin_token = '<tool_calls{}>'.format(HYTK) %}
+{%- set toolcalls_end_token = '</tool_calls{}>'.format(HYTK) %}
+{%- set toolcall_begin_token = '<tool_call{}>'.format(HYTK) %}
+{%- set toolcall_end_token = '</tool_call{}>'.format(HYTK) %}
+{%- set toolsep_token = '<tool_sep{}>'.format(HYTK) %}
+{%- set argkey_begin_token = '<arg_key{}>'.format(HYTK) %}
+{%- set argkey_end_token = '</arg_key{}>'.format(HYTK) %}
+{%- set argvalue_begin_token = '<arg_value{}>'.format(HYTK) %}
+{%- set argvalue_end_token = '</arg_value{}>'.format(HYTK) %}
+{%- set toolresponses_begin_token = '<tool_responses{}>'.format(HYTK) %}
+{%- set toolresponses_end_token = '</tool_responses{}>'.format(HYTK) %}
+{%- set toolresponse_begin_token = '<tool_response{}>'.format(HYTK) %}
+{%- set toolresponse_end_token = '</tool_response{}>'.format(HYTK) %}
+{%- set reasoning_mode_token = '<｜reasoning_mode{}｜>'.format(HYTK) %}
+
+{#- ----------‑‑‑ hyperparameters variables ‑‑‑---------- -#}
+{%- if not add_generation_prompt is defined %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- if not preserved_thinking is defined %}
+    {%- if not tools %}
+        {%- set preserved_thinking = false %}
+    {%- else %}
+        {%- set preserved_thinking = true %}
+    {%- endif %}
+{%- endif %}
+{%- if not is_training is defined %}
+    {%- set is_training = false %}
+{%- endif %}
+
+{%- if not reasoning_effort is defined %}
+    {%- set reasoning_effort = 'no_think' %}
+{%- elif reasoning_effort not in ['high', 'low', 'no_think'] %}
+    {%- if reasoning_effort is none %}
+        {{- raise_exception('reasoning_effort error : None, should be no_think/low/high') }}
+    {%- else %}
+        {{- raise_exception('reasoning_effort error : ' + reasoning_effort + ', should be no_think/low/high') }}
+    {%- endif %}
+{%- endif %}
+
+{%- if fallback_strategy is defined and fallback_strategy == 'reasoning_toolcall_retry' %}
+    {%- set reasoning_effort = 'high' %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- if not raw_last_assistant is defined %}
+    {%- set raw_last_assistant = false %}
+{%- endif %}
+
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- elif content is none -%}
+        {{- '' }}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- set ns = namespace(last_user_index=-1) %}
+{%- set sp_ns = namespace(system_prompt='', is_first_sp=true) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {%- set sp_ns.system_prompt = sp_ns.system_prompt + visible_text(message['content']) %}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.last_user_index = loop.index0 %}
+    {%- endif %}
+{%- endfor %}
+{%- if reasoning_effort is defined and reasoning_effort is string and reasoning_effort != '' and not tools %}
+    {%- set sp_ns.system_prompt = sp_ns.system_prompt + reasoning_mode_token + 'reasoning_effort:' + reasoning_effort %}
+{%- endif %}
+{{- bos_token }}
+{{- sp_ns.system_prompt }}
+{%- if tools %}
+    {%- if sp_ns.system_prompt != '' %}
+        {{- '\n\n# Tools\n\nYou may call one or more functions to assist with the user query.' }}
+    {%- else %}
+        {{- '# Tools\n\nYou may call one or more functions to assist with the user query.' }}
+    {%- endif %}
+    {{- '\n\nYou are provided with function signatures within <tools></tools> XML tags:' }}
+    {{- '\n<tools>\n' }}
+    {%- for tool in tools %}
+        {%- if loop.index0 > 0 %}
+            {{- '\n' }}
+        {%- endif %}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- '\n</tools>\n\n' }}
+    {{- 'For function call returns, you should first print ' + toolcalls_begin_token + '\n' }}
+    {{- 'For each function call, you should return object like:\n' }}
+    {{- toolcall_begin_token + '{function-name}' + toolsep_token + '\n' }}
+    {{- argkey_begin_token + '{arg-key-1}' + argkey_end_token + '\n' }}
+    {{- argvalue_begin_token + '{arg-value-1}' + argvalue_end_token + '\n' }}
+    {{- argkey_begin_token + '{arg-key-2}' + argkey_end_token + '\n' }}
+    {{- argvalue_begin_token + '{arg-value-2}' + argvalue_end_token + '\n' }}
+    {{- '...\n' }}
+    {{- toolcall_end_token + '\n' }}
+    {%- if reasoning_effort is defined and reasoning_effort is string and reasoning_effort != '' %}
+        {{- 'At the end of function call returns, you should print ' + toolcalls_end_token + reasoning_mode_token + 'reasoning_effort:' + reasoning_effort }}
+    {%- else %}
+        {{- 'At the end of function call returns, you should print ' + toolcalls_end_token }}
+    {%- endif %}
+{%- endif %}
+
+{%- set prev_ns = namespace(is_tool=false, is_tool_first=true) %}
+{%- set last_ns = namespace(last_is_assistant=false) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'user' %}
+        {%- if prev_ns.is_tool %}
+            {{- toolresponses_end_token }}
+        {%- endif %}
+        {{- user_token + visible_text(message['content']) }}
+        {%- set prev_ns.is_tool = false %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' %}
+        {%- if is_training %}
+            {%- if 'reasoning_content' in message and message['reasoning_content'] is string %}
+                {%- set rc = message['reasoning_content'] %}
+            {%- elif 'reasoning' in message and message['reasoning'] is string %}
+                {%- set rc = message['reasoning'] %}
+            {%- else %}
+                {%- set rc = none %}
+            {%- endif %}
+            {%- if rc is not none %}
+                {%- set content = think_begin_token + rc + think_end_token + visible_text(message['content']) %}
+            {%- else %}
+                {%- set content = think_begin_token + think_end_token + visible_text(message['content']) %}
+            {%- endif %}
+        {%- else %}
+            {%- if ((preserved_thinking is defined and preserved_thinking) or loop.index0 > ns.last_user_index) %}
+                {%- if 'reasoning_content' in message and message['reasoning_content'] is string %}
+                    {%- set rc = message['reasoning_content'] %}
+                {%- elif 'reasoning' in message and message['reasoning'] is string %}
+                    {%- set rc = message['reasoning'] %}
+                {%- else %}
+                    {%- set rc = none %}
+                {%- endif %}
+                {%- if rc is not none %}
+                    {%- set content = think_begin_token + rc + think_end_token + visible_text(message['content']) %}
+                {%- else %}
+                    {%- set content = think_begin_token + think_end_token + visible_text(message['content']) %}
+                {%- endif %}
+            {%- else %}
+                {%- set content = think_begin_token + think_end_token + visible_text(message['content']) %}
+            {%- endif %}
+        {%- endif %}
+        {%- if prev_ns.is_tool %}
+            {{- toolresponses_end_token }}
+        {%- endif %}
+        {{- assistant_token }}
+        {%- if message['tool_calls'] is defined and message['tool_calls'] %}
+            {%- set prev_ns.is_tool_first = true %}
+            {{- content }}
+            {{- toolcalls_begin_token + '\n' }}
+            {%- for tool in message['tool_calls'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {{- toolcall_begin_token + tool['function']['name'] + toolsep_token + '\n' }}
+                {%- for key, value in arguments.items() %}
+                    {{- argkey_begin_token + key + argkey_end_token + '\n' }}
+                    {%- if value is not string %}
+                        {%- set value = value | tojson(ensure_ascii=False) %}
+                    {%- endif %}
+                    {{- argvalue_begin_token + value + argvalue_end_token + '\n' }}
+                {%- endfor %}
+                {{- toolcall_end_token + '\n' }}
+            {%- endfor %}
+            {{- toolcalls_end_token + eos_token }}
+        {%- else %}
+            {%- if loop.last and raw_last_assistant %}
+                {{- visible_text(message['content']) }}
+            {%- elif not loop.last or is_training %}
+                {{- content + eos_token }}
+            {%- else %}
+                {{- content }}
+            {%- endif %}
+        {%- endif %}
+        {%- set prev_ns.is_tool = false %}
+    {%- endif %}
+    {%- if message['role'] == 'tool' %}
+        {%- set prev_ns.is_tool = true %}
+        {%- if prev_ns.is_tool_first %}
+            {{- toolresponses_begin_token + '\n' }}
+            {%- set prev_ns.is_tool_first = false %}
+        {%- endif %}
+        {{- toolresponse_begin_token + '\n' + visible_text(message['content']) + '\n' + toolresponse_end_token + '\n' }}
+    {%- endif %}
+    {%- if loop.last and message['role'] == 'assistant' %}
+        {%- set last_ns.last_is_assistant = true %}
+    {%- endif %}
+
+{%- endfor %}
+{%- if prev_ns.is_tool %}
+    {{- toolresponses_end_token }}
+{%- endif %}
+{%- if add_generation_prompt %}
+    {%- if not last_ns.last_is_assistant %}
+        {%- if reasoning_effort is defined and reasoning_effort in ['low', 'high'] %}
+            {{- assistant_token + think_begin_token }}
+        {%- elif reasoning_effort is defined and reasoning_effort == 'no_think' %}
+            {{- assistant_token + think_begin_token + think_end_token }}
+        {%- else %}
+            {{- assistant_token }}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,186 @@
+{
+  "architectures": [
+    "HYV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 120000,
+  "dtype": "bfloat16",
+  "enable_attention_fp32_softmax": false,
+  "enable_lm_head_fp32": true,
+  "enable_moe_fp32_combine": false,
+  "eod_token_id": 120026,
+  "eos_token_id": 120025,
+  "expert_hidden_dim": 1536,
+  "first_k_dense_replace": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.006,
+  "intermediate_size": 13312,
+  "max_position_embeddings": 262144,
+  "mlp_bias": false,
+  "mlp_layer_types": [
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "hy_v3",
+  "moe_intermediate_size": 1536,
+  "moe_router_enable_expert_bias": true,
+  "moe_router_use_sigmoid": true,
+  "num_attention_heads": 64,
+  "num_experts": 192,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "num_shared_experts": 1,
+  "output_router_logits": true,
+  "pad_token_id": 120002,
+  "qk_norm": true,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": false,
+    "dynamic": {
+      "+:.*experts": {
+        "bits": 4,
+        "group_size": 64
+      },
+      "+:.*shared_mlp": {
+        "bits": 4,
+        "group_size": 64
+      }
+    },
+    "format": "gptq",
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "act_group_aware": null,
+      "auto_forward_data_parallel": true,
+      "damp_auto_increment": null,
+      "damp_percent": null,
+      "dense_vram_strategy": "exclusive",
+      "dense_vram_strategy_devices": null,
+      "fallback": {
+        "smooth": null,
+        "strategy": "rtn",
+        "threshold": "0.5%"
+      },
+      "foem": null,
+      "gc_mode": "on_stage_end",
+      "gptaq": null,
+      "moe_vram_strategy": "exclusive",
+      "moe_vram_strategy_devices": null,
+      "mse": null,
+      "offload_to_disk": true,
+      "offload_to_disk_path": "/home/ubuntu/tmp_for_install/gptqmodel_kctb93p5",
+      "pack_impl": "cpu",
+      "quantizer": [
+        "gptqmodel:7.2.0"
+      ],
+      "static_groups": null,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel",
+      "wait_for_submodule_finalizers": true,
+      "weight_only": {
+        "smooth": null
+      }
+    },
+    "method": "gptq",
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 11158840.0,
+    "rope_type": "default"
+  },
+  "route_norm": true,
+  "router_scaling_factor": 2.826,
+  "sep_token_id": 120007,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.9.0",
+  "use_cache": true,
+  "use_grouped_mm": false,
+  "vocab_size": 120832
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 120000,
+  "do_sample": true,
+  "eos_token_id": 120025,
+  "pad_token_id": 120002,
+  "temperature": 0.9,
+  "top_k": -1,
+  "top_p": 1,
+  "transformers_version": "5.9.0"
+}

model-00001-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c985f4f1c5a6b5579ae448626673983051ab845d8a18dd52cc69d1a97d959109
+size 4293654256

model-00002-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c494d0b4dd7412630f83b3670dbf943fe29ea32f52993e29057cf1eb404b70
+size 4293928000

model-00003-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8f50831d63b65940c3b5e5f38d32022f10cb1e1846bfce5f95090dd029a0a7
+size 4293938352

model-00004-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd1e7e3a044bd2e958ee0861fd496421fe27e74e59aeb5e2bfa7535adec06a3
+size 4293928112

model-00005-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f3513a80e944a6eb679d51f706a80841e6224b9b02c8aedb214b0909b53200
+size 4293929520

model-00006-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1ef25599479adc94474b61d0edff3b38cd2450a209513c2df86ee0d2e7afbf
+size 4293943712

model-00007-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc24033601982270bbb632f28794bdc580e4529c4ed713af913616b95b0bd21b
+size 4293933472

model-00008-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0552cc46d71d2363e15e0c5869795b8ad3a36e402277e63fcfa241ac1b92a1ef
+size 4293933464

model-00009-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e18e113c699ee9668fbba196117923391b21d617daac58391c6cf6faa90a064
+size 4295537480

model-00010-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6be1a074c5cd05a9ddf432ddc67678a25cccb22205d2fa53881c0bed2dd9c6e
+size 4294195576

model-00011-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7298b1f4c48b9b5bfebadbdbe42f23226dd73cfc2acfb1f5a0a9c3442d906812
+size 4293933096

model-00012-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81122d75f3f508bba12f0f3e7c8f4c4af0e3ff4059177d20cb0cce4e0db9d83
+size 4293933088

model-00013-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a934bf4158721e67f8ef5f1dca6954d3591a4c3a4edf5e7a6c9978200d45d3c
+size 4293943672

model-00014-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69481ef9b5a40b3052f0e388e6cf673a6a9982bdda91f6d1ce6308d8ee4182b
+size 4293933472

model-00015-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28df3d6839840969914dbd05812b32ad92d211ece19348d16a6141eb8cfe8af9
+size 4293933464

model-00016-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:034a94f23b5cd25e30af0448e515bae00a406e269162ae87440961171257541f
+size 4295537568

model-00017-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e895a9f3f650993032d580a4233edbed1a0292f1d92a9bc1dd24785eeafb597
+size 4294195552

model-00018-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d76671c2c3a8702515a51efd27d392d1a48380e700aad8dd4d1cbf9ea7bd8e
+size 4293933096

model-00019-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945e914cc73122db264afbfba124b44596aae2704e7dbf4411fe21a80b678a35
+size 4293933088

model-00020-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a81cc3d9b1068cd696e801f1f13ce746d5440f164ff6c44e9e498300ef12eb9
+size 4293943512

model-00021-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2aece0073bf77a86a8bd7031b23611645bbf667f67374dbe875d3b753fbec8a
+size 4293933472

model-00022-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86617a8db0915465040ac052dc65fb85a8da514c1f1f7fd2188aa75219cc1f7
+size 4293933464

model-00023-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd5479cb1ce661c8bb625affecbeb58163ba853078586434af1e741e4b2ceea
+size 4294240736

model-00024-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249fe06d3a1d486963d67fc5f76a295b7c41975903179f8c6af3c7744dc84341
+size 4295492576

model-00025-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b091d5970f0107e538d12e18aedec4d99b7d2ae01e4c9af55fd2a37f78353bdd
+size 4293933096

model-00026-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f16badfd7cb9640fd0ac838c653db9818dc4848611c01505035e4d1c304077
+size 4293933088

model-00027-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3233f72403a3ae124ef084d28520b6254b2ec11d4cfb3b6ba6d3f28f6405ba7f
+size 4293943392

model-00028-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8760eb98c11ec6db2e2171dfe3f5257f4745f4d38a153888bca123575a4c6237
+size 4293933472

model-00029-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3789e71595a6bf4976f7f46d599d11edf474a988235fa0d8653e43a238da395e
+size 4293933464

model-00030-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bc73921003f0392c4ecb895bea75926680af9a988c5f6b69066d874e468bb1
+size 4293943712

model-00031-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93215ccd6914465d7a5e3a19db16f3a83e90af21c345504f78faa848f4e13f2
+size 4295527256

model-00032-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11186acdb95df13209d89e2fbca5a81503bc4c380d15131b07232d27309151b0
+size 4294195576

model-00033-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb530c0f32cfdada3881f3db822f3652e9bfff084030f4d7067dc1d0f9e6ad6
+size 4293933088

model-00034-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d400147e97e1f8e68d8c829e8682e6bd65d465ecf6f1b3d738460385534cba3
+size 4293943336

model-00035-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26ef0c480effe4295d57e0d5ed2f12ba6508e681802ae7e8f58761909fc8472
+size 4293933352

model-00036-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436927dbae590fdd89f5c09815d95e6ad5b8caa4862bdf02ae5818bd23e72e86
+size 4293933464

model-00037-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57171435aa68a20ad52ea96f077be4d0e20ef49dda6a5d4320d5b43617f640ee
+size 4293943712

model-00038-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71dbcd3fb225f5311f043cfc07719214eac8df830aa1f24a1bba7bf53cf42212
+size 2197831632

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa74447e93a8765234c8db1270b9c65a54945a83f6ac66e81c1879c303971f37
+size 16735577

quantize_config.json

@@ -0,0 +1,54 @@
+{
+  "bits": 4,
+  "dynamic": {
+    "+:.*shared_mlp": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "+:.*experts": {
+      "bits": 4,
+      "group_size": 64
+    }
+  },
+  "group_size": 128,
+  "desc_act": false,
+  "lm_head": false,
+  "method": "gptq",
+  "quant_method": "gptq",
+  "format": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:7.2.0"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": null,
+    "damp_auto_increment": null,
+    "static_groups": null,
+    "true_sequential": true,
+    "mse": null,
+    "gptaq": null,
+    "foem": null,
+    "act_group_aware": null,
+    "fallback": {
+      "strategy": "rtn",
+      "threshold": "0.5%",
+      "smooth": null
+    },
+    "offload_to_disk": true,
+    "offload_to_disk_path": "/home/ubuntu/tmp_for_install/gptqmodel_kctb93p5",
+    "pack_impl": "cpu",
+    "gc_mode": "on_stage_end",
+    "wait_for_submodule_finalizers": true,
+    "auto_forward_data_parallel": true,
+    "dense_vram_strategy": "exclusive",
+    "dense_vram_strategy_devices": null,
+    "moe_vram_strategy": "exclusive",
+    "moe_vram_strategy_devices": null,
+    "weight_only": {
+      "smooth": null
+    }
+  },
+  "sym": true
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜hy_begin_of_sentence:opensource｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜hy_eos:opensource｜>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<｜hy_pad:opensource｜>",
+  "token_suffix": ":opensource",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "_commit_hash": null
+}